|
Zilong Wang I am a Research Scientist at Google DeepMind. I completed my Ph.D. in Computer Science at UC San Diego in 2025, advised by Professor Jingbo Shang. Before that, I received my B.S. in Computer Science from Peking University in 2019, where I worked with Professor Xiaojun Wan. My research focuses on building effective and reliable LLM agents for code generation. If you'd like to discuss research—or just chat—feel free to reach out at zlwang.ucsd at gmail dot com . |
|
PublicationsSome papers are highlighted. |
|
A Tale of LLMs and Induced Small Proxies: Scalable Agents for Knowledge Mining
Sipeng Zhang, Longfei Yun, Zilong Wang, Jingbo Shang, Letian Peng Preprint, 2025 arXiv |
|
[Adaptive weighting for multi-objective RL, achiving SOTA for all rewards] Learning to Optimize Multi-objective Alignment through Dynamic Reward WeightingYining Lu, Zilong Wang**, Shiyang Li, Xin Liu, Changlong Yu, Qingyu Yin, Zhan Shi, Zixuan Zhang, Meng Jiang (** corresponding author) Preprint, 2025 arXiv |
|
[Build effective & reliable coding LLMs with hybrid rewards: program analysis + unit tests] Training Language Models to Generate Quality Code with Program Analysis FeedbackFeng Yao*, Zilong Wang*, Liyuan Liu, Junxia Cui, Li Zhong, Xiaohan Fu, Haohui Mai, Vish Krishnan, Jianfeng Gao, Jingbo Shang (* equal contribution) NeurIPS, 2025 arXiv / code |
|
[Rising-reward trajectory mining for efficient process-reward data collection] RRO: LLM Agent Optimization Through Rising Reward TrajectoriesZilong Wang, Jingfeng Yang, Sreyashi Nag, Samarth Varshney, Xianfeng Tang, Haoming Jiang, Jingbo Shang, Sheikh Muhammad Sarwar COLM, 2025 arXiv |
|
TableRAG: Million-Token Table Understanding with Language Models
Si-An Chen, Lesly Miculicich, Julian Martin Eisenschlos, Zifeng Wang, Zilong Wang, Yanfei Chen, Yasuhisa Fujii, Hsuan-Tien Lin, Chen-Yu Lee, Tomas Pfister NeurIPS, 2024 arXiv |
|
OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
Zilong Wang, Yuedong Cui, Li Zhong, Zimin Zhang, Da Yin, Bill Yuchen Lin, Jingbo Shang Preprint, 2024 arXiv |
|
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Zilong Wang, Zifeng Wang, Long Le, Huaixiu Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, Chen-Yu Lee, Tomas Pfister ICLR, 2025 arXiv / featured: Google Research Blog |
|
[Runtime-verified, stepwise reasoning (via execution trace) for precise LLM-based code debugging] Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
Li Zhong, Zilong Wang, Jingbo Shang (** corresponding author) ACL Findings, 2024 arXiv / code / featured: MarkTechPost / talk: BAAI / sota: HumanEval 98.2% |
|
Answer is All You Need: Instruction-following Text Embedding via Answering the Question
Letian Peng, Yuwei Zhang, Zilong Wang, Jayanth Srinivasa, Gaowen Liu, Zihan Wang, Jingbo Shang NAACL, 2024 arXiv / code |
|
[Iterative table transformation powering the first tabular reasoning agent] Chain-of-Table: Evolving Tables in the Reasoning Chain for Table UnderstandingZilong Wang, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos, Vincent Perot, Zifeng Wang, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Chen-Yu Lee, Tomas Pfister ICLR, 2024 arXiv / code / featured: Google Research Blog |
|
LMDX: Language Model-based Document Information Extraction and Localization
Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Jiaqi Mu, Hao Zhang, Nan Hua ACL Findings, 2024 arXiv |
|
[Real-world API reliability evaluation of coding LLMs at scale (LLM wasn't as good as StackOverflow at least in 2024)] Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code GenerationLi Zhong, Zilong Wang AAAI, 2024 arXiv / code / featured: TheRegister |
|
Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation
Prashant Krishnan, Zilong Wang, Yangkun Wang, Jingbo Shang COLING, 2024 arXiv |
|
Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path
Zilong Wang, Jingbo Shang EMNLP Findings, 2023 arXiv |
|
VRDU: A Benchmark for Visually-rich Document Understanding
Zilong Wang, Yichao Zhou, Wei Wei, Chen-Yu Lee, Sandeep Tata KDD, 2023 arXiv / code / dataset |
|
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Zilong Wang, Jiuxiang Gu, Chris Tensmeyer, Nikolaos Barmpalios, Ani Nenkova, Tong Sun, Jingbo Shang, Vlad I. Morariu EMNLP, 2022 arXiv |
|
Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
Zilong Wang, Jingbo Shang ACL Findings, 2022 arXiv / code |
|
LayoutReader: Pre-training of Text and Layout for Reading Order Detection
Zilong Wang, Yiheng Xu, Lei Cui, Jingbo Shang, Furu Wei EMNLP, 2021 arXiv / code |
|
DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding
Zilong Wang, Mingjie Zhan, Xuebo Liu, Ding Liang EMNLP Findings, 2020 arXiv |
|
Exploring Semantic Capacity of Terms
Jie Huang*, Zilong Wang*, Kevin Chang, Wen-Mei Hwu, Jinjun Xiong (* equal contribution) EMNLP, 2020 arXiv |
|
TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis
Zilong Wang, Zhaohong Wan, Xiaojun Wan WWW, 2020 arXiv |
|
Last updated: November 2025 | Template by Jon Barron |