Español

Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in…
arXiv cs.AI Research & Papers
SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted…
arXiv cs.AI Research & Papers
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
arXiv cs.AI Research & Papers
Reading Order Inference for Complex Document Layouts
arXiv cs.AI Research & Papers
EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology
arXiv cs.AI Research & Papers
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
arXiv cs.AI Research & Papers
LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models
arXiv cs.AI Research & Papers
Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering
arXiv cs.AI Research & Papers
CausalMix: Data Mixture as Causal Inference for Language Model Training
arXiv cs.AI Research & Papers
Muon as a Residual Connection
arXiv cs.AI Research & Papers
Autonomous Scientific Discovery via Iterative Meta-Reflection
arXiv cs.AI Research & Papers
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
arXiv cs.AI Research & Papers
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Em…
arXiv cs.AI Research & Papers
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
arXiv cs.AI Research & Papers
GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear…
arXiv cs.AI Research & Papers
Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
arXiv cs.AI Research & Papers
FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Acti…
arXiv cs.AI Research & Papers
Measuring the Gap Between Human and LLM Research Ideas
arXiv cs.AI Research & Papers
From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems
arXiv cs.AI Research & Papers
Large language models replicate and predict human cooperation across experiments in game …
arXiv cs.AI Research & Papers
CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
arXiv cs.AI Research & Papers
Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles
arXiv cs.AI Research & Papers
SleepLM: Natural-Language Intelligence for Human Sleep
arXiv cs.AI Research & Papers
Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks
arXiv cs.AI Research & Papers
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
arXiv cs.AI Research & Papers
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models
arXiv cs.AI Research & Papers
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Lang…
arXiv cs.AI Research & Papers
Relevance Is Not Permission: Warranted Attention for Value Contributions
arXiv cs.AI Research & Papers
Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradien…
arXiv cs.AI Research & Papers
ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions