Explorar

Noticias de IA

22116 elementos — filtrados, clasificados y sin duplicados

Hugging Face Daily Papers Research & Papers
REACH: Interpretability-Driven Feature Identification and Architecture Compression for Mu…
Hugging Face Daily Papers Research & Papers
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
Hugging Face Daily Papers Research & Papers
TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joi…
Hugging Face Daily Papers Research & Papers
Last-Iterate Convergence of Optimistic Multiplicative Weight Update
Hugging Face Daily Papers Research & Papers
Automated Creativity Evaluation of Language Models Across Open-Ended Tasks
Hugging Face Daily Papers Research & Papers
RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
Hugging Face Daily Papers Research & Papers
Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent wi…
Hugging Face Daily Papers Research & Papers
Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professio…
Hugging Face Daily Papers Research & Papers
Probabilistic Salary Prediction with Graph Attention Networks and a Mixture Density Netwo…
Hugging Face Daily Papers Research & Papers
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Hugging Face Daily Papers Research & Papers
Sparse probes and murky physics: a case study of interpretability challenges in a foundat…
Hugging Face Daily Papers Research & Papers
Tree-Structured Orthonormal Decomposition of the Aitchison Simplex
Hugging Face Daily Papers Research & Papers
Improving Cross-Format Robustness in Language Models with Multi-Format Training
arXiv cs.AI Research & Papers
Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs
arXiv cs.AI Research & Papers
Geometrically Averaged Hard Target Updates for Linear Q-Learning
arXiv cs.AI Research & Papers
Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Proce…
arXiv cs.AI Research & Papers
SCOPE: Sequential Causal Optimization of Process Interventions
arXiv cs.AI Research & Papers
HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent
arXiv cs.AI Research & Papers
MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean…
arXiv cs.AI Research & Papers
Adoption of Generative Artificial Intelligence in the German Software Engineering Industr…
arXiv cs.AI Research & Papers
Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models
arXiv cs.AI Research & Papers
Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept…
arXiv cs.AI Research & Papers
Divide-and-Conquer Modeling for the CTF-4-Science Lorenz Benchmark
arXiv cs.AI Research & Papers
TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving
arXiv cs.AI Research & Papers
Quantifying Uncertainty in AI Visibility: A Statistical Framework for Generative Search M…
arXiv cs.AI Research & Papers
Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport
arXiv cs.AI Research & Papers
Reasoning over Semantic IDs Enhances Generative Recommendation
arXiv cs.AI Research & Papers
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
arXiv cs.AI Research & Papers
SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning
arXiv cs.AI Research & Papers
Prosociality by Coupling, Not Mere Observation: Homeostatic Sharing in an Inspectable Rec…