Zilong Zheng

Email: z.zheng[at]ucla[dot]edu

zilong.JPG

I received my Ph.D. degree (21’) from the Department of Computer Science at University of California, Los Angeles (UCLA). My research interests lie in the intersection of statistical machine learning, natural language processing and cognition. Current research themes include:

  • Trustworthy AI: Crafting faithful, interpretable and trustworthy AI frameworks.
  • Human-like Conversational Agents: Building interactive models that align with human values and social norms.
  • Efficient Language Models: Efficient training and inference of long-context language models.
  • Generative Modeling: Statistical generative modeling (e.g. EBMs, diffusions) on high-dimensional data.

I am always looking for self-motivated students and long-term collaborators. Please contact me if you have excellent background or share similar research interests with me.

NEWS

Jun, 2025 In-context Value Alignment and Navi2Gaze are accepted to IROS’25 for Oral Presentations!
May, 2025 I will be serving as Senior Area Chair for EMNLP.
May, 2025 :fire: Three papers on bidirectional LLM Encoder, ReflectEvo (Meta Reflection Learning) and Causal Value Steering are accepted to ACL’25! One paper on combinational creativity in VLMs is accepted to CogSci’25 for Oral presentation! Congratulations to Ziyong, Jiaqi, Yipeng and Yongqian!
May, 2025 :fire: Three papers on TokenSwift (long sequence acceleration), ToEdit (LLM model collapse) and MCU (open-ended agent evaluation) are accepted to ICML’25! MCU is awarded as Spotlight Poster! Congratulations to Tong, Xuekai and Xinyue!
Mar, 2025 OmniMMI is accepted to CVPR’25 :fire:. We devised the first-ever benchmark for streaming interactive Omni understanding. Please try your models on OmniMMI Leaderboard.
Jan, 2025 Three papers on in-context knowledge editing, multimodal knowledge editing and in-context alignment are accepted to ICLR’25! :sparkles: :smile:
Dec, 2024 I will co-host 1st workshop on Large Language Models and Structure Modeling. Stay tuned :fire:.
Dec, 2024 Diver-CT is accepted to AAAI’25. Congratulations to Andrew!
Sep, 2024 Two papers on long context window extension and situated inductive reasoning are accepted to NeurIPS’24. Congratulations to Tong and Xiaojuan!
Sep, 2024 Two papers on video understanding and sentence representation are accepted to EMNLP’24 Main. Congratulations to Yuxuan and Ziyong!
Jul, 2024 One paper on ToM for dialogue modeling is accepted for an Oral presentation at SIGDial’24. Congratulations to Shuwen!
Jul, 2024 One paper on compositional visual reasoning is accepted to CoLM’24. Congratulations to Yuxuan!
Apr, 2024 Four papers are accepted to ACL’24 with 2 Main conference and 2 Findings.
Jan, 2024 One paper is accepted to NAACL’24. Congratulations to Steven Gong.
Oct, 2023 One short paper on DocumentRE is accepted to EMNLP’23.

selected publications

SEE ALL PUBLICATIONS
  1. Xuekai Zhu, Daixuan Cheng, Hengli Li, Kaiyan Zhang, Ermo Hua, Xingtai Lv, Ning Ding, Zhouhan Lin#, Zilong Zheng#, and Bowen Zhou#, in ICML, 2025.
  2. Xinyue Zheng*, Haowei Lin*, Kaichen He, Zihao Wang, Zilong Zheng#, and Yitao Liang#, in ICML, 2025.
  3. Tong Wu, Junzhe Shen, Zixia Jia, Yuxuan Wang, and Zilong Zheng#, in ICML, 2025.
    GitHub Repo stars
  4. Yuxuan Wang, Yueqian Wang, Bo Chen, Tong Wu, Dongyan Zhao, and Zilong Zheng#, in CVPR, 2025.
  5. Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng#, and Gao Huang#, Preprint, 2025.
    GitHub Repo stars
  6. Yang Liu, Jiaqi Li, and Zilong Zheng#, Preprint, 2025.
  7. Hengli Li, Chenxi Li, Tong Wu, Xuekai Zhu, Yuxuan Wang, Zhaoxin Yu, Eric Hanchen Jiang, Song-Chun Zhu, Zixia Jia, Ying Nian Wu#, and Zilong Zheng#, Preprint, 2025.
  8. Tong Wu, Yanpeng Zhao, and Zilong Zheng#, in NeurIPS, 2024.
  9. Patchwise Generative ConvNet: Training Energy-Based Models from a Single Natural Image for Internal Learning CVPR'21 Oral
    Zilong Zheng, Jianwen Xie, and Ping Li, in CVPR, 2021.
  10. Reasoning Visual Dialogs with Structural and Partial Observations CVPR'19 Oral
    Zilong Zheng*, Wenguan Wang*, Siyuan Qi*, and Song-Chun Zhu, in CVPR, 2019.
  11. Learning Descriptor Networks for 3D Shape Synthesis and Analysis CVPR'18 Oral
    Jianwen Xie*, Zilong Zheng*, Ruiqi Gao, Wenguan Wang, Song-Chun Zhu, and Ying Nian Wu, in CVPR, 2018.