Zhenhailong Wang 王镇海龙

I obtained my Ph.D. in Computer Science from the University of Illinois Urbana-Champaign (UIUC) in May 2026, advised by Prof. Heng Ji, closely working with Prof. Shih-Fu Chang, Mohit Bansal, Dilek Hakkani-Tur and Manling Li. In 2027, I will join Westlake University as an Assistant Professor. I previously earned my M.S. in Computer Science and Civil Engineering at UIUC, and my B.S. at Zhejiang University.

My research focuses on building large multimodal models (LMMs) and developing multimodal agents with human-like perception and predictive-thinking. I am a recipient of the 2025 Amazon AICE PhD Fellowship and have published 30+ papers at top-tier venues including NeurIPS, ICLR, ACL, NAACL, EMNLP, and AAAI—among them a Spotlight at NeurIPS 2023 and an Oral at the NeurIPS 2025 SEA Workshop. Seven of these papers have each accumulated over 100 citations. My representative work includes VidIL, Paxion, Solo Performance Prompting, Mobile-Agent-E, and PAPO. I have previously interned at Tencent AI Lab, Microsoft Research Asia, Salesforce AI, and Amazon Alexa AI. I also closely collaborated with Alibaba Tongyi Lab.

For my most recent work, please check out my Google Scholar.

Affiliations & Experience

News

Selected Publications

• Multimodal Policy Internalization for Conversational Agents [Project Page]
  Zhenhailong Wang, Jiateng Liu, Amin Fazel, Ritesh Sarkhel, Xing Fan, Xiang Li, Chenlei Guo, Heng Ji, Ruhi Sarikaya
  ICLR 2026

• Perception-Aware Policy Optimization for Multimodal Reasoning [Project Page]
  Zhenhailong Wang*, Xuehang Guo*, Sofia Stoica, Haiyang Xu, Hongru Wang, Hyeonjeong Ha, Xiusi Chen, Yangyi Chen, Ming Yan, Fei Huang, Heng Ji
  ICLR 2026

• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [Project Page]
  Zhenhailong Wang*, Senthil Purushwalkam*, Caiming Xiong, Silvio Savarese, Heng Ji, Ran Xu
  NeurIPS 2025

• Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks [Paper] [Project Page]
  Zhenhailong Wang, Haiyang Xu, Junyang Wang, Xi Zhang, Ming Yan, Ji Zhang, Fei Huang, Heng Ji
  NeurIPS 2025 SEA Workshop (Oral)

• MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents [Paper][Code]
  Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Xiangru Tang, Heng Ji, Jiaxuan You
  ACL 2025 Main

• Infogent: An Agent-Based Framework for Web Information Aggregation [Paper] [Project Page]
  Revanth Gangi Reddy*, Sagnik Mukherjee*, Jeonghwan Kim*, Zhenhailong Wang*, Dilek Hakkani-Tur, Heng Ji
  NAACL 2025 Findings

• Visually Descriptive Language Model for Vector Graphics Reasoning [Paper] [Project Page]
  Zhenhailong Wang, Joy Hsu, Xingyao Wang, Kuan-Hao Huang, Manling Li, Jiajun Wu, Heng Ji
  TMLR; CVPR 2025 MAR Workshop (Spotlight)

• Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning [Paper] [Project Page]
  Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi R. Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji
  ACL 2024 Findings

• Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration [Paper] [Code]
  Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji
  NAACL 2024 main

• Paxion: Patching Action Knowledge in Video-Language Foundation Models [Paper] [Code]
  Zhenhailong Wang, Ansel Blume, Sha Li, Genglin Liu, Jaemin Cho, Zineng Tang, Mohit Bansal, Heng Ji
  NeurIPS 2023 (Spotlight)

• RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought [Paper]
  Tianci Xue, Ziqi Wang, Zhenhailong Wang, Chi Han, Pengfei Yu, Heng Ji
  arXiv:2305.11499

• Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks [Paper] [Code]
  Zhenhailong Wang, Xiaoman Pan, Dian Yu, Dong Yu, Jianshu Chen, Heng Ji
  ACL 2023 Findings

• A Language First Approach for Procedural Planning [Paper]
  Jiateng Liu, Sha Li, Zhenhailong Wang, Manling Li and Heng Ji
  ACL 2023 Findings

• Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners [Paper][Video] [Code]
  Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Derek Hoiem, Shih-Fu Chang, Mohit Bansal, Heng Ji
  NeurIPS 2022

• NewsClaims: A New Benchmark for Claim Detection from News with Background Knowledge [Paper] [Code]
  Revanth Gangi Reddy, Sai Chetan, Zhenhailong Wang, Yi R. Fung, Kathryn Conger, Ahmed Elsayed, Martha Palmer, Preslav Nakov, Eduard Hovy, Kevin Small, Heng Ji
  EMNLP 2022 main

• Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification [PDF] [Code]
  Zhenhailong Wang, Heng Ji
  AAAI 2022

• The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction [Paper] [Code]
  Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han and Clare Voss
  EMNLP 2021 main

Education

• University of Illinois at Urbana-Champaign
  • Ph.D. in Computer Science, 2023 - 2026; Advisor: Prof. Heng Ji
  • M.S. in Computer Science, 2021 - 2023; Advisor: Prof. Heng Ji
  • M.S. in Civil Engineering, 2019 - 2021; Advisor: Prof. Mani Golparvar-Fard
• Zhejiang University
  • B.S. in Civil Engineering, 2016 - 2020

Experience

• 05/2025 - 08/2025, Amazon Alexa AI
  • Applied Scientist Intern
• 06/2024 - 01/2025, Salesforce AI Research
  • Research Intern
• 05/2023 - 08/2023, Microsoft Research Asia
  • Research Intern
• 05/2022 - 08/2022, Tencent AI Lab
  • Research Intern
• 07/2020 - 06/2026, BLENDER Lab
  • Graduate Research Assistant
• 09/2019 - 08/2020, RAAMAC Lab
  • Undergraduate Research Assistant