Hongyang Du

Hongyang-Du

8 1

https://hongyang-du.github.io/

AI & ML interests

Representation Learning, Explicit/Implicit World Model, Self-supervised Learning

Recent Activity

upvoted a paper 22 days ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

upvoted a paper about 2 months ago

A Cookbook of 3D Vision: Data, Learning Paradigms, and Application

upvoted a paper 3 months ago

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

View all activity

Organizations

None yet

upvoted a paper 22 days ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published 26 days ago • 76

upvoted a paper about 2 months ago

A Cookbook of 3D Vision: Data, Learning Paradigms, and Application

Paper • 2606.04291 • Published Jun 2 • 5

upvoted a paper 3 months ago

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

Paper • 2601.23286 • Published Jan 30 • 1

upvoted a paper 4 months ago

Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Paper • 2604.05333 • Published Apr 7 • 24

upvoted a paper 5 months ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published Mar 10 • 54

upvoted a paper 9 months ago

First Frame Is the Place to Go for Video Content Customization

Paper • 2511.15700 • Published Nov 19, 2025 • 54

upvoted a paper 10 months ago

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos

Paper • 2505.01481 • Published May 2, 2025 • 4

upvoted a paper 11 months ago

Self-Rewarding Vision-Language Model via Reasoning Decomposition

Paper • 2508.19652 • Published Aug 27, 2025 • 85