Español

Explorar

Noticias de IA

37834 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
Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive …
arXiv cs.AI Research & Papers
Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Servi…
arXiv cs.AI Research & Papers
Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Ou…
arXiv cs.AI Research & Papers
When Can One Obtain Certificates of Optimality Using Positivstellensaetze?
arXiv cs.AI Research & Papers
Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction
arXiv cs.AI Research & Papers
What Does an LLM-Agent Leaderboard Rank Actually Compare?
arXiv cs.AI Research & Papers
Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliabi…
arXiv cs.AI Research & Papers
APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents
arXiv cs.AI Research & Papers
A radiographic world model for clinical reasoning and evidence generation
arXiv cs.AI Research & Papers
Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems
arXiv cs.AI Research & Papers
Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors
arXiv cs.AI Research & Papers
SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis …
arXiv cs.AI Research & Papers
Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
arXiv cs.AI Research & Papers
One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware …
arXiv cs.AI Research & Papers
Layer-Wise Gate-Controlled Prompt Truncation in a Multimodal Chest X-Ray Classifier
arXiv cs.AI Research & Papers
Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Froze…
arXiv cs.AI Research & Papers
The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persi…
arXiv cs.AI Research & Papers
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supe…
arXiv cs.AI Research & Papers
Temporal Heterogeneous Graph Transformer for Credit Card Fraud Detection
arXiv cs.AI Research & Papers
Discovering Natural Transformation Vulnerabilities in Black-Box Vision Models
arXiv cs.AI Research & Papers
PAGR: Proof-Carrying Algebraic-Geometric Retrieval: A Quiver-, Provenance-, and Sheaf-The…
arXiv cs.AI Research & Papers
RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavior…
arXiv cs.AI Research & Papers
CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification
arXiv cs.AI Research & Papers
The Internal Anatomy of Strategic Choice in Large Language Models
arXiv cs.AI Research & Papers
Human-like moral judgments conceal divergent motive attributions in large language models
arXiv cs.AI Research & Papers
ViT3Flow: A Test-Time Training Transformer MeanFlow for Postoperative Radiograph Synthesi…
arXiv cs.AI Research & Papers
Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement …
arXiv cs.AI Research & Papers
Qiushi Engine on AstaBench E2E-Bench-Hard
arXiv cs.AI Research & Papers
SkillAlign: Aligning Skill Interfaces for LLM-based Agents
arXiv cs.AI Research & Papers
Weakly supervised neural network: segmentation of complex structures in X-ray microCT