Kelvin Xu

PhD student, University of California Berkeley

Joined

October 2016

Names

Kelvin Xu (Preferred)

Emails

****@gmail.com (Confirmed)

****@umontreal.ca (Confirmed)

****@eecs.berkeley.edu (Confirmed)

****@berkeley.edu (Confirmed)

****@google.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

University of California Berkeley (berkeley.edu)

2017 – Present

Researcher

Google (google.com)

2016 – 2017

MS student

University of Montreal (umontreal.ca)

2014 – 2016

Undergrad student

University of Toronto (toronto.edu)

2009 – 2014

Advisors, Relations & Conflicts

PhD Advisor

Sergey Levine

2017 – 2022

PhD Advisor

Yoshua Bengio

2014 – 2016

PhD Advisor

Aaron Courville

2014 – 2016

Expertise

Deep Learning

Sequence Models

Image Captioning

Attention

Reinforcement Learning

Present

Deep Learning

Natural Language Processing

Computer Vision

Present

Publications

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
- ICML 2025 poster
- Readers: Everyone
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
- Submitted to ICLR 2025
- Readers: Everyone
Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning
Charlie Victor Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar
- ICLR 2025 Oral
- Readers: Everyone
Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
Jiri Hron, Laura A Culp, Gamaleldin Fathy Elsayed, Rosanne Liu, Jasper Snoek, Simon Kornblith, Alex Rizkowsky, Isabelle Simpson, Jascha Sohl-Dickstein, Noah Fiedel, Aaron T Parisi, Alexander A Alemi, Azade Nova, Ben Adlam, Bernd Bohnet, Gaurav Mishra, Hanie Sedghi, Izzeddin Gur, Jaehoon Lee, John D Co-Reyes et al. (11 additional authors not shown)
- COLM
- Readers: Everyone
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Avi Singh, John D Co-Reyes, Rishabh Agarwal, Ankesh Anand, Piyush Patil, Xavier Garcia, Peter J Liu, James Harrison, Jaehoon Lee, Kelvin Xu, Aaron T Parisi, Abhishek Kumar, Alexander A Alemi, Alex Rizkowsky, Azade Nova, Ben Adlam, Bernd Bohnet, Gamaleldin Fathy Elsayed, Hanie Sedghi, Igor Mordatch et al. (20 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Small-scale proxies for large-scale Transformer training instabilities
Mitchell Wortsman, Peter J Liu, Lechao Xiao, Katie E Everett, Alexander A Alemi, Ben Adlam, John D Co-Reyes, Izzeddin Gur, Abhishek Kumar, Roman Novak, Jeffrey Pennington, Jascha Sohl-Dickstein, Kelvin Xu, Jaehoon Lee, Justin Gilmer, Simon Kornblith
- ICLR 2024 oral
- Readers: Everyone
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
- Submitted to ICLR 2024
- Readers: Everyone
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Lixuan Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, Hugo Larochelle
- 05 May 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
Autonomous Reinforcement Learning: Formalism and Benchmarking
Archit Sharma, Kelvin Xu, Nikhil Sardana, Abhishek Gupta, Karol Hausman, Sergey Levine, Chelsea Finn
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 Poster
- Readers: Everyone
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
Kelvin Xu, Ellis Ratner, Anca D. Dragan, Sergey Levine, Chelsea Finn
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone

View all 13 publications

Co-Authors

View all 79 co-authors