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
Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching
arXiv cs.AI Research & Papers
Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage
arXiv cs.AI Research & Papers
Distributional Regression with Tabular Foundation Models: Evaluating Probabilistic Predic…
arXiv cs.AI Research & Papers
Measuring Intent Comprehension in LLMs
arXiv cs.AI Research & Papers
From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with …
arXiv cs.AI Research & Papers
"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Exper…
arXiv cs.AI Policy & Regulation
Towards Adaptive Categories: Dimensional Governance for Agentic AI
arXiv cs.AI Research & Papers
Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Effici…
arXiv cs.AI Research & Papers
Efficient Traffic State Prediction With Dynamic Joint Spatio-Temporal Relation Inference
arXiv cs.AI Research & Papers
Revisiting Text Ranking in Deep Research
arXiv cs.AI Research & Papers
Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparati…
arXiv cs.AI Research & Papers
ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
arXiv cs.AI Research & Papers
HaineiFRDM: Structure-Preserving Diffusion for Film Restoration under Fast Motion and Div…
arXiv cs.AI Research & Papers
Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing
arXiv cs.AI Research & Papers
Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
arXiv cs.AI Research & Papers
Tell Me: An LLM-powered Mental Well-being Assistant with RAG, Synthetic Dialogue Generati…
arXiv cs.AI Research & Papers
EgoExo-Con: Exploring View-Invariant Video Temporal Understanding
arXiv cs.AI Research & Papers
Strengthening LLMs for Tabular Prediction with Structural Priors
arXiv cs.AI Research & Papers
DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework
arXiv cs.AI Research & Papers
OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Base…
arXiv cs.AI Research & Papers
From RAG to Agentic RAG for Faithful Islamic Question Answering
arXiv cs.AI Research & Papers
Cross-Attention is Half Explanation in Speech-to-Text Models
arXiv cs.AI Research & Papers
Meta-learning ecological priors from large language models explains human learning and de…
arXiv cs.AI Research & Papers
Mitigating Cross-Image Information Leakage in Multi-Image Understanding with Large Vision…
arXiv cs.AI Research & Papers
NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models
arXiv cs.AI Research & Papers
The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Lan…
arXiv cs.AI Research & Papers
FedSA-GCL: A Semi-Asynchronous Federated Graph Learning Framework with Personalized Aggre…
arXiv cs.AI Research & Papers
Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinfo…
arXiv cs.AI Research & Papers
LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models
arXiv cs.AI Research & Papers
HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning