zhiqiang xu

t-BEN: A Temporal Logic Guided Approach for Temporal Reasoning Benchmark Generation

Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes

Concise Reasoning in the Lens of Lagrangian Optimization

Utility Boundary of Dataset Distillation: Scaling and Configuration-Coverage Laws

GeoDM: Geometry-aware Distribution Matching for Dataset Distillation

Dynamic Locally Linear Graph Learning for Geometry-Aware GNNs

KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction

Local-Curvature-Aware Knowledge Graph Embedding via Extended Ricci Flow

CataRAG: LLM-based Enzyme-Substrate Prediction with Multi-modal Optimal Transport Maps

Silver Stepsize for Faster Zeroth-Order Optimization

Unsupervised Trajectory Optimization for 3D Registration in Serial Section Electron Microscopy using Neural ODEs

Measuring And Improving Engagement of Text-to-Image Generation Models

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

Noise Prompt Learning: Learning the Winning Tickets for Diffusion Sampling

tBen: Benchmarking and Testing the Rule-Based Temporal Logic Reasoning Ability of Large Language Models with DatalogMTL

Heterogeneous Federated Learning: A Dual Matching Dataset Distillation Approach