Carlos Guestrin
· Machine Learning, Explainability, Fairness and ML SystemsStanford University · Learning, Design, and Technology
Active 2000–2026
Academic metrics are sourced from OpenAlex and public funding records; values may differ from Google Scholar.
About
Carlos Guestrin is a Professor of Computer Science at Stanford University and serves as the Director of the Stanford AI Lab (SAIL). He holds the title of Fortinet Founders Professor and is a Senior Fellow at the Stanford Institute for Human-Centered AI (HAI). Guestrin is also the Chief Scientist of Visual Layer and Virtue AI. He is a member of the National Academy of Engineering. His research focuses on machine learning methods, with particular emphasis on explainability, fairness, and ethics of AI, as well as the development of machine learning systems.
Research topics
- Computer Science
- Business
- Virology
- Demographic economics
- Medicine
- Telecommunications
- Economics
- Environmental health
Selected publications
Optimizing generative AI by backpropagating language model feedback
Nature · 2025-03-19 · 48 citations
articleProceedings of the VLDB Endowment · 2025-07-01 · 5 citations
articleThe semantic capabilities of large language models (LLMs) have the potential to enable rich analytics and reasoning over vast knowledge corpora. Unfortunately, existing systems either empirically optimize expensive LLM-powered operations with no performance guarantees , or limit their support to simple batched-inference primitives. We introduce semantic operators , the first formalism with statistical accuracy guarantees for general-purpose AI-based operations with natural language parameters (e…
Diabetes Care · 2025-07-01 · 5 citations
articleOpen accessOBJECTIVE: The Teamwork, Targets, Technology, and Tight Range (4T) Exercise Program evaluated physical activity patterns across the first year of type 1 diabetes diagnosis and whether physical activity was associated with changes in glucose outcomes in the 24 h following physical activity. RESEARCH DESIGN AND METHODS: The 4T Exercise Program started newly diagnosed youth with type 1 diabetes on a continuous glucose monitoring (CGM) system and physical activity tracker around 1 month postdiagnosi…
Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
ArXiv.org · 2026-04-23
articleOpen accessReinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes. A common assumption is that the reasoning chains trained through RLVR reliably represent how a model gets to its answer. In this paper, we develop two metrics for critically examining this assumption: Causal Importance of Reasoning (CIR), which measures the cumulative effect of reasoning tokens on the final answer, and Sufficiency of Reasoning (S…
Reinforcement Learning via Self-Distillation
arXiv (Cornell University) · 2026-01-28
articleOpen accessLarge language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome reward per attempt, creating a severe credit-assignment bottleneck. Many verifiable environments actually provide rich textual feedback, such as runtime errors or judge evaluations, that explain why an attempt failed. We formalize this setting as reinforcement le…
Recent grants
NSF · $506k · 2006–2012
NSF · $200k · 2005–2009
NSF · $450k · 2012–2017
Frequent coauthors
- 49 shared
Andreas Krause
- 26 shared
Jure Leskovec
Stanford University
- 25 shared
Joseph M. Hellerstein
University of California, Berkeley
- 23 shared
Daphne Koller
- 22 shared
Jeanne M. VanBriesen
- 22 shared
Paul S. Fischbeck
Decision Sciences (United States)
- 20 shared
Shannon L. Isovitsch
Forbes Hospital
- 20 shared
Mitchell J. Small
Carnegie Mellon University
Labs
Education
Ph.D., Computer Science
Stanford University
Awards & honors
- Member of the National Academy of Engineering
- Fortinet Founders Professor, Stanford
Similar researchers at Stanford University
- Resume-aware match score
- Save to shortlist
- AI-drafted outreach
See your match with Carlos Guestrin
PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.
- Free to start
- No credit card
- 30-second signup