Back to feed

cs.LG

39 posts

0
cs.AIcs.CLcs.LG2d

VL-RouterBench: A Benchmark for Vision-Language Model Routing

0
0
cond-mat.stat-mechcs.LGmath.DS2d

From geometry to dynamics: Learning overdamped Langevin dynamics from sparse observations with geometric constraints

0
0
cs.LGpaperq-fin.GN2d

The Nonstationarity-Complexity Tradeoff in Return Prediction

0
0
cs.LGpaperresearch2d

Distribution-Free Process Monitoring with Conformal Prediction

0
0
cs.AIcs.LGmath.ST2d

Le Cam Distortion: A Decision-Theoretic Framework for Robust Transfer Learning

0
0
cs.AIcs.LGpaper2d

Regret-Based Federated Causal Discovery with Unknown Interventions

0
0
cs.CVcs.LGpaper2d

Memorization in 3D Shape Generation: An Empirical Study

0
0
cs.AIcs.LGpaper2d

BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization

0
0
cs.AIcs.CYcs.LG2d

AI tutoring can safely and effectively support students: An exploratory RCT in UK classrooms

0
0
cs.LGmath.NAmath.ST2d

Simultaneous Approximation of the Score Function and Its Derivatives by Deep Neural Networks

0
0
cs.LGpaperresearch2d

Random Controlled Differential Equations

0
0
cs.LGmath.OCpaper2d

Calibrated Multi-Level Quantile Forecasting

0
0
cs.LGpaperresearch2d

End-to-End Test-Time Training for Long Context

0
0
cs.LGecon.EMpaper2d

Bellman Calibration for V-Learning in Offline Reinforcement Learning

0
0
cs.CLcs.LGpaper2d

Eliciting Behaviors in Multi-Turn Conversations

0
0
cs.CLcs.HCcs.LG2d

Training AI Co-Scientists Using Rubric Rewards

0
0
cs.LGpaperresearch17h

Spectral Graph Neural Networks for Cognitive Task Classification in fMRI Connectomes

0
0
cs.LGmath.ATpaper16h

Frequent subgraph-based persistent homology for graph classification

0
0
cs.LGmath.STpaper16h

Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach

0
0
cs.CLcs.LGpaper16h

Adaptive Dependency-aware Prompt Optimization Framework for Multi-Step LLM Pipeline

0
0
cs.AIcs.CLcs.LG16h

Iterative Deployment Improves Planning Skills in LLMs

0
0
cs.AIcs.CLcs.IR16h

RAIR: A Rule-Aware Benchmark Uniting Challenging Long-Tail and Visual Salience Subset for E-commerce Relevance Assessment

0
0
cs.CVcs.LGpaper15h

ProDM: Synthetic Reality-driven Property-aware Progressive Diffusion Model for Coronary Calcium Motion Correction in Non-gated Chest CT

0
0
cs.AIcs.LGcs.RO15h

MSACL: Multi-Step Actor-Critic Learning with Lyapunov Certificates for Exponentially Stabilizing Control

0
0
cs.AIcs.LGpaper15h

Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning

0
0
cs.LGpaperresearch14h

Attribution-Guided Distillation of Matryoshka Sparse Autoencoders

0
0
cs.AIcs.LGcs.NE14h

SymSeqBench: a unified framework for the generation and analysis of rule-based symbolic sequences and datasets

0
0
cs.AIcs.CVcs.LG14h

DarkEQA: Benchmarking Vision-Language Models for Embodied Question Answering in Low-Light Indoor Environments

0
0
cs.LGpaperresearch14h

Efficiently Estimating Data Efficiency for Language Model Fine-tuning

0
0
cs.LGmath.NAmath.OC14h

Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis

0