Español

Explorar

Noticias de IA

29647 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
Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
arXiv cs.AI Research & Papers
When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-S…
arXiv cs.AI Research & Papers
Evolutionary Discovery of Bivariate Bicycle Codes with LLM-Guided Search
arXiv cs.AI Research & Papers
Policy and World Modeling Co-Training for Language Agents
arXiv cs.AI Research & Papers
AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End…
arXiv cs.AI Research & Papers
PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
arXiv cs.AI Research & Papers
MASER: Modality-Adaptive Specialist Routing for Embodied 3D Spatial Intelligence
arXiv cs.AI Research & Papers
Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
arXiv cs.AI Research & Papers
Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
arXiv cs.AI Research & Papers
SimSD: Simple Speculative Decoding in Diffusion Language Models
arXiv cs.AI Research & Papers
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
arXiv cs.AI Research & Papers
AdaCodec: A Predictive Visual Code for Video MLLMs
arXiv cs.AI Research & Papers
Algebraic anti-unification
arXiv cs.AI Research & Papers
Explainable AI Through a Democratic Lens: DhondtXAI for D'Hondt-Projected Feature Attribu…
arXiv cs.AI Security & Safety
Safety Must Precede the Deployment of Open-Ended AI
arXiv cs.AI Research & Papers
Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Sca…
arXiv cs.AI Security & Safety
Agent Guide: A Simple Agent Behavioral Watermarking Framework
arXiv cs.AI Research & Papers
Language Model Networks: Supervision-Efficient Learning through Dense Communication
arXiv cs.AI Research & Papers
Formally Solving Answer-Construction Problems in Lean
arXiv cs.AI Research & Papers
On the Theoretical Limitations of Embedding-based Link Prediction
arXiv cs.AI Research & Papers
Query Circuits: Explaining How Language Models Answer User Prompts
arXiv cs.AI Research & Papers
REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing
arXiv cs.AI Research & Papers
Addressing Longstanding Challenges in Cognitive Science with Language Models
arXiv cs.AI Research & Papers
LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services
arXiv cs.AI Research & Papers
On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering
arXiv cs.AI Research & Papers
Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention
arXiv cs.AI Opinion & Editorial
Unplugging a Seemingly Sentient Machine Is the Rational Choice -- A Metaphysical Perspect…
arXiv cs.AI Research & Papers
PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Mo…
arXiv cs.AI Research & Papers
The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language M…
arXiv cs.AI Research & Papers
Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge