Español

Explorar

Noticias de IA

21813 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
Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent
arXiv cs.AI Research & Papers
Towards a satellite image manipulation and deepfake localization benchmark dataset
arXiv cs.AI Research & Papers
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
arXiv cs.AI Research & Papers
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
arXiv cs.AI Research & Papers
Curiosity-Diffuser: Curiosity Guide Diffusion Models for Reliability
arXiv cs.AI Research & Papers
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
arXiv cs.AI Research & Papers
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Cali…
arXiv cs.AI Research & Papers
What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend
arXiv cs.AI Research & Papers
Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe A…
arXiv cs.AI Research & Papers
PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates
arXiv cs.AI Research & Papers
Personalized Federated Sparse Adaptation of Time-Series Foundation Models
arXiv cs.AI Research & Papers
Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
arXiv cs.AI Research & Papers
SimMOF: AI agent for Automated MOF Simulations
arXiv cs.AI Research & Papers
When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large L…
arXiv cs.AI Research & Papers
Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks
arXiv cs.AI Research & Papers
EuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive De…
arXiv cs.AI Research & Papers
CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical V…
arXiv cs.AI Research & Papers
The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Pro…
arXiv cs.AI Research & Papers
Masked diffusion enables coherent beat tracking
arXiv cs.AI Research & Papers
AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluati…
arXiv cs.AI Research & Papers
Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark
arXiv cs.AI Research & Papers
ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Gene…
arXiv cs.AI Research & Papers
Text2GraphQuery-Bench: A Text to Graph Query Benchmark
arXiv cs.AI Research & Papers
TwinIR: Coordinated Invisible Dual-Point Attacks on Online HD Map Construction
arXiv cs.AI Research & Papers
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
arXiv cs.AI Research & Papers
Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Medi…
arXiv cs.AI Research & Papers
Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Dis…
arXiv cs.AI Research & Papers
Approximate Multi-Objective Search Under Rulebooks
arXiv cs.AI Research & Papers
Training-Free Hashing-Based Attention via Binary Principal Components
arXiv cs.AI Research & Papers
MESH: Memory-Efficient Sinkhorn Optimization for Mixture-of-Experts Training