DRL-Driven Edge-Aware Utility Optimization for Multi-Slice 6G Networks
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Anytime Training with Schedule-Free Spectral Optimization
Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics
CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Red…
Naturalistic Computational Cognitive Science: Towards generalizable models and theories t…
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Flo…
SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
Enhancing Deep Neural Network Reliability with Refinement and Calibration
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Ski…
On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning
PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogrammin…
SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Func…
Multi-Gate Residuals
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints
Curriculum reinforcement learning with measurable task representation learning
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasti…
Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Conti…
Tensor Cache: Eviction-conditioned Associative Memory for Transformers
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
Graph Alignment Topology as an Inductive Bias for Grounding Detection
Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matt…
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
A Fine-Tuned BERT Classifier for Personal-Letter Titles in Late-Ming and Early-Qing Colle…
Defining AI Fatigue in Academic Contexts: Dimensions, Indicators, and a Stage-Based Model…
As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs
One-Forcing: Towards Stable One-Step Autoregressive Video Generation