Dingjie Song

I am a Ph.D. student in Computer Science and Engineering at Lehigh University, advised by Prof. Lichao Sun, and currently a summer research intern at Salesforce AI Research in Palo Alto. Previously a research assistant at the CUHK-Shenzhen NLP group with Dr. Benyou Wang; M.E. from Nanjing University.

My research is in Large Language Models and Natural Language Processing, currently focused on LLM agents 🤖 and AI for scientific discovery 🔬 — building agents that learn and self-evolve in open-ended environments, and AI systems that automate and accelerate the research process end-to-end. This builds on my earlier work making multimodal and medical LLMs efficient, robust, and trustworthy. My work spans:

• LLM Agents: [OpenSkill], [Agentic Robot]
• AI Scientist & Scientific Discovery: [Dr. Claw 🦞], [AutoResearch AI], [Medical AI Scientist]
• Multimodal LLM: [COLM 2024], [COLING 2025], [NAACL 2025], [ACL 2025], [EMNLP Findings 2025, ICML 2025 DIG-BUG Workshop Oral], [EMNLP Findings 2025], [ScratchMath]
• Medical LLM: [NAACL 2024], [COLM 2024], [MICCAI 2025], [KDD 2026]

Updates

Selected Publications

Google Scholar  ·  See all publications →

LLM Agents

• OpenSkill: Open-World Self-Evolution for LLM Agents
  Zhiling Yan*, Dingjie Song*, Hanrong Zhang, Wei Liang, Yuxuan Zhang, Yutong Dai, Lifang He, Philip S. Yu, Ran Xu, Xiang Li, Lichao Sun
  arXiv, Under Review, project page, code
  

AI Scientist & Scientific Discovery

• Dr. Claw 🦞: A Full-Stack AI Research Workspace
  “A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.” — carries a project from idea to publication, with structured pipelines, multi-agent support (Claude Code, Gemini CLI, Codex, OpenRouter), and 100+ built-in research skills.
    🌐 Website · GitHub · 📰 Featured by Lehigh Engineering
  

• Towards a Medical AI Scientist
  Hongtao Wu*, Boyun Zheng*, Dingjie Song*, Yu Jiang, Jianfeng Gao, Lei Xing, Lichao Sun, Yixuan Yuan
  arXiv, Under Review
  

Multimodal LLM

• Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination
  Dingjie Song*, Sicheng Lai*, Mingxuan Wang, Shunian Chen, Lichao Sun, Benyou Wang
  EMNLP Findings 2025, ICML 2025 DIG-BUG Workshop Oral, project page
  

• LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
  Xidong Wang*, Dingjie Song*, Shunian Chen, Chen Zhang, Benyou Wang
  EMNLP Findings 2025, project page, code and data
  

• Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
  Dingjie Song, Wenjun Wang, Shunian Chen, Xidong Wang, Michael Guan, Benyou Wang
  COLING 2025, code and model
  

• MileBench: Benchmarking MLLMs in Long Context
  Dingjie Song, Shunian Chen, Guiming Hardy Chen, Fei Yu, Xiang Wan, Benyou Wang
  COLM 2024, project page, code and data
  

→ Browse the full list of publications

Awards

• Outstanding Graduate Student, Nanjing University, 2022
• Yingcai Scholarship, Nanjing University, 2022
• Renmin Scholarship (People’s Scholarship), Nanjing University, 2018-2021

Services

• Conference reviewer: EMNLP, ACL Rolling Review