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
Training-Free Hidden-State Refinement for Flow-Matching Image Generators
arXiv cs.AI Research & Papers
DIP: Dynamic In-Context Planner For Diffusion Language Models
arXiv cs.AI Research & Papers
AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
arXiv cs.AI Research & Papers
Kinship Data Benchmark for Multi-hop Reasoning
arXiv cs.AI Research & Papers
A Unifying Perspective on Language Model Representations: From Filler-Role Structure to M…
arXiv cs.AI Research & Papers
To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
arXiv cs.AI Research & Papers
Entropy-Aware Token Rejection for Improving Speculative Decoding
arXiv cs.AI Research & Papers
DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Questi…
arXiv cs.AI Research & Papers
KV Admission: Learning What to Write for Efficient Long-Context LLM Inference
arXiv cs.AI Research & Papers
Development of an Autonomous AI Coding Agent using Monte Carlo Tree Search (MCTS) and Gem…
arXiv cs.AI Research & Papers
The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Founda…
arXiv cs.AI Research & Papers
Look It Up: Analysing Internal Web Search Capabilities of Modern LLMs
arXiv cs.AI Research & Papers
WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in …
arXiv cs.AI Research & Papers
The information geometry of product-reference discrete diffusion: Interaction growth comp…
arXiv cs.AI Research & Papers
On the Optimality of Kinship Naming: an Information-theoretic Approach
arXiv cs.AI Research & Papers
From the Loss Landscape to Diverse Feature Learning in Neural Networks
arXiv cs.AI Research & Papers
Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions a…
arXiv cs.AI Research & Papers
LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from sci…
arXiv cs.AI Research & Papers
FRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production
arXiv cs.AI Research & Papers
Structured State Reconciliation for Human-AI Task Handover
arXiv cs.AI Research & Papers
ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground T…
arXiv cs.AI Research & Papers
On the Instance Hardness as a Decision Criterion in TinyML Systems
arXiv cs.AI Research & Papers
Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts
arXiv cs.AI Research & Papers
ActiveAugment: Online Active Learning for Augmentation Selection in Deep Learning
arXiv cs.AI Research & Papers
AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies
arXiv cs.AI Research & Papers
The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning
arXiv cs.AI Research & Papers
MineCEraft: Evaluating Language Models as Construction Engineers in the World of Minecraft
arXiv cs.AI Research & Papers
FRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis
arXiv cs.AI Research & Papers
Benevolent Bias in Multi-Turn Human-Agent Dialogue
arXiv cs.AI Research & Papers
Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs