Hello, I'm Zhaochong An

I am a PhD student at the University of Copenhagen, affiliated with the Pioneer Centre for Artificial Intelligence, under the ELLIS program. I am fortunate to be advised by Prof. Serge Belongie. Prior to my PhD, I spent two wonderful years at ETH Zurich supervised by Prof. Luc Van Gool and received the MSc in Computer Science from ETH Zurich in 2023.

My research interests are primarily in multimodality and generative modeling. I have explored a broad range of scenarios within multimodal foundation models and video generation, including image and video analysis/generation, as well as 3D scene understanding. I have previously interned at Google and Meta.

My Email: anzhaochong [at] outlook [dot] com

Google Scholar Github Twitter Linkedin Email
Zhaochong An
University of Copenhagen ETH Zurich Meta Google EPFL University of Oxford

News

  • Jul 2026: I am on the job market now and expect to graduate in Spring 2027. I am open to research scientist roles in industry. Please feel free to reach out via email!
  • Jul 2026: VGGRPO has been accepted to ECCV 2026.
  • May 2026: MODUS has been accepted to ICML 2026.
  • Feb 21, 2026: TUNA, OneStory, Saber, VecGlypher and HiStream have been accepted to CVPR 2026 (4 main, 1 findings).
  • Oct 2025: I start a research scientist internship at Google!
  • Jul 2025: I was invited to give a talk on my research titled "Few-shot 3D Point Cloud Segmentation in the Era of Foundation Models" at INSAIT! Talk slides can be found here.
  • Jun 2025: I start a research scientist internship at Meta!

Selected Publications

* indicates equal contribution. For a full list of publications, please visit my Google Scholar profile.

MODUS: Decoder-only Any-to-Any Modeling of Diverse Modalities

MODUS: Decoder-only Any-to-Any Modeling of Diverse Modalities

Mingqiao Ye*, Zhaochong An*, Zhitong Gao, Xian Liu, Oğuzhan Fatih Kar, Jesse Allardice, Roman Bachmann, David Mizrahi, François Fleuret, Chuan Li, Amir Zadeh, Serge Belongie, Afshin Dehghan, Amir Zamir
ICML 2026
Website Code
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

Zhaochong An, Orest Kupyn, Théo Uscidda, Andrea Colaco, Karan Ahuja, Serge Belongie, Mar Gonzalez-Franco, Marta Tintore Gazulla
ECCV 2026 (work done at Google)
arXiv PDF Project Page
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

Zhaochong An, Menglin Jia, Haonan Qiu, Zijian Zhou, Xiaoke Huang, Zhiheng Liu, Weiming Ren, Kumara Kahatapitiya, Ding Liu, Sen He, Chenyang Zhang, Tao Xiang, Fanny Yang, Serge Belongie, Tian Xie
CVPR 2026 (work done at Meta)
arXiv PDF Project Page
Scaling Zero-Shot Reference-to-Video Generation

Scaling Zero-Shot Reference-to-Video Generation

Zijian Zhou, Shikun Liu, Haozhe Liu, Haonan Qiu, Zhaochong An, Weiming Ren, Zhiheng Liu, Xiaoke Huang, Kam Woh Ng, Tian Xie, Xiao Han, Yuren Cong, Hang Li, Chuyan Zhu, Aditya Patel, Tao Xiang, Sen He
CVPR 2026
arXiv PDF Project Page
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Zhiheng Liu, Weiming Ren, Haozhe Liu, Zijian Zhou, Shoufa Chen, Haonan Qiu, Xiaoke Huang, Zhaochong An, Fanny Yang, Aditya Patel, Viktar Atliha, Tony Ng, Xiao Han, Chuyan Zhu, Chenyang Zhang, Ding Liu, Juan-Manuel Perez-Rua, Sen He, Jürgen Schmidhuber, Wenhu Chen, Ping Luo, Wei Liu, Tao Xiang, Jonas Schult, Yuren Cong
CVPR 2026 Highlight Presentation
arXiv PDF Project Page
What You Have is What You Track: Adaptive and Robust Multimodal Tracking

What You Have is What You Track: Adaptive and Robust Multimodal Tracking

Yuedong Tan, Jiawei Shao, Eduard Zamfir, Ruanjun Li, Zhaochong An, Chao Ma, Danda Paudel, Luc Van Gool, Radu Timofte, Zongwei Wu
ICCV 2025
Code
Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Junlin Han, Ender Konukoglu, Serge Belongie
CVPR 2025
arXiv PDF Code
Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Min Wu, Ming-Ming Cheng, Ender Konukoglu, Serge Belongie
ICLR 2025 Spotlight - Top 5.1% of submitted paper
arXiv PDF Code
DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer

DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer

Runjia Li, Junlin Han, Luke Melas-Kyriazi, Chunyi Sun, Zhaochong An, Zhongrui Gui, Shuyang Sun, Philip Torr, Tomas Jakab
3DV 2025
arXiv PDF Project Page
Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Zhaochong An, Guolei Sun, Yun Liu, Fayao Liu, Zongwei Wu, Dan Wang, Luc Van Gool, Serge Belongie
CVPR 2024
arXiv PDF Code
Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation

Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation

Zhaochong An, Guolei Sun, Zongwei Wu, Hao Tang, Luc Van Gool
BMVC 2023
arXiv PDF Code
Indiscernible Object Counting in Underwater Scenes

Indiscernible Object Counting in Underwater Scenes

Guolei Sun, Zhaochong An, Yun Liu, Ce Liu, Christos Sakaridis, Deng-Ping Fan, Luc Van Gool
CVPR 2023
Code

Experiences

Meta
Research Scientist Intern - Apr. 2026 to Present
Google
Research Scientist Intern - Oct. 2025 to Feb. 2026
Meta
Research Scientist Intern - Jun. 2025 to Sep. 2025

Services

  • Reviewer for CVPR, NeurIPS, ICML, ICLR, ECCV, ICCV, and ACM MM.