https://news.y0.exchange/article/bitdeer-stock-rises-on-michael-potter-cfo-appointment y0 News en 2026-05-27T15:50:14.000Z Bitdeer Stock Rises on Michael Potter CFO Appointment bitdeer, cfo-appointment, ai-expansion, data-centers, crypto-infrastructure, bitcoin-mining, capital-allocation https://news.y0.exchange/article/grayscale-hyperliquid-biggest-crypto-breakout-success y0 News en 2026-05-27T15:38:48.000Z Grayscale: Hyperliquid Biggest Crypto Breakout Success hyperliquid, perpetual-futures, decentralized-exchange, hype-token, defi-revenue, grayscale-research, trading-volume, market-cap https://news.y0.exchange/article/dtcc-stellar-partnership-tokenized-securities-by-2027 y0 News en 2026-05-27T15:26:19.000Z DTCC Stellar Partnership: Tokenized Securities by 2027 dtcc, stellar, tokenized-securities, institutional-adoption, blockchain, custody, settlement, fintech https://news.y0.exchange/article/tsmc-stock-jumps-5-on-record-profits-and-employee-bonuses y0 News en 2026-05-27T15:21:15.000Z TSMC Stock Jumps 5% on Record Profits and Employee Bonuses tsmc, ai-chips, semiconductor-industry, earnings, employee-benefits, stock-analysis, chip-manufacturing https://news.y0.exchange/article/hsbc-microsoft-anthropic-deal-could-generate-43b-by-2030 y0 News en 2026-05-27T15:15:06.000Z HSBC: Microsoft Anthropic Deal Could Generate $43B by 2030 microsoft, msft, anthropic, ai, partnership, hsbc-analysis, revenue-forecast, enterprise-ai https://news.y0.exchange/article/mastercard-obtains-bitlicense-for-ny-crypto-operations y0 News en 2026-05-27T15:14:19.000Z Mastercard Obtains BitLicense for NY Crypto Operations mastercard, bitlicense, nysdfs, regulation, crypto-payments, institutional-adoption, digital-assets, compliance https://news.y0.exchange/article/fedex-hits-record-high-on-jp-morgan-buy-upgrade y0 News en 2026-05-27T15:08:22.000Z FedEx Hits Record High on J.P. Morgan Buy Upgrade fedex, stock-upgrade, spinoff, jp-morgan, logistics, corporate-restructuring, freight https://news.y0.exchange/article/dtcc-tokenization-service-gets-sec-approval-launches-by-2027 y0 News en 2026-05-27T15:06:19.000Z DTCC Tokenization Service Gets SEC Approval, Launches by 2027 dtcc, tokenization, stellar, sec-approval, institutional-adoption, blockchain-settlement, securities, regulatory-clarity https://news.y0.exchange/article/mnst-stock-hits-52-week-high-after-strong-q1-results y0 News en 2026-05-27T15:01:30.000Z MNST Stock Hits 52-Week High After Strong Q1 Results monster-beverage, mnst, earnings, q1-results, stock-price, analyst-targets, energy-drinks https://news.y0.exchange/article/mgm-stock-soars-9-on-jpmorgan-overweight-upgrade y0 News en 2026-05-27T15:00:46.000Z MGM Stock Soars 9% on JPMorgan Overweight Upgrade mgm-resorts, jpmorgan-upgrade, las-vegas, hospitality-stocks, equities, consumer-spending, analyst-rating, stock-rally https://news.y0.exchange/article/ai-advancement-ivf-innovation-keeping-pace-with-technology y0 News en 2026-05-27T12:10:00.000Z AI Advancement & IVF Innovation: Keeping Pace With Technology artificial-intelligence, biotechnology, healthcare-innovation, ivf-technology, ai-applications, medical-advancement, technology-news, innovation-trends https://news.y0.exchange/article/spacex-ipo-and-space-data-centers-financial-reality y0 News en 2026-05-27T10:00:00.000Z SpaceX IPO and Space Data Centers: Financial Reality spacex, ipo, data-centers, space-infrastructure, satellite-internet, aerospace, capital-markets https://news.y0.exchange/article/brickanything-ai-powered-buildable-brick-structure-generation y0 News en 2026-05-27T04:00:00.000Z BrickAnything: AI-Powered Buildable Brick Structure Generation 3d-generation, ai-research, generative-ai, constraint-satisfaction, procedural-content, sequence-generation, structural-design https://news.y0.exchange/article/llms-cannot-introspect-research-challenges-ai-claims y0 News en 2026-05-27T04:00:00.000Z LLMs Cannot Introspect: Research Challenges AI Claims llm-introspection, ai-metacognition, model-interpretability, evaluation-methodology, arxiv-research, machine-cognition, pattern-matching, ai-safety https://news.y0.exchange/article/agent-memory-as-state-management-new-data-paradigm y0 News en 2026-05-27T04:00:00.000Z Agent Memory as State Management: New Data Paradigm ai-memory-systems, agent-architecture, data-management, long-term-memory, database-paradigms, autonomous-agents, research, state-management https://news.y0.exchange/article/polar-personalized-ai-agents-with-long-term-memory y0 News en 2026-05-27T04:00:00.000Z POLAR: Personalized AI Agents with Long-Term Memory multimodal-llm, embodied-agents, personalization, memory-systems, ai-research, long-term-interaction, knowledge-graphs https://news.y0.exchange/article/mpmmine-constraint-acquisition-benchmarks y0 News en 2026-05-27T04:00:00.000Z MPMMine: Constraint Acquisition Benchmarks constraint-acquisition, mathematical-programming, benchmarking, ai-infrastructure, optimization, algorithm-evaluation, standardization https://news.y0.exchange/article/agent-lifespan-engineering-new-reliability-benchmark y0 News en 2026-05-27T04:00:00.000Z Agent Lifespan Engineering: New Reliability Benchmark ai-agents, reliability-engineering, agent-systems, deployment, benchmarking, memory-systems, production-ai, aging-degradation https://news.y0.exchange/article/agentic-ai-frameworks-advance-scientific-workflow-automation y0 News en 2026-05-27T04:00:00.000Z Agentic AI Frameworks Advance Scientific Workflow Automation agentic-ai, scientific-workflows, llm-orchestration, autonomous-agents, time-series-analysis, knowledge-graphs, systems-engineering, ai-infrastructure https://news.y0.exchange/article/anchor-solving-ai-agent-benchmark-consistency-issues y0 News en 2026-05-27T04:00:00.000Z Anchor: Solving AI Agent Benchmark Consistency Issues ai-agents, benchmarking, enterprise-ai, evaluation-methodology, erp-systems, task-generation, constraint-optimization, ai-reliability https://news.y0.exchange/article/omnitom-new-theory-of-mind-benchmark-for-llms y0 News en 2026-05-27T04:00:00.000Z OmniToM: New Theory of Mind Benchmark for LLMs theory-of-mind, llm-evaluation, benchmark, ai-reasoning, belief-modeling, social-reasoning, language-models https://news.y0.exchange/article/jobbench-aligning-ai-agents-with-human-work-priorities y0 News en 2026-05-27T04:00:00.000Z JobBench: Aligning AI Agents With Human Work Priorities ai-agents, benchmarking, ai-evaluation, human-augmentation, occupational-ai, claude-opus, methodology https://news.y0.exchange/article/managing-llm-uncertainty-in-virtual-laboratory-planning y0 News en 2026-05-27T04:00:00.000Z Managing LLM Uncertainty in Virtual Laboratory Planning llm-limitations, procedural-knowledge, virtual-laboratories, uncertainty-management, ai-validation, educational-technology, knowledge-extraction, constraint-learning https://news.y0.exchange/article/scientistone-fixes-ai-research-credibility-crisis y0 News en 2026-05-27T04:00:00.000Z ScientistOne Fixes AI Research Credibility Crisis autonomous-research, ai-verification, chain-of-evidence, research-integrity, benchmark-reliability, hallucination-detection, scientific-ai https://news.y0.exchange/article/fepoid-automatic-layer-selection-for-llm-hallucination-detection y0 News en 2026-05-27T04:00:00.000Z FEPoID: Automatic Layer Selection for LLM Hallucination Detection hallucination-detection, large-language-models, ai-safety, layer-selection, model-interpretability, neural-networks https://news.y0.exchange/article/carl-algorithm-enables-reusable-skills-in-hierarchical-rl y0 News en 2026-05-27T04:00:00.000Z CARL Algorithm Enables Reusable Skills in Hierarchical RL hierarchical-reinforcement-learning, skill-discovery, contrastive-learning, long-horizon-tasks, local-dynamics, reusable-abstractions, ogbench, hiql https://news.y0.exchange/article/lmms-struggle-with-creative-problem-solving-new-benchmark-shows y0 News en 2026-05-27T04:00:00.000Z LMMs Struggle With Creative Problem-Solving, New Benchmark Shows large-multimodal-models, visual-grounding, creative-reasoning, benchmark, affordance-learning, preference-optimization, hallucination-reduction, embodied-ai https://news.y0.exchange/article/calibrated-interactive-rl-fixes-dialogue-agent-distribution-shift y0 News en 2026-05-27T04:00:00.000Z Calibrated Interactive RL Fixes Dialogue Agent Distribution Shift reinforcement-learning, dialogue-systems, distribution-shift, llm-agents, simulator-alignment, multi-turn-ai, interactive-rl, human-alignment https://news.y0.exchange/article/llms-pure-reasoning-beats-code-execution y0 News en 2026-05-27T04:00:00.000Z LLMs: Pure Reasoning Beats Code Execution llm-evaluation, mathematical-reasoning, chain-of-thought, code-execution, robustness-testing, ai-reliability https://news.y0.exchange/article/minimax-m2-efficient-2299b-parameter-language-model y0 News en 2026-05-27T04:00:00.000Z MiniMax-M2: Efficient 229.9B Parameter Language Model language-models, mixture-of-experts, efficient-ai, agentic-systems, sparse-activation, reinforcement-learning, ai-infrastructure https://news.y0.exchange/article/lexguard-trustworthy-legal-ai-through-formal-reasoning y0 News en 2026-05-27T04:00:00.000Z LexGuard: Trustworthy Legal AI Through Formal Reasoning legal-ai, llm-reliability, formal-verification, trustworthy-ai, adversarial-testing, robustness, smt-solvers, ai-safety https://news.y0.exchange/article/polyfusionagent-multimodal-ai-for-polymer-discovery y0 News en 2026-05-27T04:00:00.000Z PolyFusionAgent: Multimodal AI for Polymer Discovery polymer-discovery, foundation-models, multimodal-ai, materials-science, inverse-design, drug-discovery, scientific-reasoning, generative-models https://news.y0.exchange/article/mobileexplorer-cuts-mobile-ai-latency-23-via-on-device-inference y0 News en 2026-05-27T04:00:00.000Z MobileExplorer Cuts Mobile AI Latency 23% via On-Device Inference mobile-ai, on-device-inference, gui-agents, edge-computing, vision-language-models, latency-optimization, privacy-preserving-ai https://news.y0.exchange/article/medguidex-clinical-guidelines-improve-medical-llm-reasoning y0 News en 2026-05-27T04:00:00.000Z MedGuideX: Clinical Guidelines Improve Medical LLM Reasoning medical-ai, clinical-reasoning, llm-training, practice-guidelines, healthcare-ai, model-explainability, decision-logic, synthetic-data https://news.y0.exchange/article/agora-step-level-prompt-compression-for-llm-agents y0 News en 2026-05-27T04:00:00.000Z AGORA: Step-Level Prompt Compression for LLM Agents llm-agents, prompt-compression, token-efficiency, inference-optimization, structural-parsing, action-preservation, cost-reduction https://news.y0.exchange/article/fast-goal-improving-clip-for-detailed-text-understanding y0 News en 2026-05-27T04:00:00.000Z FAST-GOAL: Improving CLIP for Detailed Text Understanding vision-language-models, clip-alignment, fine-tuning, multimodal-learning, object-detection, semantic-alignment, deep-learning, dataset-release https://news.y0.exchange/article/tail-aware-hifloat4-w4a4-quantization-for-video-models y0 News en 2026-05-27T04:00:00.000Z Tail-Aware HiFloat4: W4A4 Quantization for Video Models quantization, model-compression, video-generation, hifloat4, post-training-quantization, w4a4, neural-networks, inference-optimization https://news.y0.exchange/article/unitymas-o-rl-framework-for-multi-agent-llm-systems y0 News en 2026-05-27T04:00:00.000Z UnityMAS-O: RL Framework for Multi-Agent LLM Systems llm-agents, reinforcement-learning, multi-agent-systems, ai-optimization, distributed-training, workflow-automation, ppo-training, agent-coordination https://news.y0.exchange/article/policy-gradient-failures-in-long-horizon-cumulative-damage-rl y0 News en 2026-05-27T04:00:00.000Z Policy Gradient Failures in Long-Horizon Cumulative-Damage RL reinforcement-learning, policy-gradient, long-horizon-optimization, cumulative-damage, ppo, dynamic-programming, multi-step-planning, greedy-commitment https://news.y0.exchange/article/memfail-diagnosing-llm-memory-system-failures y0 News en 2026-05-27T04:00:00.000Z MemFail: Diagnosing LLM Memory System Failures llm-memory, benchmark, ai-reliability, failure-modes, agentic-ai, diagnostic-tools, system-architecture https://news.y0.exchange/article/medical-ai-tool-synergy-framework-improves-clinical-safety y0 News en 2026-05-27T04:00:00.000Z Medical AI Tool Synergy Framework Improves Clinical Safety medical-ai, tool-selection, reinforcement-learning, clinical-safety, ai-reliability, multi-agent-systems, healthcare-ai https://news.y0.exchange/article/cudanalyst-feedback-attribution-in-llm-kernel-generation y0 News en 2026-05-27T04:00:00.000Z CUDAnalyst: Feedback Attribution in LLM Kernel Generation llm-agents, cuda-optimization, interpretability, feedback-systems, code-generation, multi-agent-ai, model-analysis https://news.y0.exchange/article/llm-harness-sensitivity-non-monotone-across-capability-tiers y0 News en 2026-05-27T04:00:00.000Z LLM Harness Sensitivity Non-Monotone Across Capability Tiers llm-agents, harness-optimization, model-capability, failure-taxonomy, deployment-strategy, reasoning-models, chat-models https://news.y0.exchange/article/medial-speech-new-medical-ai-dataset-for-patient-consultations y0 News en 2026-05-27T04:00:00.000Z MeDial-Speech: New Medical AI Dataset for Patient Consultations medical-ai, llm-benchmarking, healthcare-technology, spoken-language-processing, dataset-release, clinical-ai, nlp https://news.y0.exchange/article/chain-of-thought-disrupts-llm-refusal-control-mechanisms y0 News en 2026-05-27T04:00:00.000Z Chain-of-Thought Disrupts LLM Refusal Control Mechanisms chain-of-thought, llm-safety, activation-steering, reasoning-models, refusal-mechanisms, deepseek-r1, ai-security, alignment https://news.y0.exchange/article/language-models-hide-memory-reliance-from-output-analysis y0 News en 2026-05-27T04:00:00.000Z Language Models Hide Memory Reliance From Output Analysis language-models, rag-systems, retrieval-augmented-generation, ai-safety, model-attribution, representational-analysis, ai-verification, hallucination-detection https://news.y0.exchange/article/livek12bench-reveals-critical-gaps-in-lmm-educational-performance y0 News en 2026-05-27T04:00:00.000Z LiveK12Bench Reveals Critical Gaps in LMM Educational Performance large-multimodal-models, educational-ai, benchmark-evaluation, lmm-performance, k12-education, ai-reasoning, model-assessment, intelligent-tutors https://news.y0.exchange/article/ai-reasoning-gap-knowledge-doesnt-guarantee-composition y0 News en 2026-05-27T04:00:00.000Z AI Reasoning Gap: Knowledge Doesn't Guarantee Composition ai-evaluation, reasoning-limitations, benchmark-critique, compositional-reasoning, language-models, post-training, model-assessment, factual-knowledge https://news.y0.exchange/article/chain-of-thought-works-via-local-token-co-occurrence y0 News en 2026-05-27T04:00:00.000Z Chain-of-Thought Works via Local Token Co-occurrence chain-of-thought, language-models, prompt-engineering, model-interpretability, token-activation, inference-analysis, reasoning-mechanisms https://news.y0.exchange/article/helicase-multi-agent-llms-for-supply-chain-knowledge-graphs y0 News en 2026-05-27T04:00:00.000Z Helicase: Multi-Agent LLMs for Supply Chain Knowledge Graphs multi-agent-llm, knowledge-graphs, supply-chain, uncertainty-quantification, reasoning, benchmark, autonomous-agents https://news.y0.exchange/article/decompr-fixing-llm-weights-for-multi-stakeholder-alignment y0 News en 2026-05-27T04:00:00.000Z DecompR: Fixing LLM Weights for Multi-Stakeholder Alignment llm-alignment, multi-stakeholder, utility-estimation, weight-stability, decompr, model-evaluation, preference-aggregation https://news.y0.exchange/article/commutative-factors-in-factor-graphs-corrected-detection y0 News en 2026-05-27T04:00:00.000Z Commutative Factors in Factor Graphs: Corrected Detection probabilistic-inference, graphical-models, factor-graphs, lifted-inference, algorithm-correctness, theoretical-foundations, machine-learning https://news.y0.exchange/article/taddle-detecting-deficient-ai-generated-peer-reviews y0 News en 2026-05-27T04:00:00.000Z TADDLE: Detecting Deficient AI-Generated Peer Reviews peer-review, llm-detection, quality-assurance, academic-publishing, ai-systems, benchmark-dataset, tool-augmented-agents https://news.y0.exchange/article/n2i-rag-legal-indicator-computation-via-agent-based-rag y0 News en 2026-05-27T04:00:00.000Z N2I-RAG: Legal Indicator Computation via Agent-Based RAG legal-tech, retrieval-augmented-generation, llm-agents, regulatory-compliance, interpretability, agentic-ai, natural-language-processing https://news.y0.exchange/article/lp-approach-enhances-process-conformance-checking y0 News en 2026-05-27T04:00:00.000Z LP Approach Enhances Process Conformance Checking process-mining, conformance-checking, linear-programming, algorithm-optimization, computational-efficiency, totally-unimodular, a-star-search, network-flow https://news.y0.exchange/article/neuro-symbolic-verification-cuts-llm-hallucinations-by-83 y0 News en 2026-05-27T04:00:00.000Z Neuro-Symbolic Verification Cuts LLM Hallucinations by 83% llm-verification, neuro-symbolic, hallucination-detection, ai-safety, formal-methods, healthcare-ai, trustworthy-ai, semantic-analysis https://news.y0.exchange/article/lela-zero-shot-llm-entity-linking-framework y0 News en 2026-05-27T04:00:00.000Z LELA: Zero-Shot LLM Entity Linking Framework entity-linking, nlp, llm, zero-shot-learning, named-entity-recognition, python-library, domain-adaptation, knowledge-graphs https://news.y0.exchange/article/llms-generate-robust-optimization-model-portfolios y0 News en 2026-05-27T04:00:00.000Z LLMs Generate Robust Optimization Model Portfolios llm, optimization, portfolio-methods, decision-making, ai-reliability, human-in-the-loop, mathematical-modeling, automation https://news.y0.exchange/article/orca-ai-copilot-for-accessible-causal-analysis y0 News en 2026-05-27T04:00:00.000Z ORCA: AI Copilot for Accessible Causal Analysis causal-analysis, root-cause-analysis, ai-copilot, accessibility, domain-experts, automated-reasoning, analytics https://news.y0.exchange/article/enhanced-negative-sampling-boosts-knowledge-graph-models y0 News en 2026-05-27T04:00:00.000Z Enhanced Negative Sampling Boosts Knowledge Graph Models knowledge-graphs, foundation-models, negative-sampling, machine-learning, ai-training, model-optimization, kgfm, zero-shot-learning https://news.y0.exchange/article/batterymformer-multi-level-transformer-for-battery-degradation y0 News en 2026-05-27T04:00:00.000Z BatteryMFormer: Multi-Level Transformer for Battery Degradation battery-degradation, transformer-model, forecasting, energy-storage, machine-learning, predictive-modeling, electric-vehicles, deep-learning https://news.y0.exchange/article/knowledge-graphs-solve-llm-hallucination-in-steel-industry y0 News en 2026-05-27T04:00:00.000Z Knowledge Graphs Solve LLM Hallucination in Steel Industry knowledge-graphs, llm-reliability, industrial-ai, neo4j, decision-support, hallucination-mitigation, domain-specific-ai, environmental-engineering https://news.y0.exchange/article/scene-framework-bridges-biomedical-knowledge-and-experimental-data y0 News en 2026-05-27T04:00:00.000Z SCENE Framework Bridges Biomedical Knowledge and Experimental Data biomedical-ai, knowledge-contextualization, explainable-ai, clinical-trials, drug-discovery, multi-agent-systems, personalized-medicine https://news.y0.exchange/article/camopd-recovering-llm-capabilities-after-domain-specialization y0 News en 2026-05-27T04:00:00.000Z CaMOPD: Recovering LLM Capabilities After Domain Specialization llm-training, fine-tuning, domain-specialization, knowledge-distillation, model-capability, machine-learning https://news.y0.exchange/article/ai-safety-requires-controllability-beyond-alignment y0 News en 2026-05-27T04:00:00.000Z AI Safety Requires Controllability Beyond Alignment ai-safety, controllability, alignment, autonomous-agents, runtime-control, benchmark, ai-architecture, governance https://news.y0.exchange/article/vision-language-agents-for-mobile-gui-navigation y0 News en 2026-05-27T04:00:00.000Z Vision-Language Agents for Mobile GUI Navigation vision-language-models, mobile-automation, reinforcement-learning, gui-navigation, benchmarking, dataset, ai-agents, evaluation-toolkit https://news.y0.exchange/article/iccu-in-context-continual-unlearning-for-language-models y0 News en 2026-05-27T04:00:00.000Z ICCU: In-Context Continual Unlearning for Language Models machine-unlearning, language-models, inference-optimization, data-privacy, ai-safety, model-alignment, continual-learning, llm-governance https://news.y0.exchange/article/stepopsd-step-aware-preference-distillation-for-agents y0 News en 2026-05-27T04:00:00.000Z StepOPSD: Step-Aware Preference Distillation for Agents reinforcement-learning, credit-assignment, agent-training, policy-distillation, multi-turn-agents, benchmark-results, language-models https://news.y0.exchange/article/vitabench-20-testing-llm-personalization-in-long-term-interactions y0 News en 2026-05-27T04:00:00.000Z VitaBench 2.0: Testing LLM Personalization in Long-Term Interactions large-language-models, benchmarking, personalization, ai-agents, user-modeling, long-term-interactions, memory-architecture, capability-gaps https://news.y0.exchange/article/llm-safety-gap-models-detect-but-ignore-contradictions y0 News en 2026-05-27T04:00:00.000Z LLM Safety Gap: Models Detect But Ignore Contradictions llm-safety, retrieval-augmented-generation, monitoring-control-gap, rag-systems, model-evaluation, adversarial-testing, ai-reliability, multi-turn-inference https://news.y0.exchange/article/dualgraph-hybrid-rag-for-semi-structured-question-answering y0 News en 2026-05-27T04:00:00.000Z DualGraph: Hybrid RAG for Semi-Structured Question Answering rag-systems, knowledge-graphs, semantic-search, nlp, e-commerce, information-retrieval, hybrid-approaches, benchmarks https://news.y0.exchange/article/knowledge-graphs-in-llms-compact-subgraphs-match-full-performance y0 News en 2026-05-27T04:00:00.000Z Knowledge Graphs in LLMs: Compact Subgraphs Match Full Performance knowledge-graphs, language-models, hypothesis-generation, ai-efficiency, structured-knowledge, battery-materials https://news.y0.exchange/article/noisyagent-improving-llm-agent-robustness-through-noise-training y0 News en 2026-05-27T04:00:00.000Z NoisyAgent: Improving LLM Agent Robustness Through Noise Training llm-agents, robustness, training-framework, real-world-deployment, noise-injection, agent-reliability, curriculum-learning, ai-engineering https://news.y0.exchange/article/gumbel-machine-ai-counterfactual-student-writing-generation y0 News en 2026-05-27T04:00:00.000Z Gumbel Machine: AI Counterfactual Student Writing Generation llm, education-tech, counterfactual-generation, text-generation, machine-learning, controlled-decoding, student-feedback, pedagogical-ai https://news.y0.exchange/article/sia-self-improving-ai-updates-harness-and-model-weights y0 News en 2026-05-27T04:00:00.000Z SIA: Self-Improving AI Updates Harness and Model Weights self-improving-ai, autonomous-optimization, language-models, ai-research, model-weights, harness-updates, machine-learning https://news.y0.exchange/article/agentic-ai-cost-framework-technical-debt-vs-stochastic-tax y0 News en 2026-05-27T04:00:00.000Z Agentic AI Cost Framework: Technical Debt vs Stochastic Tax agentic-ai, technical-debt, cost-modeling, operational-metrics, ai-governance, framework, measurement https://news.y0.exchange/article/maat-ai-agent-for-competition-law-research y0 News en 2026-05-27T04:00:00.000Z Maat: AI Agent for Competition Law Research legal-ai, llm-specialization, rag-retrieval, competition-law, domain-expertise, ai-research, professional-services https://news.y0.exchange/article/2-aspq-programs-complexity-analysis-efficient-implementation y0 News en 2026-05-27T04:00:00.000Z 2-ASP(Q) Programs: Complexity Analysis & Efficient Implementation answer-set-programming, complexity-theory, logic-programming, optimization, cegar-techniques, computational-logic, formal-methods, constraint-satisfaction https://news.y0.exchange/article/rlhf-vulnerability-how-llms-exploit-alignment y0 News en 2026-05-27T04:00:00.000Z RLHF Vulnerability: How LLMs Exploit Alignment rlhf, alignment-safety, llm-security, bias-amplification, reward-model, ai-safety, human-feedback, vulnerability https://news.y0.exchange/article/brane-dynamic-query-level-optimization-for-retrieval-pipelines y0 News en 2026-05-27T04:00:00.000Z BRANE: Dynamic Query-Level Optimization for Retrieval Pipelines retrieval-agents, optimization, llm-systems, cost-efficiency, inference, rag-pipelines, query-routing, machine-learning https://news.y0.exchange/article/muse-autoskill-self-improving-llm-agent-framework y0 News en 2026-05-27T04:00:00.000Z MUSE-Autoskill: Self-Improving LLM Agent Framework llm-agents, skill-management, agent-autonomy, ai-architecture, knowledge-transfer, continuous-learning, ai-systems https://news.y0.exchange/article/xe-forge-llm-kernel-optimization-for-intel-gpus y0 News en 2026-05-27T04:00:00.000Z Xe-Forge: LLM Kernel Optimization for Intel GPUs kernel-optimization, llm-automation, intel-gpu, hardware-acceleration, triton, gpu-porting, ai-infrastructure, compiler-optimization https://news.y0.exchange/article/edge-ai-deployment-framework-for-industrial-embedded-systems y0 News en 2026-05-27T04:00:00.000Z Edge AI Deployment Framework for Industrial Embedded Systems edge-ai, embedded-systems, systems-architecture, industrial-deployment, bsp-framework, ai-infrastructure, field-reliability https://news.y0.exchange/article/gem-geometric-entropy-mixing-for-llm-data-optimization y0 News en 2026-05-27T04:00:00.000Z GEM: Geometric Entropy Mixing for LLM Data Optimization llm-training, data-curation, geometric-methods, model-optimization, machine-learning, neural-networks https://news.y0.exchange/article/llm-pretraining-data-exposure-privacy-evaluation-risks y0 News en 2026-05-27T04:00:00.000Z LLM Pretraining Data Exposure: Privacy & Evaluation Risks llm-security, data-privacy, membership-inference, data-contamination, pretraining-exposure, ai-governance, model-evaluation, data-protection https://news.y0.exchange/article/audio-deepfakes-erode-trust-in-authentic-speech y0 News en 2026-05-27T04:00:00.000Z Audio Deepfakes Erode Trust in Authentic Speech deepfakes, audio-synthesis, trust-erosion, media-authentication, ai-detection, human-perception, content-verification https://news.y0.exchange/article/assetgen-fast-3d-asset-generation-for-interactive-creation y0 News en 2026-05-27T04:00:00.000Z AssetGen: Fast 3D Asset Generation for Interactive Creation 3d-generation, ai-content-creation, mesh-generation, real-time-rendering, mobile-optimization, computer-vision, deployment-ready, generative-ai https://news.y0.exchange/article/vista-new-ai-web-app-generation-benchmark-released y0 News en 2026-05-27T04:00:00.000Z VISTA: New AI Web-App Generation Benchmark Released benchmark, ai-agents, code-generation, web-development, llm-evaluation, vista-framework, software-engineering, visual-ui-coding https://news.y0.exchange/article/augment-engineering-multi-tool-ai-orchestration-framework y0 News en 2026-05-27T04:00:00.000Z Augment Engineering: Multi-Tool AI Orchestration Framework prompt-engineering, ai-orchestration, context-engineering, multi-tool-ai, productivity, methodology, ai-skills, workflow-automation https://news.y0.exchange/article/memmorph-memory-poisoning-attack-on-llm-agents y0 News en 2026-05-27T04:00:00.000Z MemMorph: Memory Poisoning Attack on LLM Agents llm-security, agent-vulnerability, memory-poisoning, ai-safety, adversarial-attacks, tool-hijacking, autonomous-agents https://news.y0.exchange/article/adaptive-guidance-fails-in-autonomous-driving-under-severe-occlusion y0 News en 2026-05-27T04:00:00.000Z Adaptive Guidance Fails in Autonomous Driving Under Severe Occlusion autonomous-driving, knowledge-distillation, uncertainty-quantification, partial-observability, ensemble-methods, machine-learning, pomdp, reinforcement-learning https://news.y0.exchange/article/llm-judge-vulnerability-stylistic-bias-exploitation-attack y0 News en 2026-05-27T04:00:00.000Z LLM Judge Vulnerability: Stylistic Bias Exploitation Attack llm-security, adversarial-attacks, ai-evaluation, model-bias, benchmark-gaming, ai-safety, evaluation-integrity https://news.y0.exchange/article/furina-jailbreak-exposes-llm-safety-instability-vulnerability y0 News en 2026-05-27T04:00:00.000Z Furina Jailbreak Exposes LLM Safety Instability Vulnerability llm-safety, jailbreak-attack, ai-security, uncertainty-exploitation, multimodal-models, adversarial-robustness, safety-alignment https://news.y0.exchange/article/tsfmaudit-detecting-data-contamination-in-time-series y0 News en 2026-05-27T04:00:00.000Z TSFMAudit: Detecting Data Contamination in Time Series time-series-models, data-contamination, machine-learning, model-auditing, foundation-models, evaluation-methodology, research-integrity https://news.y0.exchange/article/pushcen-adfl-80-communication-reduction-in-federated-learning y0 News en 2026-05-27T04:00:00.000Z PushCen-ADFL: 80% Communication Reduction in Federated Learning federated-learning, distributed-ml, asynchronous-algorithms, communication-efficiency, decentralized-systems, model-compression, edge-computing https://news.y0.exchange/article/tool-schema-compression-boosts-agentic-rag-under-context-limits y0 News en 2026-05-27T04:00:00.000Z Tool-Schema Compression Boosts Agentic RAG Under Context Limits agentic-rag, language-models, context-compression, tool-schemas, token-efficiency, agent-systems, rag-optimization https://news.y0.exchange/article/iot-intrusion-detection-system-achieves-95-accuracy y0 News en 2026-05-27T04:00:00.000Z IoT Intrusion Detection System Achieves 95% Accuracy iot-security, intrusion-detection, machine-learning, cybersecurity, edge-computing, autonomous-systems, model-optimization https://news.y0.exchange/article/lie-group-neural-networks-for-stable-dynamics y0 News en 2026-05-27T04:00:00.000Z Lie Group Neural Networks for Stable Dynamics neural-networks, lie-groups, geometric-ai, dynamical-systems, robotics, manifold-learning, control-theory, se3-transformations https://news.y0.exchange/article/llms-fail-at-cross-section-defect-detection-under-orchestration y0 News en 2026-05-27T04:00:00.000Z LLMs Fail at Cross-Section Defect Detection Under Orchestration llm-safety, multi-agent-systems, defect-detection, alignment-paradox, orchestration-architecture, model-evaluation, document-analysis https://news.y0.exchange/article/infoquant-low-bit-llm-quantization-via-distribution-design y0 News en 2026-05-27T04:00:00.000Z InfoQuant: Low-Bit LLM Quantization via Distribution Design llm-quantization, low-bit-inference, post-training-quantization, neural-network-compression, model-efficiency, activation-distribution, edge-deployment, ai-optimization https://news.y0.exchange/article/pitchbench-reveals-audio-language-models-struggle-with-pitch y0 News en 2026-05-27T04:00:00.000Z PitchBench Reveals Audio-Language Models Struggle With Pitch audio-language-models, pitch-perception, ai-evaluation, benchmarking, music-ai, model-limitations, machine-learning https://news.y0.exchange/article/repomirage-reveals-code-agent-context-reasoning-gaps y0 News en 2026-05-27T04:00:00.000Z RepoMirage Reveals Code Agent Context Reasoning Gaps code-agents, ai-evaluation, repository-reasoning, benchmark-analysis, software-engineering, llm-limitations, agent-architecture https://news.y0.exchange/article/autodft-llm-powered-closed-loop-dft-automation y0 News en 2026-05-27T04:00:00.000Z AutoDFT: LLM-Powered Closed-Loop DFT Automation dft-automation, llm-agents, computational-chemistry, materials-science, scientific-ai, multi-agent-systems, closed-loop-reasoning, automation https://news.y0.exchange/article/gac-adaptive-mixing-for-hybrid-sft-rl-model-training y0 News en 2026-05-27T04:00:00.000Z GAC: Adaptive Mixing for Hybrid SFT-RL Model Training machine-learning, model-training, reinforcement-learning, post-training, optimization, gradient-estimation, language-models, training-efficiency https://news.y0.exchange/article/setupx-llm-agents-learn-from-repository-setup-failures y0 News en 2026-05-27T04:00:00.000Z SetupX: LLM Agents Learn from Repository Setup Failures llm-agents, repository-setup, software-development, automation, docker, developer-tools, experiential-learning, ci-cd https://news.y0.exchange/article/low-bit-quantization-training-achieves-near-lossless-llm y0 News en 2026-05-27T04:00:00.000Z Low-Bit Quantization Training Achieves Near-Lossless LLM quantization-aware-training, llm-optimization, model-compression, hif8-w8a8, neural-networks, inference-efficiency, transformer-models https://news.y0.exchange/article/hrvconformer-ai-model-for-neonatal-hie-detection y0 News en 2026-05-27T04:00:00.000Z HRVConformer: AI Model for Neonatal HIE Detection deep-learning, medical-ai, neonatal-health, transformer-architecture, heart-rate-signals, hie-classification, signal-processing, automated-diagnosis https://news.y0.exchange/article/delaymix-dynamic-modeling-for-streaming-time-series y0 News en 2026-05-27T04:00:00.000Z DelayMix: Dynamic Modeling for Streaming Time Series machine-learning, time-series, adaptive-systems, tensor-decomposition, streaming-data, forecasting, regime-shift, non-stationary https://news.y0.exchange/article/aims-fold-proteomics-guided-protein-structure-prediction y0 News en 2026-05-27T04:00:00.000Z AIMS-Fold: Proteomics-Guided Protein Structure Prediction protein-structure-prediction, proteomics, drug-design, diffusion-models, computational-biology, machine-learning, induced-proximity, biotech https://news.y0.exchange/article/coad-cooperative-time-series-anomaly-detection-method y0 News en 2026-05-27T04:00:00.000Z CoAD: Cooperative Time Series Anomaly Detection Method time-series-anomaly-detection, deep-learning, classification-reconstruction, masked-autoencoder, outlier-exposure, machine-learning, research https://news.y0.exchange/article/cyberevolver-self-evolving-llm-agents-for-cybersecurity y0 News en 2026-05-27T04:00:00.000Z CyberEvolver: Self-Evolving LLM Agents for Cybersecurity llm-agents, cybersecurity, self-improvement, adaptive-ai, autonomous-systems, ai-architecture, ctf-challenges, agent-learning https://news.y0.exchange/article/auto-research-systems-need-external-validation-not-just-autonomy y0 News en 2026-05-27T04:00:00.000Z Auto-Research Systems Need External Validation, Not Just Autonomy ai-research, autonomous-systems, scientific-validation, research-integrity, epistemic-standards, machine-learning, methodology https://news.y0.exchange/article/agentsociety-decentralized-multi-agent-collaboration-framework y0 News en 2026-05-27T04:00:00.000Z AgentSociety: Decentralized Multi-Agent Collaboration Framework multi-agent-systems, mechanism-design, decentralized-coordination, liquid-democracy, ai-collaboration, nash-equilibrium, agent-routing, economic-incentives https://news.y0.exchange/article/unified-neural-scaling-laws-improve-ai-model-predictions y0 News en 2026-05-27T04:00:00.000Z Unified Neural Scaling Laws Improve AI Model Predictions neural-scaling-laws, deep-learning, model-efficiency, ai-research, computation-optimization, machine-learning, scaling-behavior, ai-development https://news.y0.exchange/article/multimodal-ai-predicts-respiratory-failure-better-than-ehr-alone y0 News en 2026-05-27T04:00:00.000Z Multimodal AI Predicts Respiratory Failure Better Than EHR Alone medical-ai, multimodal-learning, respiratory-failure, clinical-prediction, chest-xray, icu-monitoring, machine-learning https://news.y0.exchange/article/kv-cache-bias-correction-enables-efficient-video-diffusion y0 News en 2026-05-27T04:00:00.000Z KV-Cache Bias Correction Enables Efficient Video Diffusion video-diffusion, kv-cache-compression, quantization, attention-mechanisms, model-efficiency, memory-optimization, generative-ai https://news.y0.exchange/article/vesselsim-3d-blood-vessel-segmentation-without-annotations y0 News en 2026-05-27T04:00:00.000Z VesselSim: 3D Blood Vessel Segmentation Without Annotations medical-ai, synthetic-data, segmentation, domain-adaptation, computer-vision, deep-learning, healthcare-tech, zero-shot-learning https://news.y0.exchange/article/marl-robustness-compensating-delays-via-learned-filtering y0 News en 2026-05-27T04:00:00.000Z MARL Robustness: Compensating Delays via Learned Filtering multi-agent-reinforcement-learning, marl, state-estimation, communication-delay, kalman-filtering, robustness, real-world-deployment, learned-dynamics https://news.y0.exchange/article/croco-cross-lingual-preference-tuning-for-llms y0 News en 2026-05-27T04:00:00.000Z CroCo: Cross-Lingual Preference Tuning for LLMs llm-optimization, multilingual-ai, preference-tuning, cross-lingual-transfer, reward-models, language-models, ai-research https://news.y0.exchange/article/llms-detect-ddos-attacks-in-sdn-networks-with-rag-framework y0 News en 2026-05-27T04:00:00.000Z LLMs Detect DDoS Attacks in SDN Networks with RAG Framework dds-mitigation, sdn-security, llm-inference, rag-framework, network-security, cyber-defense, ai-security https://news.y0.exchange/article/curriculum-learning-boosts-ai-safety-alignment-by-20 y0 News en 2026-05-27T04:00:00.000Z Curriculum Learning Boosts AI Safety Alignment by 20% language-model-safety, curriculum-learning, dpo-alignment, ai-robustness, jailbreak-resistance, model-training, adversarial-security, safety-engineering https://news.y0.exchange/article/ec-egocentric-video-generation-with-3d-memory y0 News en 2026-05-27T04:00:00.000Z E³C: Egocentric Video Generation with 3D Memory egocentric-video-generation, 3d-reconstruction, embodied-ai, video-synthesis, diffusion-models, pose-control, computer-vision, robotics https://news.y0.exchange/article/semigroup-consistency-diagnostic-for-physics-simulators y0 News en 2026-05-27T04:00:00.000Z Semigroup Consistency Diagnostic for Physics Simulators physics-simulators, neural-networks, model-evaluation, scientific-ml, semigroup-consistency, temporal-composition, diagnostics https://news.y0.exchange/article/beap-attack-bypasses-ai-safety-new-unlearning-vulnerability y0 News en 2026-05-27T04:00:00.000Z BEAP Attack Bypasses AI Safety: New Unlearning Vulnerability machine-unlearning, adversarial-attacks, diffusion-models, ai-safety, prompt-injection, generative-ai, security-vulnerability, model-robustness https://news.y0.exchange/article/why-correct-demonstrations-reduce-ai-model-performance y0 News en 2026-05-27T04:00:00.000Z Why Correct Demonstrations Reduce AI Model Performance in-context-learning, machine-learning, demonstrations, model-behavior, prompt-engineering, language-models, inference-mechanisms https://news.y0.exchange/article/decouplegen-ai-model-debiasing-through-synthetic-data y0 News en 2026-05-27T04:00:00.000Z DecoupleGen: AI Model Debiasing Through Synthetic Data computer-vision, generative-models, data-augmentation, diffusion-models, bias-mitigation, synthetic-data, machine-learning, object-recognition https://news.y0.exchange/article/why-llms-hallucinate-on-structured-knowledge-mechanistic-analysis y0 News en 2026-05-27T04:00:00.000Z Why LLMs Hallucinate on Structured Knowledge: Mechanistic Analysis llm-hallucinations, mechanistic-analysis, structured-knowledge, attention-mechanisms, semantic-grounding, reasoning-systems, ai-reliability, knowledge-grounding https://news.y0.exchange/article/pager-panoramic-3d-geometry-from-foundation-models y0 News en 2026-05-27T04:00:00.000Z PaGeR: Panoramic 3D Geometry from Foundation Models 3d-reconstruction, panoramic-geometry, foundation-models, computer-vision, depth-estimation, transformer-architecture, scene-understanding https://news.y0.exchange/article/biofact-moe-specialized-ai-for-hcc-survival-prediction y0 News en 2026-05-27T04:00:00.000Z BioFact-MoE: Specialized AI for HCC Survival Prediction medical-ai, machine-learning, cancer-prognostics, mixture-of-experts, hepatocellular-carcinoma, vision-language-models, interpretability, clinical-ai https://news.y0.exchange/article/visualneedle-exposes-mllm-limitations-in-fine-grained-search y0 News en 2026-05-27T04:00:00.000Z VisualNeedle Exposes MLLM Limitations in Fine-Grained Search multimodal-llm, benchmark, visual-search, mllm-evaluation, vision-language, fine-grained-perception, ai-limitations https://news.y0.exchange/article/credit-assigned-policy-gradient-improves-retrieval-training y0 News en 2026-05-27T04:00:00.000Z Credit-Assigned Policy Gradient Improves Retrieval Training machine-learning, policy-gradient, information-retrieval, ranking-systems, reinforcement-learning, optimization, scalability, two-stage-architecture https://news.y0.exchange/article/llm-ableism-detection-autistic-communities-shape-ai-fairness y0 News en 2026-05-27T04:00:00.000Z LLM Ableism Detection: Autistic Communities Shape AI Fairness llm-bias, disability-ai, ableism-detection, annotation-methodology, ai-fairness, autistic-community, evaluation-framework https://news.y0.exchange/article/framework-for-evaluating-generative-search-summaries y0 News en 2026-05-27T04:00:00.000Z Framework for Evaluating Generative Search Summaries generative-search, llm-evaluation, ai-summary, information-retrieval, framework, search-quality https://news.y0.exchange/article/ai-jailbreak-prediction-framework-reduces-security-testing-98 y0 News en 2026-05-27T04:00:00.000Z AI Jailbreak Prediction Framework Reduces Security Testing 98% ai-safety, jailbreak-defense, model-security, behavioral-geometry, generative-ai, adversarial-robustness, deployment-efficiency https://news.y0.exchange/article/confounder-detection-in-observational-studies-via-treatment-intent y0 News en 2026-05-27T04:00:00.000Z Confounder Detection in Observational Studies via Treatment Intent causal-inference, observational-studies, unobserved-confounding, nlp, healthcare-research, clinical-data, methodology https://news.y0.exchange/article/int8-clip-quantization-fixed-with-early-exit-strategy y0 News en 2026-05-27T04:00:00.000Z INT8 CLIP Quantization Fixed with Early Exit Strategy quantization, vision-language-models, clip, early-exit, edge-inference, model-compression, transformer-optimization, zero-shot-classification https://news.y0.exchange/article/drl-vs-rule-based-controllers-benchmark-study y0 News en 2026-05-27T04:00:00.000Z DRL vs Rule-Based Controllers: Benchmark Study deep-reinforcement-learning, resource-allocation, kubernetes, autoscaling, benchmark, ml-engineering, cloud-infrastructure, rl-evaluation https://news.y0.exchange/article/uniboost-fair-traffic-allocation-in-recommendation-systems y0 News en 2026-05-27T04:00:00.000Z Uniboost: Fair Traffic Allocation in Recommendation Systems recommendation-systems, traffic-allocation, machine-learning, interpretability, optimization, algorithm, industrial-ai https://news.y0.exchange/article/structure-adaptive-conformal-inference-for-ood-testing y0 News en 2026-05-27T04:00:00.000Z Structure-Adaptive Conformal Inference for OOD Testing machine-learning, statistical-inference, out-of-distribution, conformal-methods, uncertainty-quantification, ai-safety, model-selection, high-stakes-ml https://news.y0.exchange/article/eeg-foundation-models-show-spectral-bias-in-reconstruction y0 News en 2026-05-27T04:00:00.000Z EEG Foundation Models Show Spectral Bias in Reconstruction eeg-models, foundation-models, brain-computer-interface, signal-processing, pretraining-bias, neurotechnology, representation-learning, spectral-analysis https://news.y0.exchange/article/token-to-mask-remasking-improves-discrete-diffusion-models y0 News en 2026-05-27T04:00:00.000Z Token-to-Mask Remasking Improves Discrete Diffusion Models diffusion-models, language-models, token-editing, discrete-diffusion, inference-optimization, error-detection, llama, mathematical-reasoning https://news.y0.exchange/article/lure-detecting-llm-evaluation-awareness-in-ai-safety y0 News en 2026-05-27T04:00:00.000Z LURE: Detecting LLM Evaluation Awareness in AI Safety ai-safety, benchmarking, evaluation-methodology, llm-alignment, deployment-realism, evaluation-awareness, safety-testing https://news.y0.exchange/article/game-theoretic-video-temporal-grounding-advances-vision-language-ai y0 News en 2026-05-27T04:00:00.000Z Game-Theoretic Video Temporal Grounding Advances Vision-Language AI video-understanding, game-theory, weakly-supervised-learning, cross-modal-learning, temporal-grounding, vision-language, computer-vision, deep-learning https://news.y0.exchange/article/llm-alignment-tuning-data-centric-pipeline-design y0 News en 2026-05-27T04:00:00.000Z LLM Alignment Tuning: Data-Centric Pipeline Design llm-alignment, alignment-tuning, data-pipeline, preference-learning, model-safety, data-centric-ai https://news.y0.exchange/article/ddgad-diffusion-based-graph-anomaly-detection y0 News en 2026-05-27T04:00:00.000Z DDGAD: Diffusion-Based Graph Anomaly Detection graph-anomaly-detection, machine-learning, diffusion-dynamics, fraud-detection, cybersecurity, gnn, anomaly-detection, contamination-propagation https://news.y0.exchange/article/cat-cross-scale-aligned-gan-training-method y0 News en 2026-05-27T04:00:00.000Z CAT: Cross-Scale Aligned GAN Training Method generative-models, gans, image-synthesis, deep-learning, transformer-architecture, multi-scale-training, computer-vision, model-efficiency https://news.y0.exchange/article/ai-specification-autoformalization-verus-specgym-benchmark y0 News en 2026-05-27T04:00:00.000Z AI Specification Autoformalization: Verus-SpecGym Benchmark formal-verification, ai-agents, specification-generation, code-correctness, llm-evaluation, verus, rust-verification https://news.y0.exchange/article/anchordiff-reducing-concept-leakage-in-diffusion-models y0 News en 2026-05-27T04:00:00.000Z AnchorDiff: Reducing Concept Leakage in Diffusion Models diffusion-models, concept-grounding, computer-vision, transformers, training-free-methods, object-localization, multimodal-ai, image-segmentation https://news.y0.exchange/article/ehr-data-consistency-verification-using-reasoning-based-ai y0 News en 2026-05-27T04:00:00.000Z EHR Data Consistency Verification Using Reasoning-Based AI ehr-systems, clinical-nlp, data-consistency, healthcare-ai, mimic-dataset, llm-verification, patient-safety https://news.y0.exchange/article/diffusion-models-for-semiconductor-defect-detection y0 News en 2026-05-27T04:00:00.000Z Diffusion Models for Semiconductor Defect Detection semiconductor-manufacturing, anomaly-detection, diffusion-models, unsupervised-learning, ic-testing, quality-control, machine-learning, defect-screening https://news.y0.exchange/article/vision-based-metric-measurement-in-large-scale-scenes y0 News en 2026-05-27T04:00:00.000Z Vision-Based Metric Measurement in Large-Scale Scenes computer-vision, metric-measurement, stereo-imaging, monocular-ranging, outdoor-monitoring, infrastructure, camera-calibration, image-stitching https://news.y0.exchange/article/sdpg-efficient-visual-rl-for-robotic-control y0 News en 2026-05-27T04:00:00.000Z SDPG: Efficient Visual RL for Robotic Control reinforcement-learning, visual-rl, robotics, compute-efficiency, policy-gradient, gpu-optimization, visuomotor-control, benchmarking https://news.y0.exchange/article/llm-story-diversity-crisis-one-word-appears-in-88-of-outputs y0 News en 2026-05-27T04:00:00.000Z LLM Story Diversity Crisis: One Word Appears in 88% of Outputs llm-diversity, ai-alignment, language-models, preference-data, model-homogeneity, fine-tuning, creative-ai, safety-trade-offs https://news.y0.exchange/article/dense2moe-efficient-on-device-llms-via-pruning y0 News en 2026-05-27T04:00:00.000Z Dense2MoE: Efficient On-Device LLMs via Pruning llm-optimization, mixture-of-experts, edge-inference, model-compression, on-device-ai, neural-networks https://news.y0.exchange/article/vision-language-models-vulnerable-to-multi-modal-attacks y0 News en 2026-05-27T04:00:00.000Z Vision-Language Models Vulnerable to Multi-Modal Attacks adversarial-attacks, vision-language-models, ai-security, multi-modal-learning, robustness, black-box-attacks, llm-vulnerability, autonomous-systems https://news.y0.exchange/article/mathematical-framework-for-ai-agent-risk-tolls y0 News en 2026-05-27T04:00:00.000Z Mathematical Framework for AI Agent Risk Tolls ai-safety, autonomous-agents, risk-management, formal-verification, actuarial-framework, ai-governance, mathematical-foundations https://news.y0.exchange/article/csv-vit-ai-model-detects-alzheimers-from-mri-scans y0 News en 2026-05-27T04:00:00.000Z CSV-ViT: AI Model Detects Alzheimer's From MRI Scans vision-transformer, alzheimers-disease, medical-imaging, neuroimaging, deep-learning, mri, brain-surface, biomarker-detection https://news.y0.exchange/article/intersketch-interleaved-visual-textual-ai-reasoning y0 News en 2026-05-27T04:00:00.000Z InterSketch: Interleaved Visual-Textual AI Reasoning vision-language-models, chain-of-thought, multimodal-ai, reinforcement-learning, visual-reasoning, vlm-architecture https://news.y0.exchange/article/streamsplit-adaptive-edge-ai-with-47x-latency-reduction y0 News en 2026-05-27T04:00:00.000Z StreamSplit: Adaptive Edge AI with 4.7x Latency Reduction edge-ai, contrastive-learning, reinforcement-learning, distributed-inference, audio-processing, model-compression, iot, edge-computing https://news.y0.exchange/article/cmivtp-multimodal-ai-for-maritime-vessel-trajectory y0 News en 2026-05-27T04:00:00.000Z CmIVTP: Multimodal AI for Maritime Vessel Trajectory maritime-ai, trajectory-prediction, computer-vision, transformer-models, multimodal-learning, vessel-tracking, ais-data, deep-learning https://news.y0.exchange/article/reca-recursive-context-allocation-for-long-video-generation y0 News en 2026-05-27T04:00:00.000Z ReCA: Recursive Context Allocation for Long Video Generation video-generation, generative-ai, context-allocation, deep-learning, msve, reca, cinematic-video, ml-benchmarks https://news.y0.exchange/article/domain-specific-ai-outperforms-generalist-models-for-industrial-inspec y0 News en 2026-05-27T04:00:00.000Z Domain-Specific AI Outperforms Generalist Models for Industrial Inspec industrial-ai, vision-language-models, edge-deployment, defect-detection, automation, maintenance-reports, quantization, qwen-llm https://news.y0.exchange/article/recursive-flow-matching-20x-speedup-for-physics-ai y0 News en 2026-05-27T04:00:00.000Z Recursive Flow Matching: 20x Speedup for Physics AI generative-models, flow-matching, physics-simulation, scientific-computing, speedup, efficiency, deep-learning https://news.y0.exchange/article/dgld-discovers-novel-energetic-materials-via-ai y0 News en 2026-05-27T04:00:00.000Z DGLD Discovers Novel Energetic Materials via AI generative-ai, materials-discovery, diffusion-models, energetic-materials, machine-learning, dft-validation, chemistry, scientific-computing https://news.y0.exchange/article/chaincaps-securing-ai-agent-tool-composition y0 News en 2026-05-27T04:00:00.000Z ChainCaps: Securing AI Agent Tool Composition ai-safety, agent-security, tool-composition, capability-attenuation, permission-laundering, llm-security https://news.y0.exchange/article/fav-aligning-few-step-generative-models-via-variational y0 News en 2026-05-27T04:00:00.000Z FAV: Aligning Few-Step Generative Models via Variational generative-models, alignment, variational-inference, robotics, image-synthesis, machine-learning, stein-vgd, reinforcement-learning https://news.y0.exchange/article/dueling-bandits-with-delayed-feedback-for-llm-alignment y0 News en 2026-05-27T04:00:00.000Z Dueling Bandits with Delayed Feedback for LLM Alignment dueling-bandits, delayed-feedback, recommender-systems, llm-alignment, machine-learning, inverse-probability-weighting, contextual-bandits, preference-learning https://news.y0.exchange/article/foundation-models-need-economic-constraints-for-valid-predictions y0 News en 2026-05-27T04:00:00.000Z Foundation Models Need Economic Constraints for Valid Predictions foundation-models, economic-validity, choice-prediction, constraint-learning, tabular-data, utility-maximization, ai-governance https://news.y0.exchange/article/hybrid-neural-symbolic-pipeline-outperforms-llms-on-clinical-extractio y0 News en 2026-05-27T04:00:00.000Z Hybrid Neural-Symbolic Pipeline Outperforms LLMs on Clinical Extractio clinical-nlp, hybrid-ai, neural-symbolic, healthcare-extraction, information-extraction, medical-ai, benchmark, ehr-systems https://news.y0.exchange/article/alpha-beta-crown-neural-network-verification-for-safety y0 News en 2026-05-27T04:00:00.000Z Alpha-Beta-CROWN: Neural Network Verification for Safety neural-network-verification, formal-verification, control-systems, safety-critical-ai, autonomous-systems, lyapunov-theory, gpu-acceleration, ai-safety, robotics-verification, machine-learning-assurance https://news.y0.exchange/article/stochasticity-error-correcting-effects-in-discrete-diffusion y0 News en 2026-05-27T04:00:00.000Z Stochasticity Error-Correcting Effects in Discrete Diffusion diffusion-models, generative-ai, inference-optimization, stochasticity, sampling-algorithms, error-correction, image-generation https://news.y0.exchange/article/foundation-models-outperform-ml-in-global-health-prediction y0 News en 2026-05-27T04:00:00.000Z Foundation Models Outperform ML in Global Health Prediction foundation-models, global-health, machine-learning, few-shot-learning, childhood-anemia, cross-country-generalization, tabular-ml, healthcare-ai https://news.y0.exchange/article/ai-generated-ip-legal-gaps-in-global-regulatory-frameworks y0 News en 2026-05-27T04:00:00.000Z AI-Generated IP: Legal Gaps in Global Regulatory Frameworks artificial-intelligence, intellectual-property, ai-generated-content, legal-framework, regulatory-gaps, copyright-law, ai-ownership, creative-works https://news.y0.exchange/article/covert-control-attacks-new-llm-data-poisoning-vulnerability y0 News en 2026-05-27T04:00:00.000Z Covert Control Attacks: New LLM Data Poisoning Vulnerability llm-security, data-poisoning, backdoor-attacks, adversarial-ml, fine-tuning-risks, model-security, ai-vulnerabilities https://news.y0.exchange/article/geometry-aware-contrastive-learning-advances-signal-recognition y0 News en 2026-05-27T04:00:00.000Z Geometry-Aware Contrastive Learning Advances Signal Recognition modulation-recognition, contrastive-learning, few-shot-learning, signal-processing, self-supervised-learning, wireless-communications, machine-learning, spectrum-sensing https://news.y0.exchange/article/pilot-commit-4x-faster-rl-training-via-smart-rollout-allocation y0 News en 2026-05-27T04:00:00.000Z Pilot-Commit: 4x Faster RL Training via Smart Rollout Allocation reinforcement-learning, llm-training, computational-efficiency, policy-optimization, ai-research, post-training, resource-optimization https://news.y0.exchange/article/medvol-r1-interpretable-3d-medical-image-segmentation y0 News en 2026-05-27T04:00:00.000Z MedVol-R1: Interpretable 3D Medical Image Segmentation medical-imaging, volumetric-segmentation, reinforcement-learning, interpretability, 3d-segmentation, clinical-ai, medical-ai, evidence-grounding https://news.y0.exchange/article/jetvit-efficient-vision-transformers-via-attention-search y0 News en 2026-05-27T04:00:00.000Z JetViT: Efficient Vision Transformers via Attention Search vision-transformers, efficient-ai, attention-mechanisms, model-acceleration, neural-architecture-search, deep-learning, inference-optimization https://news.y0.exchange/article/token-adaptive-activation-mixing-improves-llm-efficiency y0 News en 2026-05-27T04:00:00.000Z Token-Adaptive Activation Mixing Improves LLM Efficiency transformer-architecture, ffn-design, activation-functions, expressivity, language-models, neural-network-optimization, scaling-efficiency https://news.y0.exchange/article/panda-algorithm-advances-bilevel-rl-for-multi-agent-games y0 News en 2026-05-27T04:00:00.000Z PANDA Algorithm Advances Bilevel RL for Multi-Agent Games reinforcement-learning, bilevel-optimization, multi-agent-games, markov-games, algorithm, convergence-analysis, incentive-design, policy-gradient https://news.y0.exchange/article/closing-the-modality-gap-in-ood-detection-with-vlms y0 News en 2026-05-27T04:00:00.000Z Closing the Modality Gap in OOD Detection with VLMs out-of-distribution-detection, vision-language-models, modality-gap, zero-shot-learning, prototype-learning, machine-learning-safety, clip, anomaly-detection https://news.y0.exchange/article/ai-detection-bias-in-academic-writing-context-matters y0 News en 2026-05-27T04:00:00.000Z AI Detection Bias in Academic Writing: Context Matters ai-detection, academic-publishing, methodology, measurement-bias, llm-research, scientific-integrity, benchmarking https://news.y0.exchange/article/simplified-sequential-knowledge-editing-for-large-language-models y0 News en 2026-05-27T04:00:00.000Z Simplified Sequential Knowledge Editing for Large Language Models llm-editing, knowledge-updates, sequential-editing, model-maintenance, optimization-theory, factual-correction, neural-networks https://news.y0.exchange/article/da-gc-framework-brings-certified-causal-attribution-to-6g y0 News en 2026-05-27T04:00:00.000Z DA-GC Framework Brings Certified Causal Attribution to 6G 6g-security, causal-attribution, network-slicing, attack-forensics, formal-verification, telecommunications, cyber-defense, granger-causality https://news.y0.exchange/article/dynframe-adaptive-video-understanding-with-dynamic-frame-selection y0 News en 2026-05-27T04:00:00.000Z DynFrame: Adaptive Video Understanding with Dynamic Frame Selection multimodal-ai, video-understanding, llms, reinforcement-learning, inference-optimization, arxiv-research, computer-vision, efficient-models https://news.y0.exchange/article/cross-lingual-transfer-in-language-models-study y0 News en 2026-05-27T04:00:00.000Z Cross-Lingual Transfer in Language Models Study language-models, cross-lingual-transfer, nlp, tokenization, multilingual-ai, generalization, research-methodology https://news.y0.exchange/article/graphgpo-graph-based-credit-assignment-for-agentic-rl y0 News en 2026-05-27T04:00:00.000Z GraphGPO: Graph-Based Credit Assignment for Agentic RL reinforcement-learning, credit-assignment, agentic-ai, llm-training, graph-based-methods, policy-optimization, ai-research, training-efficiency https://news.y0.exchange/article/silo-protein-design-optimization-under-budget y0 News en 2026-05-27T04:00:00.000Z SILO: Protein Design Optimization Under Budget protein-design, machine-learning, active-learning, computational-biology, optimization, reinforcement-learning, biotechnology, scientific-computing https://news.y0.exchange/article/epimer-curvature-aware-model-merging-via-riemannian-geometry y0 News en 2026-05-27T04:00:00.000Z EpiMer: Curvature-Aware Model Merging via Riemannian Geometry model-merging, machine-learning, optimization, riemannian-geometry, epistemic-uncertainty, clip-vit, parameter-efficient, loss-landscape https://news.y0.exchange/article/rotation-invariant-spherical-watermarking-via-so3 y0 News en 2026-05-27T04:00:00.000Z Rotation-Invariant Spherical Watermarking via SO(3) watermarking, so3-representation, spherical-harmonics, image-protection, rotation-invariance, digital-media, computer-vision https://news.y0.exchange/article/sl-bilem-robust-epidemic-forecasting-with-behavior y0 News en 2026-05-27T04:00:00.000Z SL-BiLEM: Robust Epidemic Forecasting With Behavior epidemic-modeling, machine-learning, physics-informed-ai, public-health, forecasting, behavioral-dynamics, distribution-shift, interpretability https://news.y0.exchange/article/l2rec-dual-view-llm-personalization-for-recommendations y0 News en 2026-05-27T04:00:00.000Z L2Rec: Dual-View LLM Personalization for Recommendations llm-personalization, recommendation-systems, mixture-of-experts, parameter-efficient-tuning, dual-view-architecture, behavioral-semantics https://news.y0.exchange/article/neural-cellular-automata-uncertainty-estimation y0 News en 2026-05-27T04:00:00.000Z Neural Cellular Automata Uncertainty Estimation neural-cellular-automata, medical-imaging, uncertainty-quantification, ai-safety, segmentation, deep-learning, model-reliability https://news.y0.exchange/article/stars-framework-stabilizes-looped-language-models y0 News en 2026-05-27T04:00:00.000Z STARS Framework Stabilizes Looped Language Models looped-language-models, test-time-scaling, latent-reasoning, stability-optimization, neural-architecture, mathematical-reasoning, inference-efficiency https://news.y0.exchange/article/matformbench-benchmarking-materials-inverse-design-algorithms y0 News en 2026-05-27T04:00:00.000Z MatFormBench: Benchmarking Materials Inverse Design Algorithms materials-science, benchmarking, inverse-design, machine-learning, generative-models, diffusion-models, optimization, computational-materials https://news.y0.exchange/article/cordon-mas-defending-rag-against-poisoning-attacks y0 News en 2026-05-27T04:00:00.000Z Cordon-MAS: Defending RAG Against Poisoning Attacks rag-security, poisoning-attacks, ai-safety, information-flow-control, compartmentalization, retrieval-augmented-generation, adversarial-robustness, llm-security https://news.y0.exchange/article/adversarial-rl-solves-infrastructure-optimization y0 News en 2026-05-27T04:00:00.000Z Adversarial RL Solves Infrastructure Optimization reinforcement-learning, optimization, infrastructure-resilience, adversarial-training, bi-level-optimization, computational-efficiency https://news.y0.exchange/article/ai-bias-in-higher-ed-marginalizing-disability-knowledge y0 News en 2026-05-27T04:00:00.000Z AI Bias in Higher Ed: Marginalizing Disability Knowledge ai-bias, epistemic-justice, disability-studies, higher-education, algorithmic-bias, knowledge-systems, generative-ai, equity https://news.y0.exchange/article/r2e-ig-generalization-oriented-vrp-models y0 News en 2026-05-27T04:00:00.000Z R2E-IG: Generalization-Oriented VRP Models deep-reinforcement-learning, vehicle-routing-problem, mixture-of-experts, distribution-generalization, optimization, neural-networks, logistics https://news.y0.exchange/article/rvpo-better-rl-through-ratio-variance-regularization y0 News en 2026-05-27T04:00:00.000Z R²VPO: Better RL Through Ratio-Variance Regularization reinforcement-learning, policy-optimization, llm-training, sample-efficiency, algorithmic-advancement, training-stability, robotic-control https://news.y0.exchange/article/emodistill-strategic-emotion-in-llm-negotiation-agents y0 News en 2026-05-27T04:00:00.000Z EmoDistill: Strategic Emotion in LLM Negotiation Agents language-models, negotiation-ai, emotion-detection, adversarial-settings, offline-learning, lora-fine-tuning, ai-strategy, alignment-safety https://news.y0.exchange/article/rwanda-healthcare-system-assesses-big-data-analytics-for-diabetes y0 News en 2026-05-27T04:00:00.000Z Rwanda Healthcare System Assesses Big Data Analytics for Diabetes healthcare-ai, machine-learning, diabetes-management, rwanda, big-data-analytics, clinical-decision-support, health-informatics, digital-health https://news.y0.exchange/article/sedt-improves-multi-turn-llm-reliability-by-37 y0 News en 2026-05-27T04:00:00.000Z SeDT Improves Multi-Turn LLM Reliability by 37% llm-reliability, multi-turn-conversation, inference-optimization, conversational-ai, reinforcement-learning, semantic-scoring, model-robustness https://news.y0.exchange/article/htmlcure-interactive-browser-testing-for-llm-html-generation y0 News en 2026-05-27T04:00:00.000Z HTMLCure: Interactive Browser Testing for LLM HTML Generation llm-evaluation, html-generation, synthetic-data, model-training, browser-automation, code-generation, benchmarks, ai-infrastructure https://news.y0.exchange/article/llm-hallucination-characterized-by-innovation-property y0 News en 2026-05-27T04:00:00.000Z LLM Hallucination Characterized by Innovation Property large-language-models, hallucination, ai-safety, theoretical-research, machine-learning, model-behavior, calibration https://news.y0.exchange/article/ragear-graph-enhanced-academic-course-recommender y0 News en 2026-05-27T04:00:00.000Z RAGEAR: Graph-Enhanced Academic Course Recommender academic-recommendation, knowledge-graphs, retrieval-augmented, neurosymbolic-ai, course-matching, educational-technology, ranking-algorithms https://news.y0.exchange/article/contextguard-self-auditing-framework-for-llm-context-learning y0 News en 2026-05-27T04:00:00.000Z ContextGuard: Self-Auditing Framework for LLM Context Learning large-language-models, llm-reliability, context-learning, self-auditing, ai-safety, model-evaluation, contextual-reasoning https://news.y0.exchange/article/kalman-evolve-ai-discovered-filters-beat-classical-algorithms y0 News en 2026-05-27T04:00:00.000Z Kalman Evolve: AI-Discovered Filters Beat Classical Algorithms kalman-filter, signal-processing, algorithm-discovery, large-language-models, state-estimation, autonomous-systems, sensor-fusion, control-theory https://news.y0.exchange/article/topological-ai-framework-accelerates-polymer-discovery y0 News en 2026-05-27T04:00:00.000Z Topological AI Framework Accelerates Polymer Discovery topological-deep-learning, polymer-discovery, materials-science, machine-learning, computational-chemistry, property-prediction, drug-discovery, graph-neural-networks https://news.y0.exchange/article/smn-architecture-bridges-cognitivism-embodiment-divide y0 News en 2026-05-27T04:00:00.000Z SMN Architecture Bridges Cognitivism-Embodiment Divide cognitive-science, embodied-cognition, neuroscience, theoretical-framework, consciousness, intentionality, action-patterns https://news.y0.exchange/article/persistent-ai-agents-cut-costs-5x-through-cache-efficiency y0 News en 2026-05-27T04:00:00.000Z Persistent AI Agents Cut Costs 5x Through Cache Efficiency persistent-agents, ai-economics, token-caching, research-methodology, cost-efficiency, enterprise-ai, agent-evaluation, memory-systems https://news.y0.exchange/article/best-teachers-arent-always-best-for-student-models y0 News en 2026-05-27T04:00:00.000Z Best Teachers Aren't Always Best for Student Models llm-training, knowledge-distillation, teacher-student-models, machine-learning, model-optimization, synthetic-data, gradient-analysis https://news.y0.exchange/article/knowledge-graphs-boost-llm-industrial-operations-to-100-accuracy y0 News en 2026-05-27T04:00:00.000Z Knowledge Graphs Boost LLM Industrial Operations to 100% Accuracy knowledge-graphs, llm-reasoning, industrial-ai, data-architecture, semantic-search, enterprise-ai, structured-data, graph-databases https://news.y0.exchange/article/geofaith-detecting-faithful-reasoning-in-llms y0 News en 2026-05-27T04:00:00.000Z GeoFaith: Detecting Faithful Reasoning in LLMs chain-of-thought, faithfulness-detection, llm-reasoning, reinforcement-learning, interpretability, ai-safety, model-evaluation, geometric-analysis https://news.y0.exchange/article/scale-vectors-in-llms-negligible-size-significant-effect y0 News en 2026-05-27T04:00:00.000Z Scale Vectors in LLMs: Negligible Size, Significant Effect large-language-models, model-optimization, normalization-layers, neural-architecture, training-efficiency, scale-vectors, deep-learning, pretraining https://news.y0.exchange/article/llms-and-design-patterns-guiding-ai-code-generation y0 News en 2026-05-27T04:00:00.000Z LLMs and Design Patterns: Guiding AI Code Generation llm-code-generation, design-patterns, software-architecture, prompt-engineering, ai-development, code-quality, singleton-pattern, model-evaluation https://news.y0.exchange/article/icicle-in-context-generative-retrieval-framework y0 News en 2026-05-27T04:00:00.000Z ICICLE: In-Context Generative Retrieval Framework generative-retrieval, in-context-learning, document-indexing, parametric-memory, ml-infrastructure, corpus-expansion, information-retrieval, neural-search https://news.y0.exchange/article/anonymous-gbdt-training-with-privacy-preserving-cryptography y0 News en 2026-05-27T04:00:00.000Z Anonymous GBDT Training with Privacy-Preserving Cryptography privacy-preserving-ml, secure-computation, gbdt-training, cryptography, homomorphic-encryption, psi, machine-learning-security, structured-data https://news.y0.exchange/article/eeg-foundation-models-audit-reveals-supervised-baselines y0 News en 2026-05-27T04:00:00.000Z EEG Foundation Models Audit Reveals Supervised Baselines eeg-models, foundation-models, neural-decoding, benchmarking, model-evaluation, interpretability, brain-computer-interface, ai-research https://news.y0.exchange/article/rlvr-data-allocation-depth-complexity-reasoning y0 News en 2026-05-27T04:00:00.000Z RLVR Data Allocation: Depth, Complexity & Reasoning rlvr, reasoning-models, reinforcement-learning, post-training, abductive-reasoning, data-allocation, ai-research, training-optimization https://news.y0.exchange/article/bequ-new-llm-knowledge-benchmark-beyond-questions y0 News en 2026-05-27T04:00:00.000Z BeQu: New LLM Knowledge Benchmark Beyond Questions llm-evaluation, knowledge-benchmarking, parametric-knowledge, ai-research, language-models, bequ-benchmark, model-assessment, availability-bias, transformer-evaluation https://news.y0.exchange/article/juice-benchmark-reveals-llms-struggle-with-cultural-error-detection y0 News en 2026-05-27T04:00:00.000Z JuICE Benchmark Reveals LLMs Struggle With Cultural Error Detection llm-evaluation, cultural-competence, benchmark, multilingual-ai, ai-safety, cultural-errors, nlp-evaluation, global-deployment https://news.y0.exchange/article/tournament-grpo-relative-rewards-for-llm-long-form-generation y0 News en 2026-05-27T04:00:00.000Z Tournament-GRPO: Relative Rewards for LLM Long-Form Generation reinforcement-learning, llm-training, reward-modeling, long-form-generation, grpo, nlp, tournament-design https://news.y0.exchange/article/recon-reconstruction-guided-reasoning-for-user-modeling y0 News en 2026-05-27T04:00:00.000Z Recon: Reconstruction-Guided Reasoning for User Modeling user-modeling, reasoning-synthesis, language-models, action-reconstruction, behavioral-ai, causal-reasoning, interpretability https://news.y0.exchange/article/cppo-coordinated-strategy-optimization-for-code-generation y0 News en 2026-05-27T04:00:00.000Z CPPO: Coordinated Strategy Optimization for Code Generation code-generation, ai-research, reinforcement-learning, competitive-programming, model-optimization, pass-k, algorithm-diversity https://news.y0.exchange/article/timestep-aware-svdquant-gptq-for-video-model-compression y0 News en 2026-05-27T04:00:00.000Z Timestep-Aware SVDQuant-GPTQ for Video Model Compression quantization, video-diffusion, mixture-of-experts, model-compression, transformer-optimization, w4a4, gpu-memory, inference-efficiency https://news.y0.exchange/article/reasonops-unified-framework-for-trustworthy-llm-reasoning y0 News en 2026-05-27T04:00:00.000Z ReasonOps: Unified Framework for Trustworthy LLM Reasoning llm-reasoning, formal-verification, trustworthy-ai, safety-critical, autonomous-systems, ai-infrastructure, symbolic-reasoning, runtime-assurance https://news.y0.exchange/article/uncertainty-estimators-fail-to-reliably-detect-llm-hallucinations y0 News en 2026-05-27T04:00:00.000Z Uncertainty Estimators Fail to Reliably Detect LLM Hallucinations llm-hallucinations, uncertainty-estimation, ai-reliability, model-safety, rag-evaluation, factuality-detection, ai-deployment https://news.y0.exchange/article/black-box-attacks-detect-unauthorized-training-data-in-ai-models y0 News en 2026-05-27T04:00:00.000Z Black-Box Attacks Detect Unauthorized Training Data in AI Models membership-inference-attacks, diffusion-models, image-generation, privacy-security, generative-ai, copyright-infringement, black-box-attacks, model-security https://news.y0.exchange/article/early-stopping-rollout-improves-ai-model-training-efficiency y0 News en 2026-05-27T04:00:00.000Z Early Stopping Rollout Improves AI Model Training Efficiency machine-learning, distillation, training-efficiency, model-optimization, early-stopping, on-policy-learning https://news.y0.exchange/article/llm-computation-efficiency-s-trace-method-reveals-modular-processing y0 News en 2026-05-27T04:00:00.000Z LLM Computation Efficiency: s-Trace Method Reveals Modular Processing llm-efficiency, transformer-architecture, computation-analysis, model-optimization, neural-networks, parameter-utilization, research https://news.y0.exchange/article/ai-agent-security-gaps-persist-across-proprietary-systems y0 News en 2026-05-27T04:00:00.000Z AI Agent Security Gaps Persist Across Proprietary Systems ai-security, autonomous-agents, penetration-testing, vulnerabilities, proprietary-systems, agent-frameworks, security-research https://news.y0.exchange/article/conver-ai-powered-formal-c-program-verification y0 News en 2026-05-27T04:00:00.000Z ConVer: AI-Powered Formal C Program Verification formal-verification, llm-synthesis, software-security, bounded-model-checking, contract-synthesis, automated-verification, c-program-verification https://news.y0.exchange/article/quack-framework-reveals-ai-hallucination-in-social-deduction y0 News en 2026-05-27T04:00:00.000Z QUACK Framework Reveals AI Hallucination in Social Deduction ai-evaluation, vision-language-models, hallucination-detection, agent-reasoning, multimodal-ai, grounding-consistency, ai-safety, language-perception https://news.y0.exchange/article/e3-ai-review-assistant-outperforms-human-peer-review y0 News en 2026-05-27T04:00:00.000Z E3: AI Review Assistant Outperforms Human Peer Review automated-review, peer-review, research-validation, llm-evaluation, academic-ai, quality-assurance, backtesting, technical-critique https://news.y0.exchange/article/grokking-and-double-descent-explained-via-learning-decomposition y0 News en 2026-05-27T04:00:00.000Z Grokking and Double Descent Explained via Learning Decomposition neural-networks, grokking, double-descent, representation-learning, deep-learning-theory, interpretability, generalization, training-dynamics https://news.y0.exchange/article/trqam-stable-off-policy-rl-for-pretrained-models y0 News en 2026-05-27T04:00:00.000Z TRQAM: Stable Off-Policy RL for Pretrained Models reinforcement-learning, off-policy-learning, flow-policies, trust-region, stochastic-control, model-stability, pretrained-models https://news.y0.exchange/article/remoe-optimizing-moe-inference-through-router-fine-tuning y0 News en 2026-05-27T04:00:00.000Z ReMoE: Optimizing MoE Inference Through Router Fine-Tuning mixture-of-experts, inference-optimization, memory-efficiency, llm-deployment, router-fine-tuning, edge-computing, deepseek, qwen, cache-locality, sparse-models https://news.y0.exchange/article/mird-reliable-qa-predictions-via-risk-decomposition y0 News en 2026-05-27T04:00:00.000Z MiRD: Reliable QA Predictions via Risk Decomposition conformal-prediction, hallucination-mitigation, question-answering, uncertainty-quantification, language-models, risk-decomposition, calibration, ai-reliability https://news.y0.exchange/article/gan-diffusion-framework-generates-realistic-financial-time-series y0 News en 2026-05-27T04:00:00.000Z GAN-Diffusion Framework Generates Realistic Financial Time-Series synthetic-data, generative-ai, gans, diffusion-models, financial-modeling, time-series, quantitative-finance, machine-learning https://news.y0.exchange/article/dei-diversity-drives-llm-ensemble-performance y0 News en 2026-05-27T04:00:00.000Z DEI: Diversity Drives LLM Ensemble Performance evolutionary-algorithms, large-language-models, distributed-ai, quality-diversity-search, ensemble-methods, competitive-programming, model-diversity https://news.y0.exchange/article/ai-augmented-lakehouses-fixing-data-mesh-implementation y0 News en 2026-05-27T04:00:00.000Z AI-Augmented Lakehouses: Fixing Data Mesh Implementation data-mesh, lakehouse-architecture, llm-governance, enterprise-ai, data-platforms, ai-automation, organizational-design, data-products https://news.y0.exchange/article/deep-unfolding-networks-convergence-stability-analysis y0 News en 2026-05-27T04:00:00.000Z Deep Unfolding Networks: Convergence & Stability Analysis deep-unfolding, neural-networks, optimization-theory, convergence-analysis, forward-backward-splitting, theoretical-ai, machine-learning https://news.y0.exchange/article/semprobe-semantic-robustness-testing-for-safety-critical-vision y0 News en 2026-05-27T04:00:00.000Z SemProbe: Semantic Robustness Testing for Safety-Critical Vision object-detection, safety-testing, ai-robustness, vision-systems, semantic-corruption, compliance, manufacturing-ai, diffusion-models https://news.y0.exchange/article/litseg-narrative-aware-document-segmentation-for-rag y0 News en 2026-05-27T04:00:00.000Z LitSeg: Narrative-Aware Document Segmentation for RAG rag, document-segmentation, llm, retrieval, narrative-analysis, knowledge-distillation, literary-ai, information-retrieval https://news.y0.exchange/article/text-embeddings-miss-human-expert-judgment-by-26 y0 News en 2026-05-27T04:00:00.000Z Text Embeddings Miss Human Expert Judgment by 26% text-embeddings, nlp-validation, semantic-alignment, embedding-reliability, human-expert-gap, model-evaluation, domain-expertise, clustering-performance https://news.y0.exchange/article/ai-sound-design-gap-practitioners-prefer-task-specific-over-generativ y0 News en 2026-05-27T04:00:00.000Z AI Sound Design Gap: Practitioners Prefer Task-Specific Over Generativ ai-tools, creative-industry, sound-design, audio-production, workflow-integration, human-ai-collaboration, practitioner-research https://news.y0.exchange/article/foundobj-label-free-3d-segmentation-via-foundation-models y0 News en 2026-05-27T04:00:00.000Z FoundObj: Label-Free 3D Segmentation via Foundation Models 3d-segmentation, self-supervised-learning, foundation-models, reinforcement-learning, computer-vision, point-clouds, label-free-learning, zero-shot-learning https://news.y0.exchange/article/smart-reasoning-timing-for-real-time-audio-ai-models y0 News en 2026-05-27T04:00:00.000Z Smart Reasoning Timing for Real-Time Audio AI Models large-audio-language-models, streaming-ai, real-time-reasoning, policy-optimization, voice-interfaces, model-controllability, qwen2.5, conversational-ai https://news.y0.exchange/article/generative-animations-ai-system-for-prompt-driven-motion-synthesis y0 News en 2026-05-27T04:00:00.000Z Generative Animations: AI System for Prompt-Driven Motion Synthesis generative-ai, animation-synthesis, llm, computer-vision, creative-automation, motion-design, ai-research, design-tools https://news.y0.exchange/article/twist-semantic-token-sync-for-wireless-digital-twins y0 News en 2026-05-27T04:00:00.000Z TWIST: Semantic Token Sync for Wireless Digital Twins digital-twins, wireless-communication, semantic-synchronization, edge-computing, adaptive-networks, iot, error-protection, task-aware-transmission https://news.y0.exchange/article/qiskit-quantumkatas-benchmark-for-llm-quantum-computing y0 News en 2026-05-27T04:00:00.000Z Qiskit QuantumKatas Benchmark for LLM Quantum Computing quantum-computing, llm-benchmarks, ai-evaluation, qiskit, algorithm-reasoning, language-models, prompt-engineering https://news.y0.exchange/article/logical-pluralism-in-formal-reasoning-systems y0 News en 2026-05-27T04:00:00.000Z Logical Pluralism in Formal Reasoning Systems formal-reasoning, logical-pluralism, proof-assistants, knowledge-representation, computational-metaphysics, logikey-methodology, higher-order-logic, automated-reasoning https://news.y0.exchange/article/lucos-unsupervised-context-selection-for-tabular-ai y0 News en 2026-05-27T04:00:00.000Z LUCoS: Unsupervised Context Selection for Tabular AI tabular-learning, foundation-models, instance-selection, unsupervised-learning, machine-learning, tabpfn, embeddings, data-efficiency https://news.y0.exchange/article/pipo-efficient-llm-inference-through-latent-multi-token-prediction y0 News en 2026-05-27T04:00:00.000Z PIPO: Efficient LLM Inference Through Latent Multi-Token Prediction llm-inference, multi-token-prediction, latent-compression, speculative-decoding, model-efficiency, neural-architecture https://news.y0.exchange/article/pilottts-competitive-speech-synthesis-without-massive-data y0 News en 2026-05-27T04:00:00.000Z PilotTTS: Competitive Speech Synthesis Without Massive Data text-to-speech, tts, open-source, speech-synthesis, data-efficiency, voice-cloning, ai-research, neural-networks https://news.y0.exchange/article/word-coverage-score-reveals-llm-sampling-suppresses-vocabulary y0 News en 2026-05-27T04:00:00.000Z Word Coverage Score Reveals LLM Sampling Suppresses Vocabulary llm-decoding, sampling-mechanics, text-generation, linguistic-diversity, vocabulary-coverage, model-optimization, probability-distributions, output-quality https://news.y0.exchange/article/finevla-fine-grained-instruction-alignment-for-robots y0 News en 2026-05-27T04:00:00.000Z FineVLA: Fine-Grained Instruction Alignment for Robots robotics, vision-language-models, instruction-alignment, embodied-ai, robot-learning, dataset-benchmark, multimodal-ai, policy-learning https://news.y0.exchange/article/falcon-x-advanced-multivariate-time-series-foundation-model y0 News en 2026-05-27T04:00:00.000Z Falcon-X: Advanced Multivariate Time Series Foundation Model time-series-forecasting, foundation-models, multivariate-modeling, machine-learning, deep-learning, latent-space, attention-mechanisms, benchmarking https://news.y0.exchange/article/llm-conformity-driven-by-uncertainty-not-just-sycophancy y0 News en 2026-05-27T04:00:00.000Z LLM Conformity Driven by Uncertainty, Not Just Sycophancy llm-research, conformity-bias, epistemic-uncertainty, model-behavior, alignment, rlhf, ai-safety, framework https://news.y0.exchange/article/fuzzy-logic-framework-reduces-alert-fatigue-in-ids y0 News en 2026-05-27T04:00:00.000Z Fuzzy Logic Framework Reduces Alert Fatigue in IDS intrusion-detection, alert-prioritization, fuzzy-logic, cybersecurity, machine-learning, threat-detection, ids-systems, uncertainty-modeling https://news.y0.exchange/article/agent-runtime-evolution-framework-enables-governed-self-modification y0 News en 2026-05-27T04:00:00.000Z Agent Runtime Evolution Framework Enables Governed Self-Modification agent-runtimes, executable-code, governance-frameworks, autonomous-systems, multi-agent-systems, ai-infrastructure, runtime-adaptation https://news.y0.exchange/article/edgeflow-hybrid-vlm-approach-improves-industrial-flowchart-processing y0 News en 2026-05-27T04:00:00.000Z EdgeFlow: Hybrid VLM Approach Improves Industrial Flowchart Processing vision-language-models, requirements-engineering, flowchart-processing, edge-detection, ai-methodology, industrial-automation, vlm-augmentation, topology-preservation https://news.y0.exchange/article/social-gaze-consistency-new-method-for-ai-generated-image-detection y0 News en 2026-05-27T04:00:00.000Z Social Gaze Consistency: New Method for AI-Generated Image Detection ai-detection, deepfake-detection, generative-models, image-forensics, computer-vision, semantic-detection, diffusion-models https://news.y0.exchange/article/saerl-llm-post-training-via-model-internals y0 News en 2026-05-27T04:00:00.000Z SAERL: LLM Post-training via Model Internals llm-training, sparse-autoencoders, reinforcement-learning, mechanistic-interpretability, post-training-optimization, model-internals, data-engineering, curriculum-learning https://news.y0.exchange/article/mobilemoe-efficient-on-device-language-models y0 News en 2026-05-27T04:00:00.000Z MobileMoE: Efficient On-Device Language Models mobile-ai, mixture-of-experts, language-models, on-device-inference, model-efficiency, edge-computing, llm-scaling, quantization https://news.y0.exchange/article/genesis-ai-agents-transform-6g-network-development y0 News en 2026-05-27T04:00:00.000Z GENESIS: AI Agents Transform 6G Network Development 6g-networks, ai-agents, radio-access-networks, llm-applications, network-automation, infrastructure-ai, telecommunications https://news.y0.exchange/article/locateanything-parallel-box-decoding-for-vision-language-models y0 News en 2026-05-27T04:00:00.000Z LocateAnything: Parallel Box Decoding for Vision-Language Models vision-language-models, object-detection, parallel-decoding, computer-vision, machine-learning, inference-optimization, dataset-engineering, visual-grounding https://news.y0.exchange/article/algorithmic-hiring-monoculture-creates-racial-disparities y0 News en 2026-05-27T04:00:00.000Z Algorithmic Hiring Monoculture Creates Racial Disparities algorithmic-bias, hiring-discrimination, monoculture-risk, ai-fairness, employment-law, vendor-concentration, systemic-bias, regulatory-risk https://news.y0.exchange/article/multi-agent-causal-discovery-framework-outperforms-llm-baselines y0 News en 2026-05-27T04:00:00.000Z Multi-Agent Causal Discovery Framework Outperforms LLM Baselines causal-discovery, multi-agent-ai, large-language-models, machine-learning, research-advancement, statistical-methods, ai-reasoning, benchmark-testing https://news.y0.exchange/article/lipup-ma-ai-framework-transforms-urban-planning-through-simulation y0 News en 2026-05-27T04:00:00.000Z LiPUP-MA: AI Framework Transforms Urban Planning Through Simulation urban-planning, llm-agents, participatory-design, multi-agent-systems, ai-research https://news.y0.exchange/article/thought-aligner-ai-safety-model-improves-agent-reasoning y0 News en 2026-05-27T04:00:00.000Z Thought-Aligner: AI Safety Model Improves Agent Reasoning ai-safety, llm-agents, behavioral-alignment, thought-correction, autonomous-systems, guardrails, model-agnostic https://news.y0.exchange/article/doc-cob-progressive-visual-reasoning-for-document-understanding y0 News en 2026-05-27T04:00:00.000Z Doc-CoB: Progressive Visual Reasoning for Document Understanding document-understanding, multimodal-ai, vision-language-models, chain-of-boxes, visual-reasoning, information-extraction, llm-improvement, layout-analysis https://news.y0.exchange/article/chain-of-thought-mechanistic-interpretability-analysis y0 News en 2026-05-27T04:00:00.000Z Chain-of-Thought Mechanistic Interpretability Analysis chain-of-thought, interpretability, llm-reasoning, mechanistic-analysis, prompt-engineering, neuron-activation, ai-research https://news.y0.exchange/article/evoemo-evolved-emotional-policies-for-llm-negotiation-agents y0 News en 2026-05-27T04:00:00.000Z EvoEmo: Evolved Emotional Policies for LLM Negotiation Agents llm-agents, reinforcement-learning, evolutionary-algorithms, negotiation-ai, emotional-intelligence, multi-turn-dialogue, chain-of-thought, agentic-ai https://news.y0.exchange/article/pta-grpo-two-stage-llm-reasoning-framework y0 News en 2026-05-27T04:00:00.000Z PTA-GRPO: Two-Stage LLM Reasoning Framework llm-reasoning, chain-of-thought, reinforcement-learning, planning-optimization, ai-research, mathematical-reasoning, model-improvement https://news.y0.exchange/article/ai-framework-for-fair-team-contribution-evaluation y0 News en 2026-05-27T04:00:00.000Z AI Framework for Fair Team Contribution Evaluation ai-evaluation, conflict-resolution, team-dynamics, llm-framework, workload-assessment, performance-management, hr-tech, algorithmic-fairness https://news.y0.exchange/article/patas-framework-brings-trust-propagation-to-neural-networks y0 News en 2026-05-27T04:00:00.000Z PaTAS Framework Brings Trust Propagation to Neural Networks trust-assessment, neural-networks, subjective-logic, ai-safety, interpretability, adversarial-robustness, model-reliability, trustworthiness https://news.y0.exchange/article/lec-framework-enables-statistical-error-control-in-ai-models y0 News en 2026-05-27T04:00:00.000Z LEC Framework Enables Statistical Error Control in AI Models foundation-models, risk-control, selective-prediction, uncertainty-estimation, model-reliability, conformal-prediction, ai-safety, model-routing https://news.y0.exchange/article/towermind-llm-agent-benchmark-with-tower-defense y0 News en 2026-05-27T04:00:00.000Z TowerMind: LLM Agent Benchmark with Tower Defense llm-agents, benchmark, ai-evaluation, real-time-strategy, decision-making, tower-defense, reinforcement-learning, multimodal-learning https://news.y0.exchange/article/drive-p2d-progressive-vlm-benchmark-for-autonomous-driving y0 News en 2026-05-27T04:00:00.000Z Drive-P2D: Progressive VLM Benchmark for Autonomous Driving autonomous-driving, vision-language-models, ai-benchmarking, perception-decision, safety-evaluation, vlm-testing, failure-analysis https://news.y0.exchange/article/ai-agent-automates-legacy-code-translation-to-devito y0 News en 2026-05-27T04:00:00.000Z AI Agent Automates Legacy Code Translation to Devito code-translation, ai-agents, rag, devito, legacy-modernization, scientific-computing, llm, reinforcement-learning https://news.y0.exchange/article/cot-compression-54x-speedup-for-efficient-llm-reasoning y0 News en 2026-05-27T04:00:00.000Z CoT Compression: 54x Speedup for Efficient LLM Reasoning chain-of-thought, llm-efficiency, reasoning-compression, computational-optimization, alicot, latent-reasoning, theoretical-ai, model-inference https://news.y0.exchange/article/ucpo-improving-llm-reliability-through-uncertainty-aware-training y0 News en 2026-05-27T04:00:00.000Z UCPO: Improving LLM Reliability Through Uncertainty-Aware Training llm-training, reinforcement-learning, uncertainty-quantification, model-reliability, policy-optimization, ai-safety https://news.y0.exchange/article/qrita-14x-faster-llm-sampling-with-pivot-based-truncation y0 News en 2026-05-27T04:00:00.000Z Qrita: 1.4x Faster LLM Sampling with Pivot-Based Truncation llm-inference, gpu-optimization, sampling-algorithms, vllm, transformer-performance, computational-efficiency https://news.y0.exchange/article/unified-framework-needed-for-llm-agent-evaluation y0 News en 2026-05-27T04:00:00.000Z Unified Framework Needed for LLM Agent Evaluation llm-agents, evaluation-frameworks, standardization, benchmark, reproducibility, ai-research, methodology https://news.y0.exchange/article/persona-generators-diverse-synthetic-ai-personas y0 News en 2026-05-27T04:00:00.000Z Persona Generators: Diverse Synthetic AI Personas synthetic-personas, ai-evaluation, generative-agents, diversity-testing, llm-optimization, bias-detection, ai-safety https://news.y0.exchange/article/dianoia-diagnostic-framework-for-multi-agent-llm-systems y0 News en 2026-05-27T04:00:00.000Z DIANOIA: Diagnostic Framework for Multi-Agent LLM Systems multi-agent-llm, reasoning-systems, diagnostic-framework, token-efficiency, ai-optimization, benchmark-performance https://news.y0.exchange/article/hi-sam-hierarchical-multi-modal-recommendation-framework y0 News en 2026-05-27T04:00:00.000Z Hi-SAM: Hierarchical Multi-Modal Recommendation Framework recommendation-systems, multi-modal-ai, transformer-architecture, tokenization, large-scale-deployment, machine-learning, semantic-representation https://news.y0.exchange/article/ai-agents-boost-supply-chain-costs-67-but-face-reliability y0 News en 2026-05-27T04:00:00.000Z AI Agents Boost Supply Chain Costs 67% But Face Reliability autonomous-agents, supply-chain, llm-reliability, reinforcement-learning, multi-agent-systems, decision-stability, enterprise-ai https://news.y0.exchange/article/graphmind-ai-driven-workflow-automation-for-enterprise y0 News en 2026-05-27T04:00:00.000Z GraphMind: AI-Driven Workflow Automation for Enterprise workflow-automation, llm-reasoning, incident-response, multi-agent-systems, operational-ai, graph-learning, cloud-infrastructure, reinforcement-learning https://news.y0.exchange/article/agentic-affordance-profile-framework-for-knowledge-graph-discovery y0 News en 2026-05-27T04:00:00.000Z Agentic Affordance Profile Framework for Knowledge Graph Discovery knowledge-graphs, semantic-web, agent-systems, formal-methods, metadata-standards, epistemic-logic, ai-infrastructure, ontologies https://news.y0.exchange/article/agentatlas-diagnostic-framework-for-llm-agent-evaluation y0 News en 2026-05-27T04:00:00.000Z AgentAtlas: Diagnostic Framework for LLM Agent Evaluation llm-agents, benchmark-evaluation, agent-taxonomy, ai-safety, evaluation-methodology, decision-quality, trajectory-analysis https://news.y0.exchange/article/structured-ai-for-reliable-data-system-composition y0 News en 2026-05-27T04:00:00.000Z Structured AI for Reliable Data System Composition agentic-discovery, data-systems, llm-agents, infrastructure-composition, multi-system-backends, structured-search, ai-engineering https://news.y0.exchange/article/scenepilot-boundary-driven-av-safety-testing-framework y0 News en 2026-05-27T04:00:00.000Z ScenePilot: Boundary-Driven AV Safety Testing Framework autonomous-vehicles, safety-testing, simulation, scenario-generation, reinforcement-learning, av-validation, robotics https://news.y0.exchange/article/search-e1-simplified-self-evolution-for-reasoning-agents y0 News en 2026-05-27T04:00:00.000Z Search-E1: Simplified Self-Evolution for Reasoning Agents language-models, post-training, self-distillation, reasoning-agents, qwen, grpo, qa-benchmarks, open-source https://news.y0.exchange/article/inverse-learning-fast-ai-planning-framework-outperforms-rl y0 News en 2026-05-27T04:00:00.000Z Inverse Learning: Fast AI Planning Framework Outperforms RL inverse-learning, embodied-ai, planning-control, reinforcement-learning, quantum-optimization, neural-models, robotics, computational-efficiency https://news.y0.exchange/article/llm-benchmarking-bias-production-inference-measurement-flaws y0 News en 2026-05-27T04:00:00.000Z LLM Benchmarking Bias: Production Inference Measurement Flaws llm-benchmarking, measurement-bias, production-inference, performance-metrics, serving-infrastructure, latency-measurement, python-gil, evaluation-methodology https://news.y0.exchange/article/trajel-auditing-llm-agent-hallucinations-in-workflows y0 News en 2026-05-27T04:00:00.000Z Trajel: Auditing LLM Agent Hallucinations in Workflows llm-safety, hallucination-detection, autonomous-agents, ai-evaluation, trajectory-analysis, industrial-ai, benchmark, agentic-systems https://news.y0.exchange/article/synthetic-patent-data-volume-vs-quality-trade-offs y0 News en 2026-05-27T04:00:00.000Z Synthetic Patent Data: Volume vs. Quality Trade-offs synthetic-data, llm-evaluation, patent-classification, machine-learning, data-fidelity, multi-label-classification, volume-vs-quality https://news.y0.exchange/article/globaldentbench-reveals-31-unsafe-llm-clinical-recommendations y0 News en 2026-05-27T04:00:00.000Z GlobalDentBench Reveals 31% Unsafe LLM Clinical Recommendations llm-safety, clinical-ai, healthcare-validation, ai-benchmarking, medical-reasoning, dentistry, risk-assessment, model-evaluation https://news.y0.exchange/article/pando-efficient-ai-agents-through-online-skill-distillation y0 News en 2026-05-27T04:00:00.000Z PANDO: Efficient AI Agents Through Online Skill Distillation multimodal-ai, agent-efficiency, skill-distillation, llm-optimization, web-agents, prompt-caching, benchmark-evaluation https://news.y0.exchange/article/frontieror-benchmarking-llms-algorithm-design-capacity y0 News en 2026-05-27T04:00:00.000Z FrontierOR: Benchmarking LLMs' Algorithm Design Capacity llm-benchmarking, optimization-algorithms, large-language-models, operations-research, algorithm-design, ai-evaluation, computational-efficiency https://news.y0.exchange/article/self-reset-policy-optimization-improves-language-model-reasoning y0 News en 2026-05-27T04:00:00.000Z Self-Reset Policy Optimization Improves Language Model Reasoning language-models, reinforcement-learning, credit-assignment, reasoning, policy-optimization, arxiv, ai-training https://news.y0.exchange/article/evomap-study-flaws-in-decentralized-ai-agent-networks y0 News en 2026-05-27T04:00:00.000Z EvoMap Study: Flaws in Decentralized AI Agent Networks agent-networks, ai-infrastructure, incentive-design, verification, decentralized-systems, quality-assurance, autonomous-agents https://news.y0.exchange/article/resampling-outperforms-retrying-in-ai-safety-monitoring y0 News en 2026-05-27T04:00:00.000Z Resampling Outperforms Retrying in AI Safety Monitoring ai-safety, model-control, adversarial-alignment, monitoring, claude-opus, resampling, ai-security, research https://news.y0.exchange/article/prioritized-knowledge-base-repairs-complexity-argumentation y0 News en 2026-05-27T04:00:00.000Z Prioritized Knowledge Base Repairs: Complexity & Argumentation knowledge-bases, inconsistency-handling, complexity-theory, argumentation-frameworks, semantic-web, ontologies, formal-reasoning https://news.y0.exchange/article/hypercrl-continual-robot-learning-without-data-replay y0 News en 2026-05-27T04:00:00.000Z HyperCRL: Continual Robot Learning Without Data Replay reinforcement-learning, robotics, hypernetworks, continual-learning, dynamics-models, model-based-rl, robot-learning https://news.y0.exchange/article/llm-quantization-trade-offs-fp8-int8-int4-comparison y0 News en 2026-05-27T04:00:00.000Z LLM Quantization Trade-Offs: FP8, INT8, INT4 Comparison llm-quantization, model-optimization, inference-efficiency, llama-3.1, fp8, int8, int4, ai-infrastructure, computational-efficiency, deployment-guidelines https://news.y0.exchange/article/mimic-score-efficient-data-selection-via-model-weights y0 News en 2026-05-27T04:00:00.000Z Mimic Score: Efficient Data Selection via Model Weights data-selection, machine-learning, training-efficiency, clip-models, gradient-alignment, dataset-filtering, computational-optimization, model-weights https://news.y0.exchange/article/drl-for-vehicular-edge-computing-survey-future-directions y0 News en 2026-05-27T04:00:00.000Z DRL for Vehicular Edge Computing: Survey & Future Directions deep-reinforcement-learning, vehicular-edge-computing, intelligent-transportation, computational-offloading, multi-agent-systems, edge-computing, autonomous-vehicles https://news.y0.exchange/article/q-learning-boosts-offline-in-context-rl-performance-30 y0 News en 2026-05-27T04:00:00.000Z Q-Learning Boosts Offline In-Context RL Performance 30% offline-rl, in-context-learning, reinforcement-learning, ai-research, algorithm-optimization, machine-learning https://news.y0.exchange/article/sign-language-segmentation-transformer-achieves-sota-results y0 News en 2026-05-27T04:00:00.000Z Sign Language Segmentation: Transformer Achieves SOTA Results sign-language-processing, transformer-architecture, sequence-segmentation, accessibility-ai, computer-vision, temporal-modeling, dataset-annotation, nlp https://news.y0.exchange/article/chain-of-thought-reasoning-semantics-or-statistical-artifacts y0 News en 2026-05-27T04:00:00.000Z Chain of Thought Reasoning: Semantics or Statistical Artifacts? chain-of-thought, reasoning-models, llm-interpretability, transformer-training, semantic-analysis, model-behavior, arxiv-research, ai-safety https://news.y0.exchange/article/ocr-reasoning-benchmark-reveals-mllm-limitations y0 News en 2026-05-27T04:00:00.000Z OCR-Reasoning Benchmark Reveals MLLM Limitations mllm-evaluation, ocr-reasoning, multimodal-ai, text-recognition, benchmark, vision-language, ai-limitations, model-assessment https://news.y0.exchange/article/mp-ssm-graph-learning-with-state-space-models y0 News en 2026-05-27T04:00:00.000Z MP-SSM: Graph Learning with State-Space Models graph-neural-networks, state-space-models, message-passing, deep-learning, sequence-modeling, permutation-equivariance, neural-architecture, theoretical-analysis https://news.y0.exchange/article/rop-enhancing-llm-robustness-against-adversarial-perturbations y0 News en 2026-05-27T04:00:00.000Z RoP: Enhancing LLM Robustness Against Adversarial Perturbations large-language-models, prompting-strategy, adversarial-robustness, ai-safety, error-correction, model-reliability, nlp-research https://news.y0.exchange/article/casarbi-self-cascaded-diffusion-for-image-super-resolution y0 News en 2026-05-27T04:00:00.000Z CasArbi: Self-Cascaded Diffusion for Image Super-Resolution image-super-resolution, diffusion-models, computer-vision, arbitrary-scale-upsampling, generative-models, cascaded-architecture, deep-learning, image-enhancement https://news.y0.exchange/article/athena-prm-efficient-multimodal-reasoning-with-process-rewards y0 News en 2026-05-27T04:00:00.000Z Athena-PRM: Efficient Multimodal Reasoning with Process Rewards process-reward-models, multimodal-ai, reasoning-evaluation, machine-learning, data-efficiency, benchmark-performance, model-training, visual-reasoning https://news.y0.exchange/article/genre-control-in-music-generation-via-activation-steering y0 News en 2026-05-27T04:00:00.000Z Genre Control in Music Generation via Activation Steering music-generation, generative-ai, transformers, activation-steering, interpretability, human-ai-collaboration, musicgen, inference-optimization https://news.y0.exchange/article/few-shot-ood-detection-with-adaptive-multi-prompt-networks y0 News en 2026-05-27T04:00:00.000Z Few-Shot OOD Detection with Adaptive Multi-Prompt Networks few-shot-learning, out-of-distribution-detection, clip, contrastive-learning, prompt-engineering, ai-safety, anomaly-detection https://news.y0.exchange/article/real-time-progress-prediction-in-reasoning-models y0 News en 2026-05-27T04:00:00.000Z Real-Time Progress Prediction in Reasoning Models language-models, reasoning, interpretability, chain-of-thought, progress-prediction, model-transparency, research https://news.y0.exchange/article/phyworldbench-evaluating-physics-in-ai-video-models y0 News en 2026-05-27T04:00:00.000Z PhyWorldBench: Evaluating Physics in AI Video Models video-generation, benchmark, physics-simulation, text-to-video, model-evaluation, ai-research, multimodal-llm, prompt-engineering https://news.y0.exchange/article/picaco-aligning-llms-with-conflicting-values y0 News en 2026-05-27T04:00:00.000Z PICACO: Aligning LLMs With Conflicting Values llm-alignment, value-pluralism, in-context-learning, prompt-optimization, ai-safety, total-correlation, model-alignment, human-values https://news.y0.exchange/article/physics-informed-neural-network-accelerates-3d-microwave-scattering y0 News en 2026-05-27T04:00:00.000Z Physics-Informed Neural Network Accelerates 3D Microwave Scattering physics-informed-neural-networks, electromagnetic-modeling, radar-design, computational-acceleration, machine-learning-physics, surrogate-models, electromagnetic-simulation https://news.y0.exchange/article/llm-reliability-for-re-ranking-explainability-vs-accuracy y0 News en 2026-05-27T04:00:00.000Z LLM Reliability for Re-ranking: Explainability vs Accuracy large-language-models, llm-reliability, ranking-systems, semantic-understanding, model-explainability, training-methods, ai-transparency, information-retrieval https://news.y0.exchange/article/llm-based-schema-inference-for-tabular-data y0 News en 2026-05-27T04:00:00.000Z LLM-Based Schema Inference for Tabular Data schema-inference, llm, tabular-data, data-integration, metadata-extraction, data-management https://news.y0.exchange/article/scalable-gans-with-transformers-achieve-sota-imagenet y0 News en 2026-05-27T04:00:00.000Z Scalable GANs with Transformers Achieve SOTA ImageNet generative-models, gans, transformers, image-generation, latent-space, scaling, diffusion-alternatives, computer-vision https://news.y0.exchange/article/llms-show-self-bias-in-automated-benchmarking-systems y0 News en 2026-05-27T04:00:00.000Z LLMs Show Self-Bias in Automated Benchmarking Systems llm-evaluation, benchmark-bias, ai-research, model-testing, self-bias, automated-evaluation, machine-translation, methodology https://news.y0.exchange/article/hispec-hierarchical-speculative-decoding-for-llm-inference y0 News en 2026-05-27T04:00:00.000Z HiSpec: Hierarchical Speculative Decoding for LLM Inference llm-inference, speculative-decoding, early-exit-models, model-optimization, throughput, verification-bottleneck, token-generation, ai-efficiency https://news.y0.exchange/article/diffusion-models-enhanced-with-side-information y0 News en 2026-05-27T04:00:00.000Z Diffusion Models Enhanced with Side Information diffusion-models, image-reconstruction, inverse-problems, computer-vision, multi-modal, inference-optimization, machine-learning https://news.y0.exchange/article/mcps-improved-monte-carlo-tree-search-algorithm y0 News en 2026-05-27T04:00:00.000Z MCPS: Improved Monte Carlo Tree Search Algorithm monte-carlo-tree-search, game-ai, algorithms, mcts, general-game-playing, optimization, reinforcement-learning-alternative https://news.y0.exchange/article/self-signals-multi-llm-debate-cuts-costs-while-boosting-accuracy y0 News en 2026-05-27T04:00:00.000Z Self-Signals Multi-LLM Debate Cuts Costs While Boosting Accuracy multi-llm-debate, llm-efficiency, inference-optimization, reasoning-systems, token-compression, ai-research, self-signals, multimodal-llms https://news.y0.exchange/article/econcausal-testing-llm-economic-reasoning-under-context y0 News en 2026-05-27T04:00:00.000Z EconCausal: Testing LLM Economic Reasoning Under Context llm-evaluation, causal-reasoning, economic-ai, context-awareness, benchmark-dataset, decision-support, ai-limitations, finance-ai https://news.y0.exchange/article/parsvoice-2200-hour-persian-tts-dataset-released y0 News en 2026-05-27T04:00:00.000Z ParsVoice: 2,200-Hour Persian TTS Dataset Released persian-language, text-to-speech, dataset-release, multilingual-ai, speech-processing, low-resource-languages, tts-synthesis https://news.y0.exchange/article/securing-multi-agent-llm-systems-against-malicious-agents y0 News en 2026-05-27T04:00:00.000Z Securing Multi-Agent LLM Systems Against Malicious Agents multi-agent-systems, llm-security, ai-safety, adversarial-defense, system-security, distributed-ai https://news.y0.exchange/article/drl-solves-capacitated-location-routing-problems y0 News en 2026-05-27T04:00:00.000Z DRL Solves Capacitated Location-Routing Problems deep-reinforcement-learning, combinatorial-optimization, location-routing-problem, attention-mechanism, vehicle-routing, logistics-optimization, markov-decision-process, encoder-decoder https://news.y0.exchange/article/swap-sequential-watermarking-for-soft-prompt-copyright y0 News en 2026-05-27T04:00:00.000Z SWAP: Sequential Watermarking for Soft Prompt Copyright copyright-protection, watermarking, soft-prompts, vision-language-models, clip, model-auditing, intellectual-property, ai-security https://news.y0.exchange/article/explainable-ai-improves-cardiovascular-risk-from-ct-scans y0 News en 2026-05-27T04:00:00.000Z Explainable AI Improves Cardiovascular Risk from CT Scans medical-ai, cardiovascular-imaging, explainable-ai, cross-domain-reasoning, clinical-decision-support, interpretability, healthcare-tech https://news.y0.exchange/article/cfg-oec-improving-diffusion-model-sampling-quality y0 News en 2026-05-27T04:00:00.000Z CFG-OEC: Improving Diffusion Model Sampling Quality diffusion-models, classifier-free-guidance, stable-diffusion, image-generation, sampling-optimization, machine-learning, ai-research https://news.y0.exchange/article/kandinsky-50-open-source-foundation-models-for-ai y0 News en 2026-05-27T04:00:00.000Z Kandinsky 5.0: Open-Source Foundation Models for AI generative-ai, open-source, foundation-models, image-generation, video-generation, machine-learning, model-release, ai-infrastructure https://news.y0.exchange/article/vla-pruner-efficient-vision-language-action-model-acceleration y0 News en 2026-05-27T04:00:00.000Z VLA-Pruner: Efficient Vision-Language-Action Model Acceleration vision-language-action, token-pruning, embodied-ai, robotics, model-acceleration, vla-inference, computational-efficiency https://news.y0.exchange/article/cascaded-sensing-sparse-sensor-reconstruction-with-ai y0 News en 2026-05-27T04:00:00.000Z Cascaded Sensing: Sparse Sensor Reconstruction with AI machine-learning, diffusion-models, inverse-problems, sensor-networks, scientific-computing, uncertainty-quantification, reconstruction-algorithms https://news.y0.exchange/article/seal-self-evolving-ai-for-knowledge-graph-questions y0 News en 2026-05-27T04:00:00.000Z SEAL: Self-Evolving AI for Knowledge Graph Questions semantic-parsing, knowledge-graphs, conversational-qa, llm-agents, agentic-learning, natural-language-processing, reasoning https://news.y0.exchange/article/efficient-tensor-networks-new-marginalization-method y0 News en 2026-05-27T04:00:00.000Z Efficient Tensor Networks: New Marginalization Method tensor-networks, quantum-computing, machine-learning, circuits, computational-efficiency, parameterization, distribution-estimation https://news.y0.exchange/article/ehrsummarizer-privacy-first-fhir-architecture-for-ehr-summarization y0 News en 2026-05-27T04:00:00.000Z EHRSummarizer: Privacy-First FHIR Architecture for EHR Summarization ehr-summarization, fhir, healthcare-ai, clinical-nlp, health-tech, privacy-aware-ai, medical-interoperability https://news.y0.exchange/article/better-llm-attribution-evaluation-metrics-proposed y0 News en 2026-05-27T04:00:00.000Z Better LLM Attribution Evaluation Metrics Proposed llm-explainability, attribution-methods, evaluation-metrics, xai, decoder-llms, faithfulness, model-interpretability, gradient-based-methods, benchmarking https://news.y0.exchange/article/epiqal-testing-llm-epidemiological-reasoning-capabilities y0 News en 2026-05-27T04:00:00.000Z EpiQAL: Testing LLM Epidemiological Reasoning Capabilities llm-evaluation, epidemiology, reasoning-benchmarks, ai-limitations, medical-ai, evidence-synthesis, multi-step-inference https://news.y0.exchange/article/verpo-dense-verifiable-rewards-for-code-generation-rl y0 News en 2026-05-27T04:00:00.000Z VeRPO: Dense Verifiable Rewards for Code Generation RL reinforcement-learning, code-generation, reward-design, machine-learning, optimization, verifiable-rewards, policy-optimization, ai-research https://news.y0.exchange/article/shadow-unlearning-privacy-first-ai-data-removal y0 News en 2026-05-27T04:00:00.000Z Shadow Unlearning: Privacy-First AI Data Removal machine-unlearning, privacy-preservation, llm-security, gdpr-compliance, neuro-semantic, data-protection https://news.y0.exchange/article/llms-bypass-human-cognition-through-honest-non-signals y0 News en 2026-05-27T04:00:00.000Z LLMs Bypass Human Cognition Through 'Honest Non-Signals' llm-safety, epistemic-vigilance, cognitive-security, ai-alignment, misinformation, human-ai-calibration, conversational-ai, knowledge-work https://news.y0.exchange/article/open-source-mllms-fail-counter-intuitive-visual-tasks y0 News en 2026-05-27T04:00:00.000Z Open-Source MLLMs Fail Counter-Intuitive Visual Tasks multimodal-llm, language-bias, vision-language, model-evaluation, benchmark, open-source-ai, alignment, mllm-limitations https://news.y0.exchange/article/circuit-targeted-fine-tuning-for-low-resource-language-adaptation y0 News en 2026-05-27T04:00:00.000Z Circuit-Targeted Fine-Tuning for Low-Resource Language Adaptation circuit-discovery, fine-tuning, interpretability, low-resource-adaptation, transformers, cross-lingual, catastrophic-forgetting https://news.y0.exchange/article/dsa-tokenizer-semantic-acoustic-speech-separation y0 News en 2026-05-27T04:00:00.000Z DSA-Tokenizer: Semantic-Acoustic Speech Separation speech-tokenization, speech-llms, semantic-acoustic-separation, flow-matching, voice-cloning, discrete-representations, generative-models, ai-infrastructure https://news.y0.exchange/article/how-clip-models-learn-spatial-relations-mechanistic-insights y0 News en 2026-05-27T04:00:00.000Z How CLIP Models Learn Spatial Relations: Mechanistic Insights vision-language-models, clip, spatial-reasoning, mechanistic-interpretability, transformers, contrastive-learning, attention-mechanisms, research https://news.y0.exchange/article/metasicl-meta-learning-for-low-resource-speech-ai y0 News en 2026-05-27T04:00:00.000Z MetaSICL: Meta Learning for Low-Resource Speech AI auditory-llm, in-context-learning, meta-learning, speech-recognition, low-resource-adaptation, model-efficiency, few-shot-learning https://news.y0.exchange/article/orloopbench-llm-solver-iteration-for-operations-research y0 News en 2026-05-27T04:00:00.000Z ORLoopBench: LLM Solver Iteration for Operations Research llm-evaluation, operations-research, mathematical-reasoning, benchmark, solver-verification, rlvr-training, model-reliability https://news.y0.exchange/article/ecsel-explainable-classification-via-signomial-equations y0 News en 2026-05-27T04:00:00.000Z ECSEL: Explainable Classification via Signomial Equations explainable-ai, symbolic-regression, machine-learning, interpretability, classification, signomial-equations https://news.y0.exchange/article/g-substrate-graph-framework-across-data-modalities y0 News en 2026-05-27T04:00:00.000Z G-Substrate: Graph Framework Across Data Modalities graph-neural-networks, representation-learning, multimodal-ai, machine-learning, transfer-learning, research, structural-substrate, arxiv https://news.y0.exchange/article/ruleplanner-ai-framework-automates-ic-design-rule-compliance y0 News en 2026-05-27T04:00:00.000Z RulePlanner: AI Framework Automates IC Design Rule Compliance reinforcement-learning, chip-design, eda-tools, 3d-floorplanning, semiconductor, design-automation, ai-optimization https://news.y0.exchange/article/tabx-gpu-accelerated-multi-agent-rl-simulator y0 News en 2026-05-27T04:00:00.000Z TABX: GPU-Accelerated Multi-Agent RL Simulator multi-agent-learning, reinforcement-learning, simulation, jax, research-tools, marl, open-source https://news.y0.exchange/article/graphdancer-llm-graph-reasoning-via-curriculum-post-training y0 News en 2026-05-27T04:00:00.000Z GraphDancer: LLM Graph Reasoning via Curriculum Post-Training llm-training, graph-reasoning, curriculum-learning, knowledge-graphs, post-training, efficient-models, semantic-search, structured-data https://news.y0.exchange/article/dppo-improving-llm-rl-training-beyond-ppo y0 News en 2026-05-27T04:00:00.000Z DPPO: Improving LLM RL Training Beyond PPO reinforcement-learning, llm-training, ppo-algorithm, policy-optimization, deep-learning, machine-learning https://news.y0.exchange/article/llm-causal-geometric-dynamics-across-depth y0 News en 2026-05-27T04:00:00.000Z LLM Causal-Geometric Dynamics Across Depth llm-interpretability, mechanistic-transparency, representation-geometry, causal-analysis, neural-dynamics, decoder-models, ai-safety https://news.y0.exchange/article/bosq-efficient-llm-querying-for-graph-neural-networks y0 News en 2026-05-27T04:00:00.000Z BOSQ: Efficient LLM Querying for Graph Neural Networks graph-neural-networks, llm-optimization, sparse-computation, efficiency, bilevel-optimization, nlp, machine-learning https://news.y0.exchange/article/olaf-world-latent-action-learning-without-labeled-data y0 News en 2026-05-27T04:00:00.000Z Olaf-World: Latent Action Learning Without Labeled Data video-world-models, latent-actions, self-supervised-learning, zero-shot-transfer, action-controllable-ai, temporal-alignment, unsupervised-representation-learning https://news.y0.exchange/article/miplib-nl-industrial-scale-optimization-benchmark y0 News en 2026-05-27T04:00:00.000Z MIPLIB-NL: Industrial-Scale Optimization Benchmark optimization-modeling, llm-evaluation, benchmarking, miplib-nl, industrial-ai, machine-learning, decision-making-systems https://news.y0.exchange/article/vital-trace-protocol-constrained-clinical-ai-reasoning y0 News en 2026-05-27T04:00:00.000Z Vital Trace: Protocol-Constrained Clinical AI Reasoning clinical-ai, llm-reasoning, healthcare-ml, multi-agent-systems, icu-prediction, interpretability, protocol-constraints, medical-ai https://news.y0.exchange/article/per-sample-privacy-vulnerability-assessment-without-shadow-models y0 News en 2026-05-27T04:00:00.000Z Per-Sample Privacy Vulnerability Assessment Without Shadow Models privacy-attacks, membership-inference, machine-learning-security, model-vulnerability, privacy-assessment, deep-learning https://news.y0.exchange/article/gicdm-fixing-hubness-in-generative-model-evaluation y0 News en 2026-05-27T04:00:00.000Z GICDM: Fixing Hubness in Generative Model Evaluation generative-models, evaluation-metrics, hubness-correction, embedding-spaces, icdm, benchmark-methodology, machine-learning, model-assessment https://news.y0.exchange/article/persona2web-benchmarking-personalized-web-agents y0 News en 2026-05-27T04:00:00.000Z Persona2Web: Benchmarking Personalized Web Agents web-agents, personalization, large-language-models, benchmark, contextual-reasoning, user-history, llm-evaluation, autonomous-systems https://news.y0.exchange/article/geospatial-discovery-framework-for-pfas-contamination-detection y0 News en 2026-05-27T04:00:00.000Z Geospatial Discovery Framework for PFAS Contamination Detection geospatial-discovery, active-learning, meta-learning, environmental-monitoring, pfas-contamination, machine-learning, sparse-labels, public-health https://news.y0.exchange/article/llm-security-advisors-fail-on-tee-guidance-red-team-results y0 News en 2026-05-27T04:00:00.000Z LLM Security Advisors Fail on TEE Guidance: Red-Team Results llm-security, trusted-execution-environments, red-teaming, hallucination-risk, ai-safety, chatgpt, claude, vulnerability-disclosure, infrastructure-security https://news.y0.exchange/article/gui-libra-improved-training-for-native-gui-agents y0 News en 2026-05-27T04:00:00.000Z GUI-Libra: Improved Training for Native GUI Agents gui-agents, reinforcement-learning, agent-training, supervised-finetuning, automation, open-source-ai, data-efficiency https://news.y0.exchange/article/gcos-geometrically-constrained-outlier-synthesis-for-ai y0 News en 2026-05-27T04:00:00.000Z GCOS: Geometrically Constrained Outlier Synthesis for AI out-of-distribution-detection, neural-networks, anomaly-detection, conformal-inference, robust-ai, feature-synthesis, machine-learning https://news.y0.exchange/article/alignment-optimizes-language-models-for-norms-not-behavior y0 News en 2026-05-27T04:00:00.000Z Alignment Optimizes Language Models for Norms, Not Behavior language-models, alignment-training, human-behavior, game-theory, ai-research, model-bias, behavioral-economics https://news.y0.exchange/article/salo-detecting-jailbreaks-via-refusal-trajectories y0 News en 2026-05-27T04:00:00.000Z SALO: Detecting Jailbreaks via Refusal Trajectories jailbreak-detection, llm-safety, refusal-mechanisms, adversarial-attacks, representation-engineering, model-security, gcg-attack, ai-robustness https://news.y0.exchange/article/cryptographic-registry-provenance-against-dependency-attacks y0 News en 2026-05-27T04:00:00.000Z Cryptographic Registry Provenance Against Dependency Attacks supply-chain-security, dependency-confusion, cryptographic-provenance, package-managers, software-security, ai-governance, registry-identity, artifact-signing https://news.y0.exchange/article/rag-systems-struggle-with-false-context-new-diagnostic-tool-revealed y0 News en 2026-05-27T04:00:00.000Z RAG Systems Struggle with False Context: New Diagnostic Tool Revealed rag-systems, retrieval-augmented-generation, adversarial-testing, llm-robustness, context-compliance, ai-reliability, benchmark-release, information-conflict, model-evaluation https://news.y0.exchange/article/timed-genai-access-improves-student-learning-outcomes y0 News en 2026-05-27T04:00:00.000Z Timed GenAI Access Improves Student Learning Outcomes generative-ai, education, reinforcement-learning, pedagogical-strategy, metacognition, ai-scaffolding, learning-outcomes https://news.y0.exchange/article/citeprism-ai-framework-for-academic-citation-auditing y0 News en 2026-05-27T04:00:00.000Z CitePrism: AI Framework for Academic Citation Auditing citation-auditing, editorial-integrity, human-in-the-loop-ai, academic-publishing, llm-applications, research-quality, decision-support, bibliographic-verification https://news.y0.exchange/article/itc-improves-transformer-world-models-for-rl y0 News en 2026-05-27T04:00:00.000Z ITC Improves Transformer World Models for RL world-models, reinforcement-learning, transformers, token-correspondence, visual-learning, embodied-ai, structured-prediction, benchmark-improvement https://news.y0.exchange/article/ghost-framework-fixes-popularity-bias-in-ai-recommenders y0 News en 2026-05-27T04:00:00.000Z Ghost Framework Fixes Popularity Bias in AI Recommenders generative-ai, recommendation-systems, algorithmic-bias, fairness-in-ai, machine-learning, debiasing, neural-networks, filter-bubbles https://news.y0.exchange/article/symmetry-compatible-optimizers-improve-llm-training y0 News en 2026-05-27T04:00:00.000Z Symmetry-Compatible Optimizers Improve LLM Training neural-network-optimization, equivariant-learning, language-models, mixture-of-experts, gradient-descent, deep-learning, adam-optimizer, training-efficiency https://news.y0.exchange/article/amaris-memory-augmented-rubric-system-for-llm-rl-training y0 News en 2026-05-27T04:00:00.000Z AMARIS: Memory-Augmented Rubric System for LLM RL Training reinforcement-learning, llm-training, rubric-based-learning, memory-augmented-systems, model-fine-tuning, ai-research, interpretability https://news.y0.exchange/article/fluidsplat-flow-field-reconstruction-from-sparse-sensors y0 News en 2026-05-27T04:00:00.000Z FLUIDSPLAT: Flow Field Reconstruction from Sparse Sensors neural-networks, fluid-dynamics, gaussian-splatting, flow-reconstruction, aerodynamics, computational-science, sensor-based-inference https://news.y0.exchange/article/procctrlbench-evaluating-llm-coding-agent-execution y0 News en 2026-05-27T04:00:00.000Z ProcCtrlBench: Evaluating LLM Coding Agent Execution llm-agents, ai-evaluation, coding-agents, benchmarking, execution-monitoring, ai-safety, developer-tools https://news.y0.exchange/article/marl-improves-autonomous-vehicle-safety-testing-via-realistic-pedestri y0 News en 2026-05-27T04:00:00.000Z MARL Improves Autonomous Vehicle Safety Testing via Realistic Pedestri autonomous-vehicles, reinforcement-learning, multi-agent-systems, safety-testing, simulation, pedestrian-behavior, mappo, vehicle-validation https://news.y0.exchange/article/transformer-generalization-via-pac-bayes-theory-and-fourier y0 News en 2026-05-27T04:00:00.000Z Transformer Generalization via PAC-Bayes Theory and Fourier transformer-theory, generalization-bounds, pac-bayes, chain-of-thought, fourier-analysis, learning-theory, mechanistic-interpretability, neural-networks https://news.y0.exchange/article/triprorep-improves-protein-structure-prediction-via-multi-view-learnin y0 News en 2026-05-27T04:00:00.000Z TriProRep Improves Protein Structure Prediction via Multi-View Learnin protein-structure, machine-learning, generative-models, computational-biology, representation-learning, benchmark, drug-discovery https://news.y0.exchange/article/layerwise-learning-rates-boost-llm-training-speed-15x y0 News en 2026-05-27T04:00:00.000Z Layerwise Learning Rates Boost LLM Training Speed 1.5x llm-training, optimization, transformer-efficiency, learning-rates, neural-network-scaling, deep-learning https://news.y0.exchange/article/bioformer-spectral-alignment-for-biomedical-generalization y0 News en 2026-05-27T04:00:00.000Z BioFormer: Spectral Alignment for Biomedical Generalization biomedical-ai, machine-learning, signal-processing, cross-subject-generalization, time-series, healthcare-ai, deep-learning https://news.y0.exchange/article/cogadapt-ecg-foundation-models-for-wearable-cognitive-load y0 News en 2026-05-27T04:00:00.000Z CogAdapt: ECG Foundation Models for Wearable Cognitive Load foundation-models, transfer-learning, ecg-analysis, wearable-health, cognitive-load, ai-healthcare, sensor-adaptation, deep-learning https://news.y0.exchange/article/ai-suicide-risk-assessment-framework-for-metro-stations y0 News en 2026-05-27T04:00:00.000Z AI Suicide Risk Assessment Framework for Metro Stations suicide-prevention, computer-vision, ai-ethics, surveillance, public-health, interpretable-ai, mental-health, video-analysis https://news.y0.exchange/article/multimodal-information-fusion-in-document-classification y0 News en 2026-05-27T04:00:00.000Z Multimodal Information Fusion in Document Classification machine-learning, information-fusion, document-classification, multimodal, systematic-review, meta-analysis, research-methodology, reproducibility https://news.y0.exchange/article/didr-one-step-image-generation-via-aligned-reward y0 News en 2026-05-27T04:00:00.000Z DIDR: One-Step Image Generation via Aligned Reward generative-ai, reinforcement-learning, image-generation, diffusion-models, text-to-image, sdxl, optimization-alignment https://news.y0.exchange/article/irno-iterative-neural-operators-for-high-frequency-error y0 News en 2026-05-27T04:00:00.000Z IRNO: Iterative Neural Operators for High-Frequency Error neural-operators, spectral-bias, scientific-computing, machine-learning, iterative-refinement, surrogate-models, fixed-point-iteration https://news.y0.exchange/article/hidden-state-privacy-faces-fundamental-trade-off-limits y0 News en 2026-05-27T04:00:00.000Z Hidden-State Privacy Faces Fundamental Trade-Off Limits privacy, machine-learning, hidden-states, adversarial-attacks, gaussian-mechanisms, transformer-security, model-inversion, neural-networks https://news.y0.exchange/article/ppo-training-stability-via-transition-dropout y0 News en 2026-05-27T04:00:00.000Z PPO Training Stability via Transition Dropout reinforcement-learning, ppo-algorithm, training-stability, gradient-optimization, on-policy-learning, transition-dropout, deep-rl https://news.y0.exchange/article/patent-embedding-benchmarks-task-specific-fine-tuning y0 News en 2026-05-27T04:00:00.000Z Patent Embedding Benchmarks: Task-Specific Fine-Tuning embeddings, patent-analysis, machine-learning, fine-tuning, retrieval, information-retrieval, model-evaluation, cross-domain, text-embeddings https://news.y0.exchange/article/reader-efficient-ai-text-detection-with-reasoning y0 News en 2026-05-27T04:00:00.000Z READER: Efficient AI Text Detection with Reasoning ai-detection, llm-safety, text-classification, explainability, content-moderation, model-efficiency, reasoning-systems https://news.y0.exchange/article/munet-joint-3d-human-mesh-recovery-and-reconstruction y0 News en 2026-05-27T04:00:00.000Z MuNet: Joint 3D Human Mesh Recovery and Reconstruction 3d-reconstruction, computer-vision, graph-neural-networks, human-mesh-recovery, deep-learning, multi-task-learning, research https://news.y0.exchange/article/wsadbench-unified-anomaly-detection-benchmark-study y0 News en 2026-05-27T04:00:00.000Z WSADBench: Unified Anomaly Detection Benchmark Study anomaly-detection, weak-supervision, benchmark, machine-learning, foundation-models, wsad, research, evaluation-framework https://news.y0.exchange/article/why-eths-design-limits-its-potential-as-money y0 News en 2026-05-26T19:01:43.000Z Why ETH's Design Limits Its Potential as Money ethereum, eth, monetary-policy, network-design, cryptocurrency, store-of-value https://news.y0.exchange/article/enterprise-ai-gap-ambition-vs-readiness-in-2024 y0 News en 2026-05-26T14:54:10.000Z Enterprise AI Gap: Ambition vs. Readiness in 2024 enterprise-ai, organizational-change, ai-adoption, infrastructure-readiness, agentic-ai, digital-transformation https://news.y0.exchange/article/import-ai-458-ai-futures-and-singularity-scenarios y0 News en 2026-05-26T12:32:03.000Z Import AI 458: AI Futures and Singularity Scenarios ai-futures, singularity, scenario-planning, ai-research, speculative-analysis, technological-forecasting https://news.y0.exchange/article/ai-jobs-panic-lacks-empirical-evidence-data-shows y0 News en 2026-05-26T12:10:00.000Z AI Jobs Panic Lacks Empirical Evidence, Data Shows ai-jobs, employment, labor-market, technology-adoption, workforce-disruption, ai-impact https://news.y0.exchange/article/nvidia-restructures-reporting-hyperscaler-vs-stack-control y0 News en 2026-05-26T10:00:00.000Z Nvidia Restructures Reporting: Hyperscaler vs. Stack Control nvidia, earnings, ai-infrastructure, hyperscaler-competition, financial-reporting, custom-silicon, market-segmentation https://news.y0.exchange/article/ai-jobs-hysteria-separating-reality-from-hype y0 News en 2026-05-26T09:00:00.000Z AI Jobs Hysteria: Separating Reality From Hype ai-jobs, layoffs, tech-sector, employment, white-collar-jobs, ai-disruption, labor-market https://news.y0.exchange/article/ai-erodes-entry-level-jobs-hidden-labor-market-crisis y0 News en 2026-05-26T09:00:00.000Z AI Erodes Entry-Level Jobs: Hidden Labor Market Crisis artificial-intelligence, employment, entry-level-jobs, labor-market, workforce-development, economic-impact, ai-disruption, career-pathways