Español

Explorar

Noticias de IA

21863 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
Hugging Face Daily Papers Research & Papers
Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Pred…
Hugging Face Daily Papers Research & Papers
Sharp Root Anti-Concentration via Projective Incidence and Ordered Root Laws
Hugging Face Daily Papers Research & Papers
TCPO: Turn-Level Credit Policy Optimization
Hugging Face Daily Papers Research & Papers
Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation
arXiv cs.AI Research & Papers
SERUM: State Extraction and Refinement for User Modeling
arXiv cs.AI Research & Papers
OsteoCAD: A Human-in-the-Loop Cloud-Edge Framework for Bone Tumor Segmentation
arXiv cs.AI Research & Papers
CalibratedRubric: Task-Adaptive Rubric Banks for Open-Ended LLM Evaluation
arXiv cs.AI Research & Papers
When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinat…
arXiv cs.AI Research & Papers
Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Mu…
arXiv cs.AI Research & Papers
ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consiste…
arXiv cs.AI Research & Papers
HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators
arXiv cs.AI Research & Papers
Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulations
arXiv cs.AI Research & Papers
Multi-Granularity Position Embedding of Graphs via Granular-Ball for Link Prediction
arXiv cs.AI Research & Papers
Stem: Rethinking Causal Information Flow in Sparse Attention
arXiv cs.AI Research & Papers
Linear Proposal Operators and Stochastic Search Geometry in SOMA and Differential Evoluti…
arXiv cs.AI Research & Papers
DoubleHelix: Structured Cross-Modal Fusion for Audio-Visual Speech Recognition with LLMs
arXiv cs.AI Research & Papers
When Bits Break Recourse: Counterfactual-Faithful Quantization
arXiv cs.AI Research & Papers
AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian S…
arXiv cs.AI Research & Papers
Small Is Enough: Per-User Style Rewriting of AI-Edited Text via LoRA Adapters
arXiv cs.AI Research & Papers
A Human-Centered Validation of the Explainability-Performance Coefficient
arXiv cs.AI Research & Papers
Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusio…
arXiv cs.AI Research & Papers
Evaluating the Alignment Between GeoAI Explanations and Domain Knowledge in Satellite-Bas…
arXiv cs.AI Research & Papers
TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Fi…
arXiv cs.AI Research & Papers
Detecting AI-Generated Videos with Spiking Neural Networks
arXiv cs.AI Research & Papers
Robust Bidirectional Associative Memory via Regularization Inspired by the Subspace Rotat…
arXiv cs.AI Research & Papers
MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation
arXiv cs.AI Research & Papers
DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity i…
arXiv cs.AI Research & Papers
The persuasive power of large language models does not depend on their perceived national…
arXiv cs.AI Research & Papers
Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning
arXiv cs.AI Research & Papers
Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversat…