Español

Explorar

Noticias de IA

37834 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
Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural …
arXiv cs.AI Research & Papers
When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents
arXiv cs.AI Research & Papers
Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them
arXiv cs.AI Research & Papers
TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction
arXiv cs.AI Research & Papers
Imprecise Belief Fusion Improves Multi-agent Social Learning
arXiv cs.AI Research & Papers
Asking Questions the Right Way: A Multi-Agent Conversational System for Prompt Formulatio…
arXiv cs.AI Research & Papers
Spatiotemporal Proximal Causal Inference under Hidden Confounding and Interference
arXiv cs.AI Research & Papers
LongChart VQA: A Comprehensive Benchmark for MLLMs with Complex Multi-Chart Reasoning
arXiv cs.AI Research & Papers
Context Compaction Theory
arXiv cs.AI Research & Papers
Dense Language Generation Made Simple: Deterministic, Randomized, and Multi-Order Algorit…
arXiv cs.AI Research & Papers
Ranking Image Fusion the Way Humans Do: A Learned Pairwise Preference Metric for Infrared…
arXiv cs.AI Research & Papers
UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction
arXiv cs.AI Research & Papers
Training nGPT
arXiv cs.AI Research & Papers
Rethinking Video Token Compression with a Global Codebook: Learning Once, Compressing Eve…
arXiv cs.AI Research & Papers
It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for …
arXiv cs.AI Research & Papers
ReBRAC-v2: The Return of the King
arXiv cs.AI Research & Papers
DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction
arXiv cs.AI Research & Papers
Policy Optimality Measurement for Multi-Vehicle Decision-Making: From Extrinsic Indicator…
arXiv cs.AI Security & Safety
FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intel…
arXiv cs.AI Research & Papers
Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reaso…
arXiv cs.AI Research & Papers
Credit the Right Box: Marginal Contribution Assignment for Structured Visual Perception
arXiv cs.AI Research & Papers
DeBERTa-Sentinel: Toward Transparent and Trustworthy Detection of AI-Generated Text
arXiv cs.AI Research & Papers
What Could the Agent See at 19:05? Generating Temporal Enterprise Scenarios from Real Res…
arXiv cs.AI Research & Papers
WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driv…
arXiv cs.AI Security & Safety
VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Visio…
arXiv cs.AI Security & Safety
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
arXiv cs.AI Research & Papers
KING: Embodiment-Aware Kinematic Graph Neural Network for Unified Motion Representation o…
arXiv cs.AI Research & Papers
MedUPS: Towards Diagnostic Assistance in Uncommon Medical Cases with Large Language Models
arXiv cs.AI Research & Papers
Who Belongs in the Eval Set? A Capability-Taxonomy-Driven Pipeline for Curating Regressio…
arXiv cs.AI Research & Papers
Beyond Gene Reconstruction: Learning Cell Representations through Complementary Transcrip…