Massive Free Documents

Discover millions of professional documents covering academic, business, culture and more.

Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam

Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam

Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One

Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One

Fast Asymptotically Optimal Kinodynamic Planning via Vectorization

Fast Asymptotically Optimal Kinodynamic Planning via Vectorization

From Codebases to LLMs Non-Inclusive Naming in Linux Foundation Repositories

From Codebases to LLMs Non-Inclusive Naming in Linux Foundation Repositories

SUNTA: Hierarchical Video Prediction with Surprise-based Chunking

SUNTA: Hierarchical Video Prediction with Surprise-based Chunking

Reliability-Aware CT–MRI Registration Quality Engineering Framework with Stability Analysis and Risk Classification

Reliability-Aware CT–MRI Registration Quality Engineering Framework with Stability Analysis and Risk Classification

DemoPSD Disagreement-Modulated Policy Self-Distillation

DemoPSD Disagreement-Modulated Policy Self-Distillation

Freeform Preference Learning for Robotic Manipulation

Freeform Preference Learning for Robotic Manipulation

Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deployment

Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deployment

Optimal Scaling of MCMC Algorithms: the Hamiltonian Approach

Optimal Scaling of MCMC Algorithms: the Hamiltonian Approach

Deforking the World of Code: A Project-Provenance Map that Recovers Cross-Forge Fork Families that Platform Graphs Cannot See

Deforking the World of Code: A Project-Provenance Map that Recovers Cross-Forge Fork Families that Platform Graphs Cannot See

Safety from Honesty in a Disinterested AI Predictor

Safety from Honesty in a Disinterested AI Predictor

CADENZA：将自然语言意图编译为用于语义查询处理的特定任务算子DAG

CADENZA：将自然语言意图编译为用于语义查询处理的特定任务算子DAG

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

Forget, Anticipate and Adapt: Test Time Training for Long Videos

Forget, Anticipate and Adapt: Test Time Training for Long Videos