Hongyang Du 杜泓洋
Logo Master's Student

Hi, I am Hongyang Du — a Sc.M. student in Computer Science at Brown University advised by Randall Balestriero. Currently I am collaborating with Yue Wang at the USC Physical SuperIntelligence Lab. I previously obtained my B.S. in Computer Science and Mathematics from the University of Maryland, College Park. My research explores how Self-Supervised Learning can build World Models for Robotic Control. I focus on extracting spatiotemporal and 3D-aware priors to capture physical dynamics and how to create a scalable loop that couples causal prediction and action prediction.

Outside of research, I am an amateur powerlifter 💪 and a pro drummer 🥁; I am a Jazz cat and prog metalhead — think Chick Corea meets Animals as Leaders. Also, I live with a cat named Dingzhen(丁真)🐱, who keeps me grounded.


Education
  • Brown University
    Brown University
    Department of Computer Science
    Master's Student
    Aug. 2025 - present
  • University of Maryland, College Park
    University of Maryland, College Park
    B.S. in Computer Science and Mathematics
    Aug. 2021 - May. 2025
Honors & Awards
  • Robert Ma Scholarship Recipent
    2024
  • Break Thhrough Tech Scholarship Recipent
    2021
News
2026
🏆 VideoGPA won 🥉 place in eBay sponsored Image-to-Video Consistent Generation Challenge!
Jun 04
🌴 Joined Adobe in San Jose to research Self-Evolving Agentic Image Gen!
May 26
🎉 Paper on VideoGPA accepted to ICML 2026!
Apr 30
2025
🎉 Paper on Video INR Compression accepted to WACV 2026!
Nov 11
🎉 Paper on VideoHallu accepted to NeurIPS 2025!
Sep 18
🐻 Starting the Sc.M. Computer Science Program at Brown University in Fall 2025
Sep 01
🐢 Graduated from University of Maryland, College Park with Bachelor’s in Computer Science (Honors) and Minor in Mathematics!
May 21
🎉 Paper on VLM Survey accepted to CVPR Workshop 2025 as Oral presentation!
Apr 08
2024
🐱 found me in the wild!
Jun 14
🤖 Joining iFLYTEK, as a Machine Learning Engineer Intern on Agriculture MLLM Team.
May 30
Selected Publications (view all )
Vision & Geometric Representation
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

Hongyang Du*, Junjie Ye*, Xiaoyan Cong*, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang (* equal contribution)

ICML 2026, CVPR Workshop 2026 Oral

TL;DR: VideoGPA uses a geometry foundation model to mine preference pairs for DPO, nudging video diffusion toward 3D-consistent motion without hand-labeled human preferences. CVPR VGBE Challenge 🥉

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

Hongyang Du*, Junjie Ye*, Xiaoyan Cong*, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang (* equal contribution)

ICML 2026, CVPR Workshop 2026 Oral

TL;DR: VideoGPA uses a geometry foundation model to mine preference pairs for DPO, nudging video diffusion toward 3D-consistent motion without hand-labeled human preferences. CVPR VGBE Challenge 🥉

How to Design and Train Your Implicit Neural Representation for Video Compression
How to Design and Train Your Implicit Neural Representation for Video Compression

Matthew Gwilliam, Roy Zhang, Namitha Padmanabhan, Hongyang Du, Abhinav Shrivastava

WACV 2026

TL;DR: We dissect NeRV-style video INRs in a library, propose Rabbit NeRV (RNeRV) as a strong recipe under equal training budget, then use hyper-networks + weight masking to speed encoding while keeping quality competitive.

How to Design and Train Your Implicit Neural Representation for Video Compression

Matthew Gwilliam, Roy Zhang, Namitha Padmanabhan, Hongyang Du, Abhinav Shrivastava

WACV 2026

TL;DR: We dissect NeRV-style video INRs in a library, propose Rabbit NeRV (RNeRV) as a strong recipe under equal training budget, then use hyper-networks + weight masking to speed encoding while keeping quality competitive.

Ipelets for the Convex Polygonal Geometry
Ipelets for the Convex Polygonal Geometry

Nithin Parepally, Ainesh Chatterjee, Auguste Gezalyan, Hongyang Du, Sukrit Mangla, Kenny Wu, Sarah Hwang, David Mount

40th International Symposium on Computational Geometry (SoCG) 2024

TL;DR: New Ipelets for the Ipe editor that draw and explore convex polygonal geometry—Funk/Hilbert metric balls, polar bodies, enclosing balls, MSTs, and polygon utilities (union, intersection, Minkowski sum).

Ipelets for the Convex Polygonal Geometry

Nithin Parepally, Ainesh Chatterjee, Auguste Gezalyan, Hongyang Du, Sukrit Mangla, Kenny Wu, Sarah Hwang, David Mount

40th International Symposium on Computational Geometry (SoCG) 2024

TL;DR: New Ipelets for the Ipe editor that draw and explore convex polygonal geometry—Funk/Hilbert metric balls, polar bodies, enclosing balls, MSTs, and polygon utilities (union, intersection, Minkowski sum).

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

Dawei Liu*, Zongxia Li*, Hongyang Du, Xiyang Wu, Shihang Gui, Yongbei Kuang, Lichao Sun (* equal contribution)

ACM CAIS Workshop 2026

TL;DR: Graph of Skills (GoS): offline skill dependency graph + inference-time retrieval (seeding + PageRank + token budget) so agents load a small, relevant skill bundle instead of the whole library—higher reward, fewer tokens.

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

Dawei Liu*, Zongxia Li*, Hongyang Du, Xiyang Wu, Shihang Gui, Yongbei Kuang, Lichao Sun (* equal contribution)

ACM CAIS Workshop 2026

TL;DR: Graph of Skills (GoS): offline skill dependency graph + inference-time retrieval (seeding + PageRank + token budget) so agents load a small, relevant skill bundle instead of the whole library—higher reward, fewer tokens.

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

Zongxia Li*, Hongyang Du*, Chengsong Huang*, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, Xiaomin Wu, Zhichao Liu, Jiarui Zhang, Fuxiao Liu (* equal contribution)

Preprint 2026

TL;DR: MM-Zero trains one base VLM in three roles—Proposer, Coder (code-to-image), Solver—with GRPO and rich rewards, achieving self-evolution on multimodal reasoning without any seed images.

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

Zongxia Li*, Hongyang Du*, Chengsong Huang*, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, Xiaomin Wu, Zhichao Liu, Jiarui Zhang, Fuxiao Liu (* equal contribution)

Preprint 2026

TL;DR: MM-Zero trains one base VLM in three roles—Proposer, Coder (code-to-image), Solver—with GRPO and rich rewards, achieving self-evolution on multimodal reasoning without any seed images.

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

Zongxia Li*, Xiyang Wu*, Yubin Qin, Hongyang Du, Guangyao Shi, Dinesh Manocha, Tianyi Zhou, Jordan Lee Boyd-Graber (* equal contribution)

NeurIPS 2025

TL;DR: VideoHallu: benchmark of synthetic videos (e.g. from frontier generators) with QA that exposes commonsense and physics failures; we show strong MLLMs still struggle and that GRPO fine-tuning (with counterexamples) helps.

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

Zongxia Li*, Xiyang Wu*, Yubin Qin, Hongyang Du, Guangyao Shi, Dinesh Manocha, Tianyi Zhou, Jordan Lee Boyd-Graber (* equal contribution)

NeurIPS 2025

TL;DR: VideoHallu: benchmark of synthetic videos (e.g. from frontier generators) with QA that exposes commonsense and physics failures; we show strong MLLMs still struggle and that GRPO fine-tuning (with counterexamples) helps.

All publications