Models, papers, tools. 109,925 articles with AI-powered sentiment analysis and key takeaways.
AIBearisharXiv – CS AI · May 77/10
🧠Researchers demonstrate that the shuffling defense mechanism used to protect Transformer model weights during secure inference can be broken through an alignment attack, allowing adversaries to recover weights with minimal cost. The attack exploits multiple shuffled activations by finding a common permutation, undermining a key security assumption in privacy-preserving machine learning.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers propose Anchored Learning, a new fine-tuning method that prevents catastrophic forgetting in large language models by controlling distributional drift through a dynamically evolving reference anchor. The technique achieves near-optimal performance gains while reducing degradation from over 53% to under 5% on benchmark tasks.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers introduce RFT-FaultBench, the first comprehensive benchmark for diagnosing failures in reinforcement fine-tuning of large language models, and propose RFT-FM, an automated framework for detecting, diagnosing, and remediating training failures. This addresses a critical gap in LLM post-training reliability where practitioners currently rely on manual inspection.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers propose skill neologisms—soft tokens added to LLM vocabularies—as a scalable approach to continual learning that enables models to acquire new capabilities without catastrophic forgetting or weight updates. The method demonstrates that independently trained skill tokens can compose zero-shot and work with out-of-distribution tasks, offering a practical alternative to fine-tuning.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers introduce CCL-D, a diagnostic system for detecting anomalies in large-scale AI model training that identifies GPU communication failures in under 6 minutes. Deployed across 4,000 GPUs over one year, the system addresses a critical bottleneck in distributed training where slow/hang anomalies typically require days to diagnose.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers propose Experiment-as-Code (EaC) Labs, a new paradigm that bridges AI agents with physical laboratory equipment by encoding experiments as declarative configurations compiled to device-level APIs. This framework combines artificial intelligence with automated lab instrumentation through a systems layer that performs safety checks, resource allocation, and job orchestration, enabling AI-driven scientific discovery beyond purely digital environments.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers have developed MAILA, a machine learning framework that predicts mental health conditions from cursor and touchscreen interactions with biomarker-level accuracy. Trained on 1.3 million self-reports from 9,500 participants, the system tracks 13 psychological dimensions and outperforms traditional self-reporting methods, potentially enabling scalable digital mental health assessment.
AIBearisharXiv – CS AI · May 77/10
🧠Researchers analyzed Terms of Service agreements for AI coding assistants and autonomous agents, finding that providers consistently shift responsibility for code correctness, safety, and legal compliance to users. The study identifies misalignment between current policy frameworks and increasingly agent-mediated software development, proposing a research roadmap to establish clearer accountability structures.
AIBearisharXiv – CS AI · May 77/10
🧠A comprehensive study evaluating five multimodal large language models (MLLMs) on real-world dermatology tasks reveals a significant gap between benchmark performance and clinical applicability. While models achieved up to 42% accuracy on public datasets, performance dropped dramatically to 1.5-24.65% on actual hospital cases, highlighting critical limitations in deploying these systems for clinical decision-making.
🧠 GPT-4
AIBullisharXiv – CS AI · May 77/10
🧠Researchers present JoyAI-Image, a unified multimodal foundation model that combines visual understanding, text-to-image generation, and image editing through a spatially enhanced architecture. The model achieves state-of-the-art performance across multiple benchmarks while advancing spatial reasoning capabilities, positioning unified visual models as promising infrastructure for future applications like vision-language-action systems.
AIBullisharXiv – CS AI · May 77/10
🧠TSCG is a deterministic compiler that converts JSON tool schemas into structured text optimized for language model interpretation, solving a critical failure point in agentic AI systems. The technology restores accuracy in smaller models (4B-14B) from near-zero to 84%+ on production-scale tool catalogs while reducing token consumption by 52-57%, shipping as a lightweight TypeScript package.
🏢 OpenAI🏢 Anthropic🧠 GPT-5
AIBullisharXiv – CS AI · May 77/10
🧠Researchers present CTM-AI, a general-purpose AI architecture combining the Conscious Turing Machine model with modern foundation models to achieve human-like flexibility across tasks. The system demonstrates state-of-the-art performance on multimodal benchmarks and tool-using tasks, suggesting that consciousness-inspired architectures may offer a path toward more capable and adaptable AI systems.
AIBearisharXiv – CS AI · May 77/10
🧠A comprehensive bibliometric audit reveals that academic papers evaluating large language models systematically lag behind frontier AI capabilities by a median of 10.85 points on the Epoch AI Capabilities Index, with this gap widening at 5.53 points annually. The study finds that most papers fail to disclose critical configuration details and make broad claims about "AI" capabilities rather than specific tested models, distorting how AI progress is understood in policy and media.
🧠 GPT-4🧠 GPT-5🧠 Claude
AIBullisharXiv – CS AI · May 77/10
🧠Researchers introduce FASQ, a calibration-free compression framework for large language models that uses product quantization to achieve flexible compression ratios between 27-49% of original model size. The method outperforms existing quantization approaches like GPTQ and AWQ while enabling faster inference than FP16 on consumer GPUs through custom CUDA kernels.
🧠 Llama
AINeutralarXiv – CS AI · May 77/10
🧠Researchers developed and validated the first FMECA (Failure Mode, Effects, and Criticality Analysis) framework to systematically assess patient safety risks in clinical summaries generated by large language models. Testing with GPT-OSS 120B on real hospital discharge summaries demonstrated moderate-to-substantial inter-rater agreement and identified 14 distinct failure modes, establishing a reproducible methodology for evaluating AI-generated clinical content safety.
AIBearisharXiv – CS AI · May 77/10
🧠Researchers present Sparse Backdoor, a supply-chain attack that embeds undetectable backdoors into pre-trained image classifiers by injecting sparse perturbations masked with Gaussian noise. The attack is proven computationally infeasible to distinguish from original models under standard hardness assumptions, raising critical security concerns for AI model deployment and verification.
AINeutralarXiv – CS AI · May 77/10
🧠A research study evaluates whether combining human and AI judgments can improve decision-making across diverse tasks, finding only modest complementarity gains of 0.4 percentage points. The primary bottleneck identified is not human accuracy but rather the inability to effectively route decisions to humans when needed and design assistance methods that help humans catch AI mistakes.
AIBullisharXiv – CS AI · May 77/10
🧠RetentiveKV introduces an entropy-driven optimization method for multimodal large language models that achieves 5x KV cache compression and 1.5x decoding acceleration by reformulating token eviction as continuous memory evolution rather than discrete pruning. The approach addresses limitations of existing compression methods by accounting for visual tokens that gain importance later in decoding and preserving spatial continuity of visual information.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers present the RGF-AFFD, an integrated governance framework for AI-driven fraud detection in U.S. banking that unifies compliance requirements from four regulatory bodies (OCC, SR 11-7, CFPB, FinCEN). The framework includes a Regulatory Digital Twin meta-model that benchmarks six AI architectures, with an LSTM+XGBoost ensemble achieving 0.9289 ROC-AUC, and establishes continuous monitoring protocols to satisfy fragmented regulatory requirements simultaneously.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers introduce LAWS, a self-certifying caching architecture for neural inference that builds a library of expert functions with formal error bounds, enabling efficient deployment across LLMs, robotics, and edge devices. The system generalizes both Mixture-of-Experts and KV prefix caching while providing mathematically verifiable performance guarantees without requiring ground truth validation.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers introduce Neural Rule Inducer (NRI), a pretrained foundation model enabling zero-shot logical rule induction without task-specific retraining. By encoding domain-agnostic statistical properties instead of literal identities, NRI generalizes across different predicates and demonstrates robustness to label noise and spurious correlations, advancing toward foundation models for symbolic reasoning.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers introduced Uno-Orchestra, a new orchestration framework for multi-agent LLM systems that dynamically decides when to decompose tasks and which model-primitive pairs to use, achieving 77% accuracy across 13 benchmarks while reducing computational costs by an order of magnitude compared to existing approaches.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers have developed a neural network architecture inspired by large language models to predict high-dimensional molecular potential energy surfaces, successfully computing accurate predictions for a 186-dimensional system representing a protonated 21-water cluster—a significant advance in computational chemistry that could accelerate reaction rate predictions.
AIBearisharXiv – CS AI · May 77/10
🧠Researchers introduce DecodingTrust-Agent Platform (DTap), a red-teaming framework designed to systematically test AI agent vulnerabilities across 14 real-world domains. The platform includes an autonomous red-teaming agent (DTap-Red) that discovers attack strategies and a benchmarking dataset, revealing critical security gaps in popular AI agents that could enable API key theft, unauthorized transactions, and data deletion.
AIBullisharXiv – CS AI · May 77/10
🧠AgentTrust is a runtime safety layer that intercepts AI agent tool calls before execution to prevent unsafe actions like accidental deletion, credential exposure, or data exfiltration. The system achieves 95-96.7% verdict accuracy across benchmarks using deobfuscation, risk chain detection, and LLM-based judgment, addressing a critical gap in AI agent safety infrastructure.
