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.
",
which does not match the baseurl ("") configured in _config.yml.
baseurl in _config.yml to "".
GoS and MM-Zero accepted to EMNLP 2026 Main Conference!VideoGPA won 🥉 place in
sponsored Image-to-Video Consistent Generation Challenge!
in San Jose to research Self-Evolving Agentic Image Gen!VideoGPA accepted to ICML 2026!Video INR Compression accepted to WACV 2026!VideoHallu accepted to NeurIPS 2025!Brown University in Fall 2025University of Maryland, College Park with Bachelor’s in Computer Science (Honors) and Minor in Mathematics!VLM Survey accepted to CVPR Workshop 2025 as Oral presentation!
Jingcheng Ni, Zekun Li, Zhiyang Dou, Xiaoyan Cong, Ziyao Zeng, Hongyang Du, Randall Balestriero, Taku Komura, Srinath Sridhar
arXiv 2026
TL;DR: Generating human motion in real time as spatial audio arrives.
Jingcheng Ni, Zekun Li, Zhiyang Dou, Xiaoyan Cong, Ziyao Zeng, Hongyang Du, Randall Balestriero, Taku Komura, Srinath Sridhar
arXiv 2026
TL;DR: Generating human motion in real time as spatial audio arrives.

Hongyang Du, Yunfei Xie, Junjie Ye, Jiawei Yang, Xiaoyan Cong, Haodong Zhang, Yongchao Huang, Haiyu Wu, Zongxia Li, Shihang Gui, Dawei Liu, Runhao Li, Jingcheng Ni, Chen Wei, Randall Balestriero, Yue Wang
arXiv 2026 #1 HuggingFace Daily Paper
TL;DR: A very simple regularization can mitigate the reconstruction-generation gap.
Hongyang Du, Yunfei Xie, Junjie Ye, Jiawei Yang, Xiaoyan Cong, Haodong Zhang, Yongchao Huang, Haiyu Wu, Zongxia Li, Shihang Gui, Dawei Liu, Runhao Li, Jingcheng Ni, Chen Wei, Randall Balestriero, Yue Wang
arXiv 2026 #1 HuggingFace Daily Paper
TL;DR: A very simple regularization can mitigate the reconstruction-generation gap.

Hongyang Du, Lan Yan, Christian Flores, Asim Kadav
NeurIPS 2026 Workshop CLEA Oral
TL;DR: A design agent that keeps learning new skills from real users without retraining.
Hongyang Du, Lan Yan, Christian Flores, Asim Kadav
NeurIPS 2026 Workshop CLEA Oral
TL;DR: A design agent that keeps learning new skills from real users without retraining.

Dawei Liu*, Zongxia Li*, Hongyang Du, Xiyang Wu, Shihang Gui, Yongbei Kuang, Lichao Sun
EMNLP 2026
TL;DR: Helping AI agents find just the skills they need from a huge skill library.
Dawei Liu*, Zongxia Li*, Hongyang Du, Xiyang Wu, Shihang Gui, Yongbei Kuang, Lichao Sun
EMNLP 2026
TL;DR: Helping AI agents find just the skills they need from a huge skill library.

Zongxia Li*, Hongyang Du*, Chengsong Huang*, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, Xiaomin Wu, Zhichao Liu, Jiarui Zhang, Fuxiao Liu
EMNLP 2026
TL;DR: A vision-language model that improves itself without any training data.
Zongxia Li*, Hongyang Du*, Chengsong Huang*, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, Xiaomin Wu, Zhichao Liu, Jiarui Zhang, Fuxiao Liu
EMNLP 2026
TL;DR: A vision-language model that improves itself without any training data.

Hongyang Du*, Junjie Ye*, Xiaoyan Cong*, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang
ICML 2026 CVPR VGBE Challenge 🏆 Oral
TL;DR: Using 3D geometry knowledge to make generated videos more 3D-consistent.
Hongyang Du*, Junjie Ye*, Xiaoyan Cong*, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang
ICML 2026 CVPR VGBE Challenge 🏆 Oral
TL;DR: Using 3D geometry knowledge to make generated videos more 3D-consistent.

Matthew Gwilliam, Roy Zhang, Namitha Padmanabhan, Hongyang Du, Abhinav Shrivastava
WACV 2026
TL;DR: A practical guide to designing and training neural networks that compress videos.
Matthew Gwilliam, Roy Zhang, Namitha Padmanabhan, Hongyang Du, Abhinav Shrivastava
WACV 2026
TL;DR: A practical guide to designing and training neural networks that compress videos.

Zongxia Li*, Xiyang Wu*, Yubin Qin, Hongyang Du, Guangyao Shi, Dinesh Manocha, Tianyi Zhou, Jordan Lee Boyd-Graber
NeurIPS 2025
TL;DR: A benchmark showing that AI models still miss obvious errors in AI-generated videos.
Zongxia Li*, Xiyang Wu*, Yubin Qin, Hongyang Du, Guangyao Shi, Dinesh Manocha, Tianyi Zhou, Jordan Lee Boyd-Graber
NeurIPS 2025
TL;DR: A benchmark showing that AI models still miss obvious errors in AI-generated videos.

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 Ipe plugins for drawing and exploring convex polygon 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 Ipe plugins for drawing and exploring convex polygon geometry.