Zihao Lin
Portrait of Zihao Lin

Zihao Lin

Ph.D. Student in Computer Science · University of California, Davis

Scholar GitHub LinkedIn Email CV
1k+ Total citations 400+ First / corresponding-author citations 14 h-index

Google Scholar, Oct 2026

I am a fourth-year Ph.D. student in Computer Science at the University of California, Davis, advised by Prof. Lifu Huang. My research aims to build multimodal agents that can perceive, reason, and act in complex real-world environments, and that keep improving themselves from their own experience.

My work spans multimodal agents for video and document tasks; self-evolving agents and agent harnesses; multimodal reasoning and reasoning-driven generation; and applications of these systems in medicine and personalization. I have spent time as a research scientist intern at Meta and Adobe Research, and I serve as an Area Chair for ACL ARR.

Before UC Davis, I received my M.S. in Electrical & Computer Engineering from Duke University (2022) and my B.S. in Financial Mathematics from the Southern University of Science and Technology (2019).

I am always happy to collaborate. Feel free to reach out at qzlin@ucdavis.edu or zihao.lin.0123@gmail.com.

Research Interests

02

Self-Evolving Agents

Agents and agent harnesses that keep improving themselves from their own experience, through recursive self-improvement, branch-based optimization, and continual knowledge updates.

VideoHarness-SRSIPreprint MoSIBPreprint

First- or corresponding-author work

News

Publications

* equal contribution  ·  † corresponding author

2026

  1. Preprint
    Confident First, Reflective Second: Reinforcement Learning of Confidence-Preserving Reflection for Video Understanding
    Zihao Lin, Jingyuan Liu, Yucheng Zhang, Yuguang Yao, Lifu Huang
    arXiv preprint, 2026
    arXiv
  2. Preprint
    VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
    Zihao Lin, Haoyu Dong, Haobo Xu, Chi-Chih Chang, Xuying Ning, Yinglong Xia, Shuang Yang, Zhuokai Zhao, Xinying Song, Dongfang Liu, Lifu Huang, Yang Song, Qifan Wang
    arXiv preprint, 2026
    arXiv
  3. Preprint
    MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows
    Ruoxin Wang, Yuanting Pan, Binxu Li, Ruiyang Ji, Yaqian Chen, Jiayuan Ding, Qifan Wang, Lifu Huang, Mingjie Li, Yu Zhang, Ehsan Adeli, Kilian Pohl, Zhe Xu, Zihao Lin†, Haoyu Dong†, Yixin Wang†
    arXiv preprint, 2026
    arXiv
  4. Preprint
    Mixture of Self-Improving Branches For Agent Harness Optimization
    Haoyu Dong, Yuhang Zhou, Zihao Lin, Yifan Wu, Bo Peng, Mingyi Wang, Xiangjun Fan, Lizhu Zhang, Zhuokai Zhao
    arXiv preprint, 2026
    arXiv
  5. Preprint
    VideoGen-Agent: Reinforcing Video Generation Agents
    Binxu Li, Haoyi Duan, Yuhui Zhang, Yaohui Zhang, Zihao Lin, Kaituo Feng, Suozhi Huang, Xiangyi Li, Yu Li, Chunyuan Li, Shilong Liu, Mengdi Wang
    arXiv preprint, 2026
    arXiv
  6. ECCV'26
    UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
    Lin Zhang, Sicheng Mo, Zefan Cai, Jinhong Lin, Zihao Lin, Jiuxiang Gu, Krishna Kumar Singh, Yuheng Li, Yin Li
    ECCV 2026
    arXiv
  7. MM'26
    GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
    Zihao Lin, Haibo Wang, Zhiyang Xu, Siyao Dai, Huanjie Dong, Xiaohan Wang, Yolo Y. Tang, Yixin Wang, Qifan Wang, Lifu Huang
    ACM Multimedia (ACMMM) 2026
    arXiv
  8. MM'26
    Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding
    Muyang Zheng, Tong Zhou, Geyang Wu, Zihao Lin, Haibo Wang, Lifu Huang
    ACM Multimedia (ACMMM) 2026
    arXiv
  9. EMNLP'26
    Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding
    Haibo Wang, Zihao Lin, Zhiyang Xu, Lifu Huang
    EMNLP 2026
    arXiv
  10. TMLR'26
    MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing
    Zihao Lin, Wanrong Zhu, Jiuxiang Gu, Jihyung Kil, Christopher Tensmeyer, Lin Zhang, Shilong Liu, Ruiyi Zhang, Lifu Huang, Vlad I. Morariu, Tong Sun
    TMLR 2026 Spotlight, NeurIPS 2025 Workshop on Multimodal Algorithmic Reasoning
    arXiv
  11. EACL'26
    A Survey on LLM-based Conversational User Simulation
    Bo Ni, Leyao Wang, Yu Wang, Branislav Kveton, Franck Dernoncourt, ..., Zihao Lin, ..., Tyler Derr, Ryan A. Rossi
    EACL 2026
    arXiv
  12. IEEE ToN
    Decentralized Partial Model Personalization With Guaranteed Nonconvex Convergence
    Yifan Shi, Yingqi Liu, Yan Sun, Zihao Lin, Xueqian Wang, Li Shen, Dacheng Tao
    IEEE Transactions on Networking, 2026
    arXiv
  13. AACL'26
    SuperFlow: Training Flow Matching Models with RL on the Fly
    Kaijie Chen, Zhiyang Xu, Ying Shen, Zihao Lin, Yuguang Yao, Lifu Huang
    AACL 2026
    arXiv

2025

  1. EMNLP'25
    R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation
    Kaijie Chen, Zihao Lin, Zhiyang Xu, Ying Shen, Yuguang Yao, Joy Rimchala, Jiaxin Zhang, Lifu Huang
    EMNLP 2025 Oral, Outstanding Paper Award Nominee
    arXiv
  2. NeurIPS'25
    Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals
    Roy Xie, Junlin Wang, Paul Rosu, Chunyuan Deng, Bolun Sun, Zihao Lin, Bhuwan Dhingra
    NeurIPS 2025
    arXiv
  3. NeurIPS'25
    Localizing Knowledge in Diffusion Transformers
    Arman Zarei, Samyadeep Basu, Keivan Rezaei, Zihao Lin, Sayan Nag, Soheil Feizi
    NeurIPS 2025
    arXiv
  4. Preprint
    A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models
    Zihao Lin, Samyadeep Basu, Mohammad Beigi, Varun Manjunatha, Ryan A. Rossi, Zichao Wang, Yufan Zhou, ..., Soheil Feizi, Lifu Huang
    arXiv preprint, 2025
    arXiv
  5. ICCVW'25
    RoRA-VLM: Robust Retrieval-Augmented Vision Language Models
    Jingyuan Qi, Zhiyang Xu, Rulin Shao, Zihao Lin, Yang Chen, Jin Di, Yu Cheng, Qifan Wang, Lifu Huang
    ICCV 2025 Workshop on Knowledge-Intensive Multimodal Reasoning
    arXiv
  6. NAACL'25
    Persona-SQ: A Personalized Suggested Question Generation Framework For Real-world Documents
    Zihao Lin, Zichao Wang, Yuanting Pan, Varun Manjunatha, Ryan Rossi, Angela Lau, Lifu Huang, Tong Sun
    NAACL 2025 (System Demonstrations)
    arXiv

2024

  1. EMNLP'24
    MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
    Binxu Li, Tiankai Yan, Yuanting Pan, Jie Luo, Ruiyang Ji, Jiayuan Ding, Zhe Xu, Shilong Liu, Haoyu Dong, Zihao Lin†, Yixin Wang†
    Findings of EMNLP 2024
    PaperarXivCode
  2. EMNLP'24
    ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models
    Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana
    EMNLP 2024
    arXiv
  3. EMNLP'24
    Holistic Evaluation for Interleaved Text-and-Image Generation
    Minqian Liu, Zhiyang Xu, Zihao Lin, Trevor Ashby, Joy Rimchala, Jiaxin Zhang, Lifu Huang
    EMNLP 2024
    arXiv
  4. EMNLP'24
    InternalInspector: Robust Confidence Estimation in LLMs through Internal States
    Mohammad Beigi, Ying Shen, Runing Yang, Zihao Lin, Qifan Wang, Ankith Mohan, Jianfeng He, Ming Jin, Chang-Tien Lu, Lifu Huang
    Findings of EMNLP 2024
    arXiv
  5. Preprint
    Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
    Mohammad Beigi, Sijia Wang, Ying Shen, Zihao Lin, Adithya Kulkarni, Jianfeng He, Feng Chen, Ming Jin, Jin-Hee Cho, Dawei Zhou, Chang-Tien Lu, Lifu Huang
    arXiv preprint, 2024
    arXiv
  6. ACL'24
    Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models
    Zihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou, Yuxiang Zhang, Qifan Wang, Wenpeng Yin, Lifu Huang
    ACL 2024
    PaperarXiv
  7. Neurocomputing
    Trust It or Not: Confidence-Guided Automatic Radiology Report Generation
    Zihao Lin*, Yixin Wang*, Zhe Xu, Haoyu Dong, Jiang Tian, Jie Luo, Zhongchao Shi, Lifu Huang, Yang Zhang, Jianping Fan, Zhiqiang He
    Neurocomputing, 2024
    arXiv

2023

  1. Preprint
    Efficient Federated Prompt Tuning for Black-Box Large Pre-trained Models
    Zihao Lin, Yan Sun, Yifan Shi, Xueqian Wang, Lifu Huang, Li Shen, Dacheng Tao
    arXiv preprint, 2023
    arXiv
  2. ICMLW'23
    Rethinking Medical Report Generation: Disease Revealing Enhancement with Knowledge Graph
    Zihao Lin*, Yixin Wang*, Haoyu Dong*
    ICML 2023 Workshop on Interpretable Machine Learning in Healthcare (IMLH)
    arXiv
  3. Preprint
    Prompt Tuning based Adapter for Vision-Language Model Adaption
    Jingchen Sun, Jiayu Qin, Zihao Lin, Changyou Chen
    arXiv preprint, 2023
    arXiv

2021

  1. MICCAI'21
    ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
    Yixin Wang, Yang Zhang, Yang Liu, Zihao Lin, Jiang Tian, Cheng Zhong, Zhongchao Shi, Jianping Fan, Zhiqiang He
    MICCAI 2021
    PaperarXivCode

Experience

Education

Service

Area Chair for ACL ARR (2026). Reviewer for ACL ARR (2024–2026), EMNLP (2024–2026), ICLR (2025–2026), NAACL (2025–2026), COLM (2025–2026), AAAI (2026), ECCV (2026), and WWW (2026).