Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Representational alignment yields generalizable safety in language models
arXiv cs.AI Research & Papers
Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasonin…
arXiv cs.AI Research & Papers
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
arXiv cs.AI Research & Papers
Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxili…
arXiv cs.AI Security & Safety
SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations …
arXiv cs.AI Research & Papers
A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequ…
arXiv cs.AI Research & Papers
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
arXiv cs.AI Research & Papers
TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathol…
arXiv cs.AI Research & Papers
Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-…
arXiv cs.AI Research & Papers
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
arXiv cs.AI Research & Papers
ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize
arXiv cs.AI Research & Papers
RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting
arXiv cs.AI Research & Papers
GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Model…
arXiv cs.AI Research & Papers
Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO
arXiv cs.AI Research & Papers
Investigating the Ability of Large Language Models to Analyze Recipes for Diabetes
arXiv cs.AI Research & Papers
FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation
arXiv cs.AI Research & Papers
Catalogue Photography as a Cold Start: Toward Deployable Carbide Burr Recognition
arXiv cs.AI Research & Papers
Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data
arXiv cs.AI Research & Papers
The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations
arXiv cs.AI Research & Papers
Grammar-Aligned Decoding
arXiv cs.AI Research & Papers
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation
arXiv cs.AI Research & Papers
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive J…
arXiv cs.AI Research & Papers
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
arXiv cs.AI Research & Papers
Data Market Design through Deep Learning
arXiv cs.AI Research & Papers
Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcem…
arXiv cs.AI Research & Papers
Sionna RT: Technical Report
arXiv cs.AI Research & Papers
Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners
arXiv cs.AI Research & Papers
Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmF…
arXiv cs.AI Research & Papers
Beyond BLEU: A Case for Redefining Sign Language Translation Benchmarks
arXiv cs.AI Research & Papers
Witnesses Explain Anomalies