Picture for Di Wang

Di Wang

refer to the report for detailed contributions

CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale

Add code
Jul 09, 2025
Viaarxiv icon

FlashDP: Private Training Large Language Models with Efficient DP-SGD

Add code
Jul 01, 2025
Viaarxiv icon

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs

Add code
Jun 24, 2025
Viaarxiv icon

A Unified Graph-based Framework for Scalable 3D Tree Reconstruction and Non-Destructive Biomass Estimation from Point Clouds

Add code
Jun 18, 2025
Viaarxiv icon

Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Add code
Jun 18, 2025
Viaarxiv icon

The Compositional Architecture of Regret in Large Language Models

Add code
Jun 18, 2025
Viaarxiv icon

OneRec Technical Report

Add code
Jun 16, 2025
Viaarxiv icon

Intra-Trajectory Consistency for Reward Modeling

Add code
Jun 10, 2025
Viaarxiv icon

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs

Add code
Jun 08, 2025
Viaarxiv icon

Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment

Add code
Jun 08, 2025
Viaarxiv icon