Yu Zeng

Researcher, NVIDIA

Joined

July 2019

Names

Yu Zeng

Emails

****@mail.dlut.edu.cn (Confirmed)

****@qq.com (Confirmed)

****@tencent.com (Confirmed)

****@jhu.edu (Confirmed)

****@gmail.com (Confirmed)

****@nvidia.com (Confirmed)

Personal Links

Google Scholar

Semantic Scholar

Career & Education History

Researcher

NVIDIA (nvidia.com)

2024 – Present

PhD student

Johns Hopkins University (jhu.edu)

2021 – 2024

Researcher

Tencent (tencent.com)

2020 – 2021

Intern

Adobe Systems (adobe.com)

2019 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Vishal M. Patel

Present

Expertise

deep learning

Present

image synthesis

Present

image editing

Present

Publications

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
Haotian Xue, Yunhao Ge, Yu Zeng, Max Li, Ming-Yu Liu, Yongxin Chen, Jiaojiao Fan
- Submitted to ICLR 2026
- Readers: Everyone
$PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
Jing Gu, Xian Liu, Yu Zeng, Ashwin Nagarajan, Fangrui Zhu, Daniel Hong, Yue Fan, Qianqi Yan, Kaiwen Zhou, Ming-Yu Liu, Xin Eric Wang
- ICLR 2026 Oral
- Readers: Everyone
Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
Lu Ling, Chen-Hsuan Lin, Tsung-Yi Lin, Yifan Ding, Yu Zeng, Yichen Sheng, Yunhao Ge, Ming-Yu Liu, Aniket Bera, Max Li
- ICLR 2026 Poster
- Readers: Everyone
One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
Zhendong Wang, Max Li, Ajay Mandlekar, Zhenjia Xu, Jiaojiao Fan, Yashraj Narang, Linxi Fan, Yuke Zhu, Yogesh Balaji, Mingyuan Zhou, Ming-Yu Liu, Yu Zeng
- ICML 2025 poster
- Readers: Everyone
Learning Universal Features for Generalizable Image Forgery Localization
Hengrun Zhao, Yunzhi Zhuge, Yifan Wang, Lijun Wang, Huchuan Lu, Yu Zeng
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
Zhendong Wang, Zhaoshuo Li, Ajay Mandlekar, Zhenjia Xu, Jiaojiao Fan, Yashraj Narang, Linxi Fan, Yuke Zhu, Yogesh Balaji, Mingyuan Zhou, Ming-Yu Liu, Yu Zeng
- Submitted to ICLR 2025
- Readers: Everyone
JR2Net: joint monocular 3D face reconstruction and reenactment
Jiaxiang Shang, Yu Zeng, Xin Wang, Runze Zhang, Guangyuan Sun, Vishal M. Patel, Hongbo Fu
- 13 Nov 2023 (modified: 13 Nov 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
SceneComposer: Any-Level Semantic Image Synthesis
Yu Zeng, Zhe Lin, Jianming Zhang, Qing Liu, John Collomosse, Jason Kuen, Vishal M. Patel
- 02 Nov 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Securing Deep Generative Models with Universal Adversarial Signature
Yu Zeng, Mo Zhou, Yuan Xue, Vishal M. Patel
- Submitted to ICLR 2024
- Readers: Everyone
Shape-guided Object Inpainting
Yu Zeng, Zhe Lin, Vishal Patel
- 17 May 2022
- OpenReview Archive Direct Upload
- Readers: Everyone

View all 26 publications

Co-Authors

View all 98 co-authors