Español

Explorar

Noticias de IA

22116 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
Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
arXiv cs.AI Research & Papers
The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Polic…
arXiv cs.AI Research & Papers
LSTM based IoT Device Identification
arXiv cs.AI Research & Papers
MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Sc…
arXiv cs.AI Research & Papers
When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications
arXiv cs.AI Research & Papers
CoVar: Confidence-Variance-Guided Pseudo-Label Selection for Semi-Supervised Learning
arXiv cs.AI Research & Papers
Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Schedu…
arXiv cs.AI Research & Papers
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learni…
arXiv cs.AI Research & Papers
Mind the Perspective: Let's Reason Recursively for Theory of Mind
arXiv cs.AI Research & Papers
Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning
arXiv cs.AI Research & Papers
TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Da…
arXiv cs.AI Research & Papers
HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distil…
arXiv cs.AI Research & Papers
Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline
arXiv cs.AI Research & Papers
Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
arXiv cs.AI Research & Papers
From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral …
arXiv cs.AI Research & Papers
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeli…
arXiv cs.AI Research & Papers
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
arXiv cs.AI Research & Papers
APPO: Agentic Procedural Policy Optimization
arXiv cs.AI Research & Papers
Non-frontal face recognition using GANs and memristor-based classifiers
arXiv cs.AI Research & Papers
On the Limits of LLM-as-Judge for Scientific Novelty Assessment
arXiv cs.AI Research & Papers
Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simul…
arXiv cs.AI Research & Papers
Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding
arXiv cs.AI Research & Papers
Runtime Enforcement of Hybrid System Properties
arXiv cs.AI Research & Papers
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral G…
arXiv cs.AI Research & Papers
Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation
arXiv cs.AI Research & Papers
Multi-Rate Mixture of Experts for Accelerating Liquid Neural Network Training
arXiv cs.AI Research & Papers
Making Foresight Actionable: Repurposing Representation Alignment in World Action Models
arXiv cs.AI Research & Papers
Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuou…
arXiv cs.AI Research & Papers
Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Lea…
arXiv cs.AI Research & Papers
DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real W…