Scholar
Yiming Yang
Google Scholar ID: MlZq4XwAAAAJ
Professor, Carnegie Mellon University
Citations & Impact
Citations
50,573
H-index
66
i10-index
183
Publications
20
Co-authors
56
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications (list)
- Teaching: 11-741/11-441 Machine Learning with Graphs (Syllabus)
Research Experience
- - LLM-Based Agents for Problem Solving: Research spans instruction tuning, demonstration-guided control, retrieval-augmented reasoning, and reinforcement learning—enabling adaptive agents for complex tasks such as math problem solving, combinatorial search, code synthesis and revision, and PDE solving.
- - Combinatorial Optimization and AI for Science: Developed learning-based solvers for NP-hard problems using diffusion models, Langevin dynamics, and Fourier neural operators; contributed to neural PDE solving, scientific workload scheduling, and code-generation-driven scientific computing.
- - Scalable Oversight and Learning Beyond Human Supervision: Advanced reinforcement learning–based alignment frameworks that scale supervision using self-play, instructible reward models, and principle-driven fine-tuning—enabling controllable and generalizable LLMs that go beyond human-written data and guidance.
Background
- Professor of Language Technologies Institute and Machine Learning Department, School of Computer Science, Carnegie Mellon University. Research interests include LLM-based agents for problem solving, combinatorial optimization and AI for science, scalable oversight and learning beyond human supervision.
