Scholar
Minkai Xu
Google Scholar ID: fKuiInUAAAAJ
Stanford University
Citations & Impact
Citations
4,032
H-index
26
i10-index
40
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- 1. CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers (ICCV, 2025)
- 2. Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems (Foundations and Trends® in Machine Learning, 2025)
- 3. Smooth Interpolation for Improved Discrete Graph Generative Models (ICML, 2025)
- 4. f-PO: Generalized Preference Optimization with f-divergence Minimization (AISTATS, 2025)
- 5. RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation (AISTATS, 2025)
- 6. Energy-Based Diffusion Language Models for Text Generation (ICLR, 2025)
- 7. TabDiff: a Multi-Modal Diffusion Model for Tabular Data Generation (ICLR, 2025)
- 8. SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights (ICLR, 2025)
- 9. Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization (NeurIPS, 2024)
- 10. Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models (NeurIPS, 2024)
- 11. MADiff: Offline Multi-agent Learning with Diffusion Models (NeurIPS, 2024)
- 12. RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models (NeurIPS, 2024)
- 13. TFG: Unified Training-Free Guidance for Diffusion Models (NeurIPS, 2024)
Research Experience
- Worked at AI research labs of Nvidia, Meta, Amazon, and ByteDance.
Education
- 1. Ph.D. candidate at Stanford Computer Science, advisors: Stefano Ermon and Jure Leskovec
- 2. M.S. from MILA, advisor: Jian Tang
- 3. B.S. (Summa Cum Laude) from SJTU, advisor: Weinan Zhang
Background
- Research Interest: Scalable machine learning, with an emphasis on generative models. Interested in developing generative methods for various real-world problems, from language, vision, to science.
Miscellany
- Personal interests and hobbies not mentioned
