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
Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved Utility
arXiv cs.AI Research & Papers
Preference Tuning as Spectral Update Reorganization
arXiv cs.AI Research & Papers
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
arXiv cs.AI Research & Papers
GuardianAgentBench: Where Agents Fail and How to Guard Them
arXiv cs.AI Research & Papers
Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions …
arXiv cs.AI Research & Papers
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents
arXiv cs.AI Research & Papers
From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying …
arXiv cs.AI Research & Papers
SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integr…
arXiv cs.AI Research & Papers
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
arXiv cs.AI Research & Papers
Logical Regression for Planning with Axioms
arXiv cs.AI Research & Papers
Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls
arXiv cs.AI Research & Papers
DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making
arXiv cs.AI Research & Papers
SafeStep: AI-powered Travel Assistance for Elderly People with Frailty or Dementia
arXiv cs.AI Research & Papers
Reliability-Aware LLM Alignment from Inconsistent Human Feedback
arXiv cs.AI Research & Papers
Constrained latent state modeling: A unifying perspective on representation learning unde…
arXiv cs.AI Research & Papers
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
arXiv cs.AI Research & Papers
Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis
arXiv cs.AI Research & Papers
From Agent Failures to Text Policies: What Works and What Breaks
arXiv cs.AI Research & Papers
Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Lear…
arXiv cs.AI Research & Papers
LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
arXiv cs.AI Research & Papers
slang.gr as a Large-Scale Crowdsourced Resource for Non-Standard Greek
arXiv cs.AI Research & Papers
Probabilistic Residual Learning for Online Recommendations
arXiv cs.AI Research & Papers
Benchmarking Unlearning for Vision Transformers
arXiv cs.AI Research & Papers
Multimodal Learning for Arcing Detection in Pantograph-Catenary Systems
arXiv cs.AI Research & Papers
NeuraLSP: A Neural Spectral Preconditioner for Accelerating PDE Solvers
arXiv cs.AI Research & Papers
Knowledge-Guided Time-Varying Causal Inference for Arctic Sea Ice Dynamics
arXiv cs.AI Research & Papers
StabilityBench: Benchmarking Instability in LLMs
arXiv cs.AI Research & Papers
Vision-Language-Policy Model for Dynamic Robot Task Planning
arXiv cs.AI Research & Papers
Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine …
arXiv cs.AI Research & Papers
TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework