Scholar
Sheng Liu
Google Scholar ID: rzhzR-cAAAAJ
Stanford University
Citations & Impact
Citations
3,111
H-index
23
i10-index
34
Publications
20
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- 1. Organized a workshop on AI and healthcare at ICCV 2025 in Hawaii.
- 2. Co-authored work on trainable multi-agent system is now online and has received over 900 stars on GitHub.
- 3. Serving as an Area Chair for ICLR 2026.
- 4. Co-authored work on revealing neurocognitive and behavioral patterns by unsupervised manifold learning from dynamic brain data is accepted at Nature Computational Science.
- 5. Paper on investigating reasoning and hallucination of MLLMs is accepted at NeurIPS 2025.
- 6. Invited talks at Symposium on AI Medicine at Stanford University.
- 7. Invited talks at National University of Singapore, University of Macau, Hong Kong University, and Hong Kong University of Science and Technology.
- 8. Serving as an Area Chair for NeurIPS 2025.
- 9. Serving as an Area Chair for ACML 2025.
- 10. Serving as the Local Chair for Conference on Parsimony and Learning (CPAL 2025).
- 11. OctoTools is accepted by KnowledgeNLP 2025, Foundation Models in the Wild, Reasoning and Planning for LLMs workshops at ICLR 2025.
- 12. Agentic framework for tool usage OctoTools is online now, with demo and GitHub code.
- 13. TextGrad is accepted by Nature.
- 14. Paper on reducing hallucinations in VLM via latent space steering is accepted at ICLR 2025 as a Spotlight paper.
- 15. Paper on theoretically evaluating the data reconstruction problem is accepted at AISTATS 2025.
- 16. Large-scale multimodal dataset for medicine MedTrinity-25M is accepted at ICLR 2025.
- 17. Guest lecture at UC Santa Cruz by Prof. Yuyin Zhou.
- 18. Invited talk at UIUC NLP Talk seminar by Prof. Heng Ji.
- 19. Co-organizing the GenAI for Healthcare workshop at NeurIPS 2024.
- 20. Paper on Training-Free Guidance for Diffusion Models is accepted at NeurIPS 2024 as a spotlight.
- 21. Paper on LLMs in scientific papers is accepted at COLM 2024.
- 22. Paper on AI-guided radiotherapy treatment planning is awarded Best in Medical Physics Award by American Association of Physicists in Medicine (AAPM 2024).
- 23. Introduced TextGrad: Automatic 'Differentiation' via Text, optimizing prompts in LLM systems.
- 24. Paper on In-Context Vector: making ICL more effective and controllable is accepted at ICML 2024.
Research Experience
- Postdoctoral Researcher at Stanford University, collaborating with Prof. James Zou and Prof. Lei Xing. Research focuses on developing machine learning methods with theoretical foundations to enable AI to move from rigid tools to reliable, collaborative partners, with an emphasis on robustness, inference-time steering, and agency, particularly in the context of disease and healthcare.
Education
- PhD in Data Science from New York University
Background
- Postdoctoral Researcher at Stanford University, working with Prof. James Zou and Prof. Lei Xing. Research interests include developing machine learning methods with theoretical foundations, particularly their applications in disease and healthcare. Personal interests include tennis, scuba diving, and surfing.
Miscellany
- Loves playing tennis, certified scuba diver, and surfer.
