Español

Explorar

Noticias de IA

29341 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
Local verification cannot detect non-transportability: a cohomological theory of context …
arXiv cs.AI Research & Papers
Every pooling rule has its world: matching probability combination rules to situations an…
arXiv cs.AI Research & Papers
Symbolic Machine Learning for Vapor-Liquid Equilibrium Prediction in Cx-N2 Binary Mixtures
arXiv cs.AI Research & Papers
When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
arXiv cs.AI Research & Papers
Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation
arXiv cs.AI Research & Papers
Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Tex…
arXiv cs.AI Research & Papers
Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World …
arXiv cs.AI Research & Papers
High-dimensional Multi-objective Bayesian Optimization with Learned Variable Interactions
arXiv cs.AI Research & Papers
From Numbers to Judgment: Specialist LLM Agents and Reinforcement Learning for European L…
arXiv cs.AI Research & Papers
CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Networ…
arXiv cs.AI Research & Papers
REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
arXiv cs.AI Research & Papers
The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance
arXiv cs.AI Research & Papers
Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads
arXiv cs.AI Research & Papers
Consolidator: Learning Persistent Routed Memory Across Context Boundaries
arXiv cs.AI Research & Papers
Robust and Efficient Noisy-Label Time-Series Classification via Dynamic Time Warping Base…
arXiv cs.AI Research & Papers
When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problem…
arXiv cs.AI Research & Papers
BEST-KAG: Enhancing Question Answering of Building Engineering Standards with Multimodal …
arXiv cs.AI Research & Papers
Confidence Calibration of Deep Learning Systems
arXiv cs.AI Research & Papers
From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evalua…
arXiv cs.AI Research & Papers
Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing
arXiv cs.AI Research & Papers
Claim-Level Reliability Assessment for Efficient Test-Time Reasoning
arXiv cs.AI Research & Papers
Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperativ…
arXiv cs.AI Research & Papers
CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications
arXiv cs.AI Research & Papers
Making AI-Generated Feedback Matter: From Provision to Student Enactment
arXiv cs.AI Research & Papers
VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies
arXiv cs.AI Research & Papers
Backdoor Decontamination Dynamics in LLM Agents
arXiv cs.AI Research & Papers
Dynamics Models for Offline Hyperparameter Selection in Real-World RL
arXiv cs.AI Research & Papers
From Monolithic to Modular: Segment-level Automatic Prompt Optimization
arXiv cs.AI Research & Papers
Distribird: Literature-Informed Prior Distribution Design for Bayesian Model Calibration
arXiv cs.AI Research & Papers
Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evalua…