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
Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance fo…
arXiv cs.AI Research & Papers
Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity
arXiv cs.AI Research & Papers
DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on…
arXiv cs.AI Research & Papers
DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy …
arXiv cs.AI Research & Papers
Are Video Reasoning Models Ready to Go Outside?
arXiv cs.AI Research & Papers
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
arXiv cs.AI Research & Papers
Visual Prompt Discovery via Semantic Exploration
arXiv cs.AI Research & Papers
Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
arXiv cs.AI Research & Papers
TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scen…
arXiv cs.AI Research & Papers
SMART: When is it Actually Worth Expanding a Speculative Tree?
arXiv cs.AI Research & Papers
RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora
arXiv cs.AI Research & Papers
Lyapunov-Certified Direct Switching Theory for Q-Learning
arXiv cs.AI Research & Papers
Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Superv…
arXiv cs.AI Research & Papers
Shared Lexical Task Representations Explain Behavioral Variability In LLMs
arXiv cs.AI Research & Papers
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving
arXiv cs.AI Research & Papers
An Executable Benchmarking Suite for Tool-Using Agents
arXiv cs.AI Research & Papers
TDGT: A Tabular Data Generation Toolkit supporting adaptive GPU-accelerated Bayesian mixt…
arXiv cs.AI Research & Papers
Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking
arXiv cs.AI Research & Papers
TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation
arXiv cs.AI Research & Papers
LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driv…
arXiv cs.AI Research & Papers
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
arXiv cs.AI Research & Papers
BREIT: A Framework for Brain Stroke Reconstruction using Multi-Frequency 3D EIT
arXiv cs.AI Research & Papers
When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models
arXiv cs.AI Research & Papers
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv cs.AI Research & Papers
A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimizati…
arXiv cs.AI Research & Papers
What Drives Interactive Improvement from Feedback?
arXiv cs.AI Research & Papers
How Can AI Find My Model? A Model-Finding Experimental Study Considering Data Formats, Em…
arXiv cs.AI Research & Papers
Beyond expert users: agents should help users construct preferences, not just elicit them
arXiv cs.AI Research & Papers
The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving…
arXiv cs.AI Research & Papers
Cross-Domain Feature Expansion for Tabular Medical Data via Knowledge Graphs Injection