Español

Explorar

Noticias de IA

22318 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
Variance Reduction for Non-Log-Concave Sampling with Applications to Inverse Problems
arXiv cs.AI Research & Papers
Data Augmentations for Data-Constrained Language Model Pretraining
arXiv cs.AI Research & Papers
From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation
arXiv cs.AI Research & Papers
Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning
arXiv cs.AI Research & Papers
LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flo…
arXiv cs.AI Research & Papers
EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video
arXiv cs.AI Research & Papers
Minimal Oversight: Uncertainty-Aware Governance for Delegated AI Systems
arXiv cs.AI Research & Papers
When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LV…
arXiv cs.AI Research & Papers
EffGen: Enabling Small Language Models as Capable Autonomous Agents
arXiv cs.AI Research & Papers
Lect\=uraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning a…
arXiv cs.AI Research & Papers
SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quali…
arXiv cs.AI Research & Papers
Input-Dependent Fisher Information for Local Sensitivity Analysis of Medical Image Classi…
arXiv cs.AI Research & Papers
What Should a Streaming Video Model Remember?
arXiv cs.AI Research & Papers
ArtBoost: Synthetic Articulatory Data Augmentation for Acoustic-to-Articulatory Inversion
arXiv cs.AI Research & Papers
RL-Index: Reinforcement Learning for Retrieval Index Reasoning
arXiv cs.AI Research & Papers
Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
arXiv cs.AI Research & Papers
Is Your Trajectory Displacement Safe in Long-tail?
arXiv cs.AI Research & Papers
FlowMPC: Improving Flow Matching policies with World Models
arXiv cs.AI Research & Papers
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffus…
arXiv cs.AI Research & Papers
InvDesMobility: a reliability-gated first-principles feedback framework for closed-loop m…
arXiv cs.AI Research & Papers
Scaling Adaptive Depth with Norm-Agnostic Residual Networks
arXiv cs.AI Research & Papers
VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal …
arXiv cs.AI Research & Papers
Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting
arXiv cs.AI Research & Papers
Training and Evaluating Diffusion Policies with Long Context Lengths
arXiv cs.AI Research & Papers
Autonomous End-to-End SOH Prediction Services for Battery Systems via Temporal-Contrastiv…
arXiv cs.AI Research & Papers
Leveraging Deep Learning for Object and Position Recognition of Load Carriers for Autonom…
arXiv cs.AI Research & Papers
Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering A…
arXiv cs.AI Research & Papers
Theorem-Grounded Execution Ontologies for Interpretable Machine Reasoning
arXiv cs.AI Research & Papers
Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re…
arXiv cs.AI Research & Papers
Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning