Zhenhao Zhang

Video Generation & Multimodal

Email Google Scholar GitHub

About

I am an Incoming PhD Student at the Department of Automation, Tsinghua University supervised by Prof. Yebin Liu.

I am now working at Tencent IEG as a Qingyun Program Intern(腾讯青云计划) from October 2026 on Video Generation Post-training. Before that, I worked at Kling Team, Kuaishou Technology as an intern from June 2026 to October 2026 on Video Generation Post-training. I worked as a Research Intern at Tsinghua University from October 2025 to October 2026 on Video Generation Post-training. I worked at Signalplus as an Intern from June 2025 to August 2025 on Agentic Quant Trading.

My research interests span Video Generation, Multimodal LLMs, and their applications in 3D vision and Embodied AI. I actively seek collaborations and friends. Feel free to contact me if you are interested in any of these areas.

我正在广泛的寻找科研合作与工业界实习机会，如果您对此感兴趣，欢迎与我联系!

News

  1. Joined Tencent IEG as an intern (Qingyun Program).

  2. OR-Expert accepted by ACM Multimedia 2026.

  3. DAG accepted by ECCV 2026.

  4. Joined Kling Team, Kuaishou Technology as an intern.

  5. UniHM accepted by ICLR 2026.

  6. SDEval accepted by AAAI 2026.

  7. Joined Tsinghua University as a research intern.

  8. OpenHOI accepted by NeurIPS 2025 as an Oral.

  9. Joined SignalPlus as an intern.

  10. QVPO accepted by NeurIPS 2024.

Publications

DAG research preview ECCV 2026

ECCV 2026 Poster

Diffusion Models are Open-World Affordance Learners

Hanqing Wang*, Zhenhao Zhang*, Kaiyang Ji*, Mingyu Liu, Wenti Yin, Yuchao Chen, Zhirui Liu, Xiangyu Zeng, Tianxiang Gui, Hangxing Zhang, Jiahao Yuan, Zhiqing Cui, Jiaxin Liu, Zhiyuan Ma†, Hui Xiong†

Paper ↗Project ↗Code ↗
OR-Expert research preview ACM MM 2026

ACM Multimedia 2026 Poster

Generalizable Operating Room Expert with Multimodal Enhancement

Peiqi He*, Zhenhao Zhang*‡, Yixiang Zhang, Jiaxin Liu, Xiongjun Zhao†, Shaoliang Peng†

Paper ↗
SDEval research preview AAAI 2026

AAAI 2026 Poster

SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models

Hanqing Wang, Yuan Tian, Mingyu Liu, Zhenhao Zhang, Xiangyang Zhu†

Paper ↗Code ↗
QVPO research preview NeurIPS 2024

NeurIPS 2024 Poster

Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization

Shutong Ding, Ke Hu, Zhenhao Zhang, Kan Ren, Weinan Zhang, Jingyi Yu, Jingya Wang, Ye Shi†

Paper ↗Project ↗Code ↗

Experience

Tencent logo

Tencent IEG

Video Generation Post-training

Qingyun Program

Kling Team, Kuaishou Technology

Video Generation Post-training

Department of Video Model

Finish Gnomon4D

Tsinghua University logo

Tsinghua University

Video Generation Post-training.

Signalplus logo

Signalplus Singapore

Agentic Quant Trading

Honors

  • 2026.5ICML Gold Reviewer, ICML Foundation
  • 2025.10NeurIPS Scholar Award, Neural Information Processing Foundation
  • 2022.06Finalist, America Mathematics Contest in Modeling

Academic service

  • Journal reviewerTMLR
  • Conference reviewerNeurIPS, ICLR, ICML, AAAI, CoRL, AISTATS