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
Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance
arXiv cs.AI Research & Papers
Diffusion Crossover: Defining Evolutionary Recombination in Diffusion Models via Noise Se…
arXiv cs.AI Research & Papers
Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation…
arXiv cs.AI Research & Papers
Can VLMs Reason Robustly? A Neuro-Symbolic Investigation
arXiv cs.AI Research & Papers
Learning Dexterous Grasping from Sparse Taxonomy Guidance
arXiv cs.AI Research & Papers
On Variance Reduction in Learning Mean Flows
arXiv cs.AI Research & Papers
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
arXiv cs.AI Research & Papers
Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
arXiv cs.AI Research & Papers
Optimal Self-Consistency for Efficient Reasoning with Large Language Models
arXiv cs.AI Research & Papers
Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation
arXiv cs.AI Research & Papers
Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise
arXiv cs.AI Research & Papers
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation
arXiv cs.AI Research & Papers
CoReLIN: Constraint-based Reasoning for Zero-shot Lifelong Interactive Navigation
arXiv cs.AI Research & Papers
Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models
arXiv cs.AI Research & Papers
An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
arXiv cs.AI Research & Papers
LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Mu…
arXiv cs.AI Research & Papers
MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents
arXiv cs.AI Research & Papers
Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection
arXiv cs.AI Research & Papers
Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?
arXiv cs.AI Research & Papers
SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion…
arXiv cs.AI Research & Papers
CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning
arXiv cs.AI Research & Papers
CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigge…
arXiv cs.AI Research & Papers
Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models
arXiv cs.AI Research & Papers
Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in L…
arXiv cs.AI Research & Papers
Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models
arXiv cs.AI Research & Papers
DA-Studio: An Agentic System for End-to-End Data Analysis
arXiv cs.AI Research & Papers
Corruption Robust Offline Reinforcement Learning with Human Feedback
arXiv cs.AI Research & Papers
Design and Implementation of Agentic Orchestrations and Orchestration of Agents
arXiv cs.AI Research & Papers
LLM-Driven Personalities for Decision Making in Emergency Simulations
arXiv cs.AI Research & Papers
ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs