I am a fourth-year PhD student in the School of Computer Science at Peking University, advised by Prof. Zongqing Lu. I received my Bachelor’s degree in 2021 from the School of Information Science and Technology at PKU.
My research interests lie in Multimodal Large Language Models (MLLMs), Embodied Artificial Intelligence, and Reinforcement Learning. In particular, I focus on vision-language understanding and generation, vision-language-action (VLA) modeling, and LLM-based autonomous agents.
🔥 News
- 2025.06: 🎉🎉 Two papers accepted by ICCV 2025.
- 2025.01: 🎉🎉 One paper accepted by ICLR 2025.
📝 Publications
Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos.
Hao Luo†, Yicheng Feng†, Wanpeng Zhang†, Sipeng Zheng†, Ye Wang, Haoqi Yuan, Jiazheng Liu, Chaoyi Xu, Qin Jin, Zongqing Lu
†: equal contribution
arxiv preprint
[Paper][PDF][Website][Code][Huggingface]
VideoOrion: Tokenizing Object Dynamics in Videos.
Yicheng Feng†, Yijiang Li†, Wanpeng Zhang, Hao Luo, Zihao Yue, Sipeng Zheng, Zongqing Lu
†: equal contribution
International Conference on Computer Vision, ICCV 2025
Unified Multimodal Understanding via Byte-Pair Visual Encoding.
Wanpeng Zhang, Yicheng Feng, Hao Luo, Yijiang Li, Zihao Yue, Sipeng Zheng, Zongqing Lu
International Conference on Computer Vision, ICCV 2025
From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities.
Wanpeng Zhang, Zilong Xie, Yicheng Feng, Yijiang Li, Xingrun Xing, Sipeng Zheng, Zongqing Lu
International Conference on Learning Representations, ICLR 2025
Unicode: Learning a unified codebook for multimodal large language models.
Sipeng Zheng, Bohan Zhou, Yicheng Feng, Ye Wang, Zongqing Lu
European Conference on Computer Vision, ECCV 2024
LLaMA Rider: Spurring Large Language Models to Explore the OpenWorld.
Yicheng Feng, Yuxuan Wang, Jiazheng Liu, Sipeng Zheng, Zongqing Lu
Findings of the Association for Computational Linguistics, NAACL 2024
Steve-eye: Equipping llm-based embodied agents with visual perception in open worlds.
Sipeng Zheng, Jiazheng Liu, Yicheng Feng, Zongqing Lu
International Conference on Learning Representations, ICLR 2024
Learning Multi-Object Positional Relationships via Emergent Communication.
Yicheng Feng†, Boshi An†, Zongqing Lu
†: equal contribution
The Association for the Advancement of Artificial Intelligence, AAAI 2024
Multi-Agent Language Learning: Symbolic Mapping.
Yicheng Feng, Zongqing Lu
Findings of the Association for Computational Linguistics: ACL 2023
🎖 Honors and Awards
- 2024.12 Outstanding Research Award, Peking University
- 2021.06 Outstanding Graduate Award, Peking University
- 2020.09 Merit Student Award, Peking University
- 2019.09 Huawei Scholarship, Peking University
- 2019.09 Merit Student Award, Peking University
- 2018.09 Academic Progress Award, Peking University
📖 Educations
- 2021.09 - Present: Ph.D. in Computer Science, Peking University
- 2017.09 - 2021.06: B.Sc. in Intelligent Science and Technology, Peking University
💻 Internships
- 2025.08 - Present, ByteDance Seed Multimodal Understanding & Generation Models
- 2025.03 - 2025.08, BeingBeyond Multimodal LLMs / Embodied AI
- 2023.03 - 2025.03, Beijing Academy of Artificial Intelligence (BAAI) Multimodal LLMs / Embodied AI