Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
DRL-Driven Edge-Aware Utility Optimization for Multi-Slice 6G Networks
arXiv cs.AI Research & Papers
Anytime Training with Schedule-Free Spectral Optimization
arXiv cs.AI Research & Papers
Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics
arXiv cs.AI Research & Papers
CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
arXiv cs.AI Research & Papers
VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Red…
arXiv cs.AI Research & Papers
Naturalistic Computational Cognitive Science: Towards generalizable models and theories t…
arXiv cs.AI Research & Papers
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Flo…
arXiv cs.AI Research & Papers
SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
arXiv cs.AI Research & Papers
Enhancing Deep Neural Network Reliability with Refinement and Calibration
arXiv cs.AI Research & Papers
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Ski…
arXiv cs.AI Research & Papers
On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning
arXiv cs.AI Research & Papers
PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogrammin…
arXiv cs.AI Research & Papers
SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Func…
arXiv cs.AI Research & Papers
Multi-Gate Residuals
arXiv cs.AI Research & Papers
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
arXiv cs.AI Research & Papers
Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints
arXiv cs.AI Research & Papers
Curriculum reinforcement learning with measurable task representation learning
arXiv cs.AI Research & Papers
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasti…
arXiv cs.AI Research & Papers
Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Conti…
arXiv cs.AI Research & Papers
Tensor Cache: Eviction-conditioned Associative Memory for Transformers
arXiv cs.AI Research & Papers
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
arXiv cs.AI Research & Papers
Graph Alignment Topology as an Inductive Bias for Grounding Detection
arXiv cs.AI Research & Papers
Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matt…
arXiv cs.AI Research & Papers
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
arXiv cs.AI Research & Papers
Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good
arXiv cs.AI Research & Papers
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
arXiv cs.AI Research & Papers
A Fine-Tuned BERT Classifier for Personal-Letter Titles in Late-Ming and Early-Qing Colle…
arXiv cs.AI Research & Papers
Defining AI Fatigue in Academic Contexts: Dimensions, Indicators, and a Stage-Based Model…
arXiv cs.AI Research & Papers
As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs
arXiv cs.AI Research & Papers
One-Forcing: Towards Stable One-Step Autoregressive Video Generation