Español

Explorar

Noticias de IA

27413 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
VERPO: Verified Evidence Regularized Policy Optimization
arXiv cs.AI Research & Papers
Linear Algebra Foundations of Efficient Attention: A Phase Reversal in Rank Collapse Unde…
arXiv cs.AI Research & Papers
From Splats to Silicon: Rethinking Computational Efficiency of 3DGS
arXiv cs.AI Research & Papers
Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Servi…
arXiv cs.AI Research & Papers
PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Represe…
arXiv cs.AI Research & Papers
Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliabi…
arXiv cs.AI Research & Papers
TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs
arXiv cs.AI Research & Papers
The Role of Gradient Modification in Heavy-Tailed Nonconvex Stochastic Min-Max Optimizati…
arXiv cs.AI Research & Papers
MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grou…
arXiv cs.AI Research & Papers
Explainable Deep Learning for Price-Trade Dynamics: From Black-Box Forecasts to Effective…
arXiv cs.AI Research & Papers
SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness
arXiv cs.AI Research & Papers
FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures
arXiv cs.AI Research & Papers
Hypersolid: Emergent Vision Representations via Short-Range Repulsion
arXiv cs.AI Research & Papers
On BatchNorm Forward Modes in Value-Based Reinforcement Learning
arXiv cs.AI Research & Papers
SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-B…
arXiv cs.AI Research & Papers
Discovering Translation-Worthy Languages with E-Values
arXiv cs.AI Research & Papers
Parity, Sensitivity, and Transformers
arXiv cs.AI Research & Papers
Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
arXiv cs.AI Research & Papers
Attention-Weighted Value Projection for KV-Cache Compression
arXiv cs.AI Research & Papers
Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems
arXiv cs.AI Research & Papers
Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Un…
arXiv cs.AI Research & Papers
DART: Distributional Adversarial Recurrent Training for Algorithm Learning
arXiv cs.AI Research & Papers
STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient L…
arXiv cs.AI Research & Papers
AVSplat: Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning
arXiv cs.AI Research & Papers
Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User …
arXiv cs.AI Research & Papers
Grounded and Faithful P&ID Reasoning: Constraining Vision-Language Models with Recovered …
arXiv cs.AI Research & Papers
What if LLMs Ate Their Words: Causal History Effects in Multi-Turn Interaction
arXiv cs.AI Research & Papers
AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection
arXiv cs.AI Research & Papers
Memory in Deep Time-Series Models
arXiv cs.AI Research & Papers
Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning