I am a first-year Ph.D. student in Computer Science at University of Illinois Urbana-Champaign (UIUC), under the supervision of Prof. Jiawei Han.
Before this, I received my Bachelor’s degree (2017-2021, computer science), Master’s degree (2021-2024, computer science) from Shandong University and Xiamen University, respectively. I also worked as researcher at DAMO Academy, Alibaba Group from August, 2024 to June, 2025.
🤔 Currently, my research interests are primarily focused on Large Language Models (LLMs), covering the following topics:
- Knowledge-Augmented LLMs allow LLMs to make full use of external knowledge to solve real-world problems.
- LLM-Agent that creates interfaces to help LLMs and humans communicate, interact, and exchange knowledge. I believe all these questions are fundamental for bridging the gap between LLMs and human intelligence, and their solutions will play significant roles in implementing a knowledge-centric AI.
- Reinforcement Learning that can train the model without human knowledge and even beyond human performance.
- Large-Vision Language Models (LVLMs) that enables LVLMs to better understand images, comprehend user intent, and mitigate hallucination issues.
🤝 Looking for collaboration! If you are interested in working with me with any topics, please drop me an email.
🙌🏻 I am actively seeking Summer 2026 Internship!
🔥 News
- 2026.01: 🎉🎉 One paper (GRACE) is accepted by ICLR 2026! See you in Brazil!
- 2025.07: 🎉🎉 One paper (DynamicRAG) is accepted by NeurIPS 2025! See you in San Diego!
- 2025.08: 🎉🎉 Join UIUC!
- 2025.07: 🎉🎉 One paper (CaReVL) is accepted by ACMM 2025!
- 2025.06: 🎉🎉 One paper (Multimodal Textbook) is accepted by ICCV 2025!
- 2024.11: 🎉🎉 One paper (MVP) is accepted by COLING 2025!
- 2024.09: 🎉🎉 One paper (ConflictBank) is accepted by NeurIPS 2024 Track Datasets and Benchmarks!
- 2024.09: 🎉🎉 One paper (SURf) is accepted by EMNLP 2024!
- 2024.08: 🎉🎉 Starting a new position as Research Engineer at DAMO Academy, Alibaba Group!
- 2024.03: 🎉🎉 Two papers (Iter-CoT, Guide-Align) are accepted by NAACL 2024!
- 2024.02: 🎉🎉 One paper (APOLLO) is accepted by COLING 2024!
- 2024.02: 🎉🎉 One paper (Think-on-Graph) is accepted by ICLR 2024!
📝 Publications 
-
ICLR 2024Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph, Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M. Ni, Heung-Yeung Shum, Jian Guo. -
COLING 2024APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning, Jiashuo Sun, Hang Zhang, Chen Lin, Yeyun Gong, Jian Guo, Nan Duan. -
NAACL 2024 FindingsEnhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models, Jiashuo Sun, Yi Luo, Yeyun Gong, Chen Lin, Yelong Shen, Jian Guo, Nan Duan. -
EMNLP 2024SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information, Jiashuo Sun, Jihai Zhang, Chengyu Zhou, Zhaochen Su, Xiaoye Qu, Yu Cheng -
COLING 2025Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning, Xiaoye Qu, Jiashuo Sun, Wei Wei, Daizong Liu, Jianfeng Dong, Yong Deng, Weitao Zheng, Yu Cheng -
NAACL 2024Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models, Yi Luo, Zhenghao Lin, Yuhao Zhang, Jiashuo Sun, Chen Lin, Chengjin Xu, Xiangdong Su, Yelong Shen, Jian Guo, Yeyun Gong. -
NeurIPS 2024 Track Datasets and BenchmarksConflictBank: A Benchmark for Evaluating Knowledge Conflicts in Large Language Models, Zhaochen Su, Jun Zhang, Xiaoye Qu, Tong Zhu, Yanshu Li, Jiashuo Sun, Juntao Li, Min Zhang, Yu Cheng. -
TOMM 2025Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation, Xiaoye Qu, Qiyuan Chen, Wei wei, Jiashuo Sun, Jianfeng Dong. -
ICCV 20252.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining, Wenqi Zhang, Hang Zhang, Xin Li, Jiashuo Sun, Yongliang Shen, Weiming Lu, Deli Zhao, Yueting Zhuang, Lidong Bing -
ACMM 2025From Captions to Rewards (CaReVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models, Muzhi Dai, Jiashuo Sun, Zhiyuan Zhao, Shixuan Liu, Rui Li, Junyu Gao, Xuelong Li -
NeurIPS 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation, Jiashuo Sun, Xianrui Zhong, Sizhe Zhou, Jiawei Han -
ICLR 2026GRACE: Generative Representation Learning via Contrastive Policy Optimization, Jiashuo Sun, Shixuan Liu, Zhaochen Su, Xianrui Zhong, Pengcheng Jiang, Bowen Jin, Peiran Li, Weijia Shi, Jiawei Han -
Submission to ICML 2026Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency, Zhikai Wang, Jiashuo Sun, Wenqi Zhang, Zhiqiang Hu, Xin Li, Fan Wang, Deli Zhao -
Submission to KDD 2026Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning , Junlin Wu, Xianrui Zhong, Jiashuo Sun, Bolian Li, Bowen Jin, Jiawei Han, Qingkai Zeng -
Submission to ICML 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation, Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang, Jiajun Fan,…, Jiaxin Huang, Ge Liu, Heng Ji, Jiawei Han Agent SurveyAdaptation of Agentic AI, Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi,…, Jiashuo Sun, Chaoqi Yang, Kun Qian, Tian Wang,…, Jimeng Sun, Jiawei HanSubmission to ICML 2026Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs, Pengrui Han, Xueqiang Xu, Keyang Xuan, Peiyang Song, Siru Ouyang, Runchu Tian, Yuqing Jiang, Cheng Qian, Pengcheng Jiang, Jiashuo Sun, Junxia Cui, Ming Zhong, Ge Liu, Jiawei Han, Jiaxuan YouSubmission to KDD 2026TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation, Jiashuo Sun, Yixuan Xie, Jimeng Shi, Shaowen Wang, Jiawei HanSubmission to ICML 2026BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature, Peiran Li, Fangzhou Lin, Shuo Xing, Xiang Zheng, Xi Hong, Siyuan Yang, Jiashuo Sun, Zhengzhong Tu, Chaoqun NiSubmission to ICML 2026Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents, Peiran Li, Jiashuo Sun, Fangzhou Lin, Shuo Xing, Tianfu Fu, Suofei Feng, Chaoqun Ni, Zhengzhong Tu
👨💻 Open-Source Projects
-
NanoRAG: Simple implementation of Retrieval-Augmented Generation System
-
PiXiu: Instruct-tuning Large Language Models with Chinese Financial Knowledge Graph
🎖 Honors and Awards
- 2022.11 FinQA Competition Leaderboard Rank 1
- 2022.11 ConvFinQA Competition Leaderboard Rank 1
📖 Educations
- 2025.08 - Present, Ph.D. in Computer Science, University of Illinois Urbana-Champaign.
- 2021.09 - 2024.06, M.S. in Computer Science, Xiamen University.
- 2017.09 - 2021.06, B.S. in Computer Science, Shandong University.
💁 Volunteer
- Area Chair: ARR, ACL, EMNLP
- Conference Reviewer: ARR, ICLR, NeurIPS, ACL, EMNLP, ICCV, NAACL, ACMM, TKDE
- 2022.09 - 2023.03, Object Oriented Programming (2022 Fall) Teaching Assistant
💻 Internships and Work Experiences
- 2024.08 - Present, DAMO Academy, Alibaba Group, Research Engineer
- 2023.04 - 2023.12, International Digital Economy Academy Fin-AI Group, Research Intern
- 2022.09 - 2023.04, Microsoft Research Asia NLC Group, Research Assitant
🎨 Miscellaneous
- I am an amateur singer 🎤 and have won the Top Ten Singer Award at Xiamen University twice (you can check out my competition videos at this). I also enjoy playing instruments, such as the piano 🎹 and guitar 🎸. When I’m not coding, I love listening to music and making music (R&B is my favourite).
- If you have similar interests or would like to connect with me, feel free to email me anytime!