Shudong Liu (刘树东)

Hi! I am currently a PhD candidate of Computer Science in Department of Computer and Information Science and Faculty of Science and Technology at University of Macau beginning from 2022 Fall, also a member of NLP²CT Lab advised by Prof. Derek F. Wong.
Recently, I also work as a research intern at Moonshot AI, Shanghai AI Lab and Microsoft Research Asia. I am broadly interested in natural language processing and machine learning. My research is currently focused on cooking up Coding Agents that actually work, building out the pipeline around them, from scalable post-training to evaluation.
🌟 I am currently on the job market!

Research Interests

Scalable Training and Evaluation Methods for LLMs and Coding Agents

• Developing reliable and robust evaluation methods for LLMs
• Exploring scalable data-centric training pipelines (SFT & RL)
• Building general and generative reward models and systems
• Shipping the full pipeline as Coding Agents, especially for WebDev

Recent Publications (* denotes equal contribution)

• Kimi K2.6: Advancing Open-Source Coding
  Shudong Liu as a contributor in Kimi RL(Coding Agents) Team.
  In Technical Blog. [Models] [X]
• Kimi K2.5: Visual Agentic Intelligence
  Shudong Liu as a contributor in Kimi RL(Coding Agents) Team.
  In Technical Report. [Models] [X] (Top-1 in Design Arena; Top-1 open model in Code Arena)
• Intern-S1: A Scientific Multimodal Foundation Model.
  Shudong Liu as a contributor in Intern-S1 Team.
  In Technical Report. [Project] [Models] (CompassVerifier for RL Reward Models)
• From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG.
  Guanhua Chen, Chuyue Huang, Yutong Yao, Shudong Liu, Xueqing Song, Lidia S. Chao, Derek F. Wong.
  In ACL 2026 Findings.
• Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA.
  Guanhua Chen, Yutong Yao, Shenghe Sun, CI-JUN GAO, Shudong Liu, Lidia S. Chao, Feng Wan, Derek F. Wong.
  In ACL 2026 Findings.
• CompassVerifier: A Unified and Robust Answer Verifier for LLMs Evaluation and Outcome Reward.
  Shudong Liu*, Hongwei Liu*, Junnan Liu, Songyang Gao, Chengqi Lyu, Yuzhe Gu, Wenwei Zhang, Derek F. Wong, Songyang Zhang, Kai Chen.
  In EMNLP 2025. [Project] [Dataset] (Top 1% Score in ARR May 2025)
• Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist.
  Zihao Zhou*, Shudong Liu*, Maizhen Ning, Wei Liu, Jindong Wang, Derek F. Wong, Xiaowei Huang, Qiufeng Wang, Kaizhu Huang.
  In ICLR 2025. [Project]
• CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries.
  Shudong Liu, Yiqiao Jin, Cheng Li, Derek F. Wong, Qingsong Wen, Lichao Sun, Haipeng Chen, Xing Xie, Jindong Wang.
  In Preprint. [Project]
• DeepResearch RewardBench: Evaluating Reward Models for Deep Research Report.
  Shudong Liu, Zhongyuting, Guanhua Chen, Xinyi Yang, Lidia S. Chao, Jiaheng Liu, Derek F. Wong.
  In Preprint.
• Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models.
  Rui Wang, Hongru Wang, Boyang Xue, Jianhui Pang, Shudong Liu, Yi Chen, Jiahao Qiu, Derek Fai Wong, Heng Ji, Kam-Fai Wong.
  In Preprint. [Project]
• Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner
  Shudong Liu, Zhaocong Li, Xuebo Liu, Runzhe Zhan, Derek F. Wong, Lidia S. Chao, Min Zhang.
  In EMNLP 2024.
• Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation.
  Zhexuan Wang*, Shudong Liu*, Xuebo Liu, Miao Zhang, Derek F. Wong, and Min Zhang.
  In ACL 2024 Findings.
• kNN-TL: k-Nearest-Neighbor Transfer Learning for Low-Resource Neural Machine Translation.
  Shudong Liu, Xuebo Liu, Derek F. Wong, Zhaocong Li, Wenxiang Jiao, Lidia S. Chao and Min Zhang.
  In ACL 2023.
• Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization.
  Chi Seng Cheang, Hou Pong Chan, Derek F. Wong, Xuebo Liu, Zhaocong Li, Yanming Sun, Shudong Liu, Lidia S. Chao.
  In EMNLP 2023.
• A Graph Attention Interactive Refine Framework with Contextual Regularization for Jointing Intent Detection and Slot Filling.
  Zhanbiao Zhu, Peijie Huang, Haojing Huang, Shudong Liu and Leyi Lao.
  In ICASSP 2022.
• Cross-domain Slot Filling with Distinct Slot Entity and Type Prediction.
  Shudong Liu, Peijie Huang, Zhanbiao Zhu, Hualin Zhang and Jianying Tan.
  In NLPCC 2021. (Oral)

Experience

• Moonshot AI 2025.12 - present
  Research Intern. Team: Coding Agents and RL; Project: Kimi K2.5 and Kimi K2.6.
• Shanghai AI Lab 2025.01 - 2025.11
  Research Intern. Team: LLM Center; Project: OpenCompass (7k+ Github Stars) and Intern-S1.
• Microsoft Research 2024.05 - 2024.12
  Research Intern. Mentor: Prof. Jindong Wang.

Services

• Website Chair: COLING 2027
• Web and App Chair: AACL 2026
• Webmaster Chair: NLPCC 2026
• OpenReview Co-Chair: NLPCC 2024
• PC Member / Reviewer: NeurIPS; ICML; ICLR; ACL ARR (ACL, EMNLP, NAACL, EACL); TASLP
• Student Volunteer: EMNLP 2024; MT Summit 2023
• Teaching Assistant
  • CISC7021 Applied Natural Language Processing (2022-2025 Fall)
  • CISC4000 Graduation Project (2023 Spring)
  • CISC7203 Database and Data Mining Technologies (2024 Spring)

Selected Awards & Talks

• 2025.01, Be awarded the Stars of Tomorrow at Microsoft Research Asia
• 2024.11, Be recognized as an Outstanding Reviewer at EMNLP 2024
• 2024.02, Invited talk Transfer Learning for Low-Resource NMT at University of Toronto (Online)

Education

• Ph.D. student in Computer Science, University of Macau, Macau SAR
  2022 - present. Advised by Prof. Derek F. Wong and collaborated with Prof. Xuebo Liu
• B.E. in Software Engineering, South China Agricultural University, Guangzhou, China
  2018 - 2022.