Zilong Zheng

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

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:

  • Human AI Alignment: Building interactive models that align with human values and social norms.
  • Long-context 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 interns and long-term collaborators. Please contact me if you have excellent background or share similar research interests with me.

News

2024/09 Two papers on long context window extension and situated inductive reasoning are accepted to NeurIPS’24. Congratulations to Tong and Xiaojuan!
2024/09 Two papers on video understanding and sentence representation are accepted to EMNLP’24 Main. Congratulations to Yuxuan and Ziyong!
2024/07 One paper on ToM for dialogue modeling is accepted for an Oral presentation at SIGDial’24. Congratulations to Shuwen!
2024/07 One paper on compositional visual reasoning is accepted to CoLM’24. Congratulations to Yuxuan!
2024/04 Four papers are accepted to ACL’24 with 2 Main conference and 2 Findings.

Selected Publications

*: Equal contribution, : Corresponding author
  1. Mars: Situated Inductive Reasoning in an Open-World Environment NeurIPS'24
    Xiaojuan Tang, Jiaqi Li, Yitao Liang, Muhan Zhang, and Zilong Zheng, in NeurIPS D&B Track, 2024.
  2. Never Miss A Beat: An Efficient Recipe for Context Window Extension of Large Language Models with Consistent “Middle” Enhancement NeurIPS'24
    Tong Wu, Yanpeng Zhao, and Zilong Zheng, in NeurIPS, 2024.
  3. Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge for Long Video Understanding EMNLP'24
    Yuxuan Wang, Yueqian Wang, Pengfei Wu, Jianxin Liang, Dongyan Zhao, Yang Liu, and Zilong Zheng, in EMNLP, 2024.
  4. Varying Sentence Representations via Condition-Specified Routers EMNLP'24
    Ziyong Lin, Quansen Wang, Zixia Jia, and Zilong Zheng, in EMNLP, 2024.
  5. ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning CoLM'24
    Yuxuan Wang, Alan Yuille, Zhuowan Li, and Zilong Zheng, in CoLM, 2024.
  6. LooGLE: Can Long-Context Language Models Understand Long Contexts? ACL'24
    Jiaqi Li, Mengmeng Wang, Zilong Zheng, and Muhan Zhang, in ACL, 2024.
  7. LangSuit⋅E: Controlling, Planning, and Interacting with Large Language Models in Embodied Text Environments ACL'24
    Zixia Jia, Mengmeng Wang, Baichen Tong, Song-Chun Zhu, and Zilong Zheng, in ACL Findings, 2024. (also in SpLU-RoboNLP Workshop at ACL 2024)
  8. Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels ACL'24
    Zixia Jia, Junpeng Li, Shichuan Zhang, and Zilong Zheng, in ACL, 2024.
  9. Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers
    Chao Lou, Zixia Jia, Zilong Zheng, and Kewei Tu.
  10. In-Context Editing: Learning Knowledge from Self-Induced Distributions
    Siyuan Qi, Bangcheng Yang, Kailin Jiang, Xiaobo Wang, Jiaqi Li, Yifan Zhong, Yaodong Yang, and Zilong Zheng.
  11. DiveR-CT: Diversity-enhanced Red Teaming with Relaxing Constraints
    Andrew Zhao, Quentin Xu, Matthieu Liu, Shenzhi Wang, Yong-jin Liu, Zilong Zheng, and Gao Huang.
  12. In situ bidirectional human-robot value alignment ScienceRobotics
    Luyao Yuan*, Xiaofeng Gao*, Zilong Zheng*, Mark Edmonds, Ying Nian Wu, Federico Rossano, Hongjing Lu, Yixin Zhu, and Song-Chun Zhu, Science Robotics, 2022.
  13. Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling Oral ICLR'22
    Bo Wan, Wenjuan Han, Zilong Zheng, and Tinne Tuytelaars, in ICLR, 2022.
  14. Patchwise Generative ConvNet: Training Energy-Based Models from a Single Natural Image for Internal Learning Oral CVPR'21
    Zilong Zheng, Jianwen Xie, and Ping Li, in CVPR, 2021.
  15. Reasoning Visual Dialogs with Structural and Partial Observations Oral CVPR'19
    Zilong Zheng*, Wenguan Wang*, Siyuan Qi*, and Song-Chun Zhu, in CVPR, 2019.
  16. Learning Descriptor Networks for 3D Shape Synthesis and Analysis Oral CVPR'18
    Jianwen Xie*, Zilong Zheng*, Ruiqi Gao, Wenguan Wang, Song-Chun Zhu, and Ying Nian Wu, in CVPR, 2018.

Professional Services

  • Conference reviewer for ICML 2022-2023; ICLR 2022-2023; CVPR 2019-2022; NeurIPS 2020-2022; AAAI 2020-2022; ICCV 2019-2023; ECCV 2020-2022; BMVC 2020; WACV 2021
  • Journal reviewer for International Journal of Computer Vision (IJCV), Pattern Recognition (PR), Neurocomputing