y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto
🤖All137,537🧠AI22,940⛓️Crypto17,363💎DeFi1,799🤖AI × Crypto1,480📰General93,955

AI × Crypto News Feed

Real-time AI-curated news from 137,537+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.

137537 articles
AIBullisharXiv – CS AI · Apr 157/10
🧠

How Transformers Learn to Plan via Multi-Token Prediction

Researchers demonstrate that multi-token prediction (MTP) outperforms standard next-token prediction (NTP) for training language models on reasoning tasks like planning and pathfinding. Through theoretical analysis of simplified Transformers, they reveal that MTP enables a reverse reasoning process where models first identify end states then reconstruct paths backward, suggesting MTP induces more interpretable and robust reasoning circuits.

AIBullisharXiv – CS AI · Apr 157/10
🧠

AutoSurrogate: An LLM-Driven Multi-Agent Framework for Autonomous Construction of Deep Learning Surrogate Models in Subsurface Flow

AutoSurrogate is an LLM-driven framework that automates the construction of deep learning surrogate models for subsurface flow simulation, enabling domain scientists without machine learning expertise to build high-quality models through natural language instructions. The system autonomously handles data profiling, architecture selection, hyperparameter optimization, and quality assessment while managing failure modes, demonstrating superior performance to expert-designed baselines on geological carbon storage tasks.

AIBullisharXiv – CS AI · Apr 157/10
🧠

Drawing on Memory: Dual-Trace Encoding Improves Cross-Session Recall in LLM Agents

Researchers introduce dual-trace memory encoding for LLM agents, pairing factual records with narrative scene reconstructions to improve cross-session recall by 20+ percentage points. The method significantly enhances temporal reasoning and multi-session knowledge aggregation without increasing computational costs, advancing the capability of persistent AI agent systems.

AINeutralarXiv – CS AI · Apr 157/10
🧠

Benchmarking Deflection and Hallucination in Large Vision-Language Models

Researchers introduce VLM-DeflectionBench, a new benchmark with 2,775 samples designed to evaluate how large vision-language models handle conflicting or insufficient evidence. The study reveals that most state-of-the-art LVLMs fail to appropriately deflect when faced with noisy or misleading information, highlighting critical gaps in model reliability for knowledge-intensive tasks.

AIBullisharXiv – CS AI · Apr 157/10
🧠

Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical Reasoning

Researchers propose Schema-Adaptive Tabular Representation Learning, which uses LLMs to convert structured clinical data into semantic embeddings that transfer across different electronic health record schemas without retraining. When combined with imaging data for dementia diagnosis, the method achieves state-of-the-art results and outperforms board-certified neurologists on retrospective diagnostic tasks.

AIBullisharXiv – CS AI · Apr 157/10
🧠

Transferable Expertise for Autonomous Agents via Real-World Case-Based Learning

Researchers propose a case-based learning framework enabling LLM-based autonomous agents to extract and reuse knowledge from past tasks, improving performance on complex real-world problems. The method outperforms traditional zero-shot, few-shot, and prompt-based baselines across six task categories, with gains increasing as task complexity rises.

AIBullisharXiv – CS AI · Apr 157/10
🧠

DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding

Researchers introduce DocSeeker, a multimodal AI system designed to improve long document understanding by implementing structured analysis, localization, and reasoning workflows. The breakthrough addresses critical limitations in existing large language models that struggle with lengthy documents due to high noise levels and weak training signals, achieving superior performance on both short and ultra-long documents.

AIBearisharXiv – CS AI · Apr 157/10
🧠

AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance

Researchers have catalogued 195 AI safety benchmarks released since 2018, revealing that rapid proliferation of evaluation tools has outpaced standardization efforts. The study identifies critical fragmentation: inconsistent metric definitions, limited language coverage, poor repository maintenance, and lack of shared measurement standards across the field.

🏢 Hugging Face
AIBullisharXiv – CS AI · Apr 157/10
🧠

Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models

Researchers introduce Ariadne, a framework demonstrating that Reinforcement Learning with Verifiable Rewards (RLVR) expands spatial reasoning capabilities in Vision-Language Models beyond their base distribution. Testing on synthetic mazes and real-world navigation benchmarks shows the technique enables models to solve previously unsolvable problems, suggesting genuine capability expansion rather than sampling efficiency.

AINeutralarXiv – CS AI · Apr 157/10
🧠

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Researchers have identified a critical vulnerability in large language models where safety guardrails fail across low-resource languages despite strong performance in high-resource ones. The team proposes LASA (Language-Agnostic Semantic Alignment), a new method that anchors safety protocols at the semantic bottleneck layer, dramatically reducing attack success rates from 24.7% to 2.8% on tested models.

AIBullisharXiv – CS AI · Apr 157/10
🧠

Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models

Researchers present Chain-of-Models Pre-Training (CoM-PT), a novel method that accelerates vision foundation model training by up to 7.09X through sequential knowledge transfer from smaller to larger models in a unified pipeline, rather than training each model independently. The approach maintains or improves performance while significantly reducing computational costs, with efficiency gains increasing as more models are added to the training sequence.

AIBullisharXiv – CS AI · Apr 157/10
🧠

RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair

Researchers introduce RePAIR, a framework enabling users to instruct large language models to forget harmful knowledge, misinformation, and personal data through natural language prompts at inference time. The system uses a training-free method called STAMP that manipulates model activations to achieve selective unlearning with minimal computational overhead, outperforming existing approaches while preserving model utility.

AIBearisharXiv – CS AI · Apr 157/10
🧠

Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

Researchers introduce MemJack, a multi-agent framework that exploits semantic vulnerabilities in Vision-Language Models through coordinated jailbreak attacks, achieving 71.48% attack success rates against Qwen3-VL-Plus. The study reveals that current VLM safety measures fail against sophisticated visual-semantic attacks and introduces MemJack-Bench, a dataset of 113,000+ attack trajectories to advance defensive research.

AIBullisharXiv – CS AI · Apr 157/10
🧠

OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension

Researchers present OSC, a hardware-efficient framework that addresses the challenge of deploying Large Language Models with 4-bit quantization by intelligently separating activation outliers into a high-precision processing path while maintaining low-precision computation for standard values. The technique achieves 1.78x speedup over standard 8-bit approaches while limiting accuracy degradation to under 2.2% on state-of-the-art models.

AIBearisharXiv – CS AI · Apr 157/10
🧠

Red Teaming Large Reasoning Models

Researchers introduce RT-LRM, a comprehensive benchmark for evaluating the trustworthiness of Large Reasoning Models across truthfulness, safety, and efficiency dimensions. The study reveals that LRMs face significant vulnerabilities including CoT-hijacking and prompt-induced inefficiencies, demonstrating they are more fragile than traditional LLMs when exposed to reasoning-induced risks.

AIBearisharXiv – CS AI · Apr 157/10
🧠

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems

Researchers have identified a critical privacy vulnerability in LLM-based multi-agent systems, demonstrating that communication topologies can be reverse-engineered through black-box attacks. The Communication Inference Attack (CIA) achieves up to 99% accuracy in inferring how agents communicate, exposing significant intellectual property and security risks in AI systems.

AIBullisharXiv – CS AI · Apr 157/10
🧠

Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices

Researchers introduce Vec-LUT, a novel vector-based lookup table technique that dramatically improves ultra-low-bit LLM inference on edge devices by addressing memory bandwidth underutilization. The method achieves up to 4.2x performance improvements over existing approaches, enabling faster LLM execution on CPUs than specialized NPUs.

AIBullisharXiv – CS AI · Apr 157/10
🧠

Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints

Researchers propose Coupled Weight and Activation Constraints (CWAC), a novel safety alignment technique for large language models that simultaneously constrains weight updates and regularizes activation patterns to prevent harmful outputs during fine-tuning. The method demonstrates that existing single-constraint approaches are insufficient and outperforms baselines across multiple LLMs while maintaining task performance.

AINeutralarXiv – CS AI · Apr 157/10
🧠

Policy-Invisible Violations in LLM-Based Agents

Researchers identified a critical failure mode in LLM-based agents called policy-invisible violations, where agents execute actions that appear compliant but breach organizational policies due to missing contextual information. They introduced PhantomPolicy, a benchmark with 600 test cases, and Sentinel, an enforcement framework using counterfactual graph simulation that achieved 93% accuracy in detecting violations compared to 68.8% for baseline approaches.

AINeutralarXiv – CS AI · Apr 157/10
🧠

Beyond Scores: Diagnostic LLM Evaluation via Fine-Grained Abilities

Researchers propose a cognitive diagnostic framework that evaluates large language models across fine-grained ability dimensions rather than aggregate scores, enabling targeted model improvement and task-specific selection. The approach uses multidimensional Item Response Theory to estimate abilities across 35 dimensions for mathematics and generalizes to physics, chemistry, and computer science with strong predictive accuracy.

AIBullisharXiv – CS AI · Apr 157/10
🧠

JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

Researchers introduce JanusCoder, a foundational multimodal AI model that bridges visual and programmatic intelligence by processing both code and visual outputs. The team created JanusCode-800K, the largest multimodal code corpus, enabling their 7B-14B parameter models to match or exceed commercial AI performance on code generation tasks combining textual instructions and visual inputs.

AINeutralarXiv – CS AI · Apr 157/10
🧠

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training

Researchers demonstrate that post-training in reasoning models creates specialized attention heads that enable complex problem-solving, but this capability introduces trade-offs where sophisticated reasoning can degrade performance on simpler tasks. Different training methods—SFT, distillation, and GRPO—produce fundamentally different architectural mechanisms, revealing tensions between reasoning capability and computational reliability.

AIBullisharXiv – CS AI · Apr 157/10
🧠

Safe-FedLLM: Delving into the Safety of Federated Large Language Models

Researchers propose Safe-FedLLM, a defense framework addressing security vulnerabilities in federated large language model training by detecting malicious clients through analysis of LoRA update patterns. The lightweight classifier-based approach effectively mitigates attacks while maintaining model performance and training efficiency, representing a significant advancement in securing distributed LLM development.

AINeutralarXiv – CS AI · Apr 157/10
🧠

Evaluating Relational Reasoning in LLMs with REL

Researchers introduce REL, a benchmark framework that evaluates relational reasoning in large language models by measuring Relational Complexity (RC)—the number of entities that must be simultaneously bound to apply a relation. The study reveals that frontier LLMs consistently degrade in performance as RC increases, exposing a fundamental limitation in higher-arity reasoning that persists even with increased compute and in-context learning.

← PrevPage 524 of 5502Next →
Filters
Sentiment
Importance
Sort
Stay Updated
Everything combined