Sedrick Keh

Research Scientist, Toyota Research Institute

Joined

November 2021

Names

Sedrick Keh (Preferred)

Sedrick Scott Keh

Emails

****@gmail.com (Confirmed)

****@cs.cmu.edu (Confirmed)

****@tri.global (Confirmed)

Personal Links

Career & Education History

Research Scientist

Toyota Research Institute (tri.global)

2023 – Present

AI Resident

Toyota Research Institute (tri.global)

2023 – 2023

MS student

Carnegie Mellon University (cmu.edu)

2021 – 2022

Undergrad student

Hong Kong University of Science and Technology (ust.hk)

2017 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

text generation

large language models

prompt-based learning

creative language generation

controllable language generation

multimodal models

visual question answering

code generation

Present

Publications

SkillFactory: Self-Distillation for Learning Cognitive Behaviors
Zayne Rea Sprague, Jack Lu, Manya Wadhwa, Sedrick Keh, Mengye Ren, Greg Durrett
- ICLR 2026 Poster
- Readers: Everyone
OpenThoughts: Data Recipes for Reasoning Models
Etash Kumar Guha, Ryan Marten, Sedrick Keh, Negin Raoof, Georgios Smyrnis, Hritik Bansal, Marianna Nezhurina, Jean Mercat, Trung Vu, Zayne Rea Sprague, Ashima Suvarna, Benjamin Feuer, Leon Liangyu Chen, Zaid Khan, Eric Frankel, Sachin Grover, Caroline Choi, Niklas Muennighoff, Shiye Su, Wanjia Zhao et al. (31 additional authors not shown)
- ICLR 2026 Oral
- Readers: Everyone
OpenThoughts: Data Recipes for Reasoning Models
Etash Kumar Guha, Ryan Marten, Sedrick Keh, Negin Raoof, Georgios Smyrnis, Hritik Bansal, Marianna Nezhurina, Jean Mercat, Trung Vu, Zayne Rea Sprague, Ashima Suvarna, Benjamin Feuer, Leon Liangyu Chen, Zaid Khan, Eric Frankel, Sachin Grover, Caroline Choi, Niklas Muennighoff, Shiye Su, Wanjia Zhao et al. (30 additional authors not shown)
- FoRLM 2025
- Readers: Everyone
Improving Test-Time Search for LLMs with Backtracking Against In-Context Value Verifiers
Anikait Singh, Kushal Arora, Sedrick Keh, Jean Mercat, Tatsunori Hashimoto, Chelsea Finn, Aviral Kumar
- SSI-FM Poster
- Readers: Everyone
Improving Test-Time Search for LLMs with Backtracking Against In-Context Value Verifiers
Anikait Singh, Kushal Arora, Sedrick Keh, Jean Mercat, Tatsunori Hashimoto, Chelsea Finn, Aviral Kumar
- Reasoning and Planning for LLMs @ ICLR2025
- Readers: Everyone
Improving the Efficiency of Test-Time Search in LLMs with Backtracking
Anikait Singh, Kushal Arora, Sedrick Keh, Jean Mercat, Tatsunori Hashimoto, Chelsea Finn, Aviral Kumar
- Submitted to ICLR 2025
- Readers: Everyone
Should VLMs be Pre-trained with Image Data?
Sedrick Keh, Jean Mercat, Samir Yitzhak Gadre, Kushal Arora, Igor Vasiljevic, Benjamin Burchfiel, Shuran Song, Russ Tedrake, Thomas Kollar, Ludwig Schmidt, Achal Dave
- ICLR 2025 Poster
- Readers: Everyone
Language models scale reliably with over-training and on downstream tasks
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, Rui Xin, Marianna Nezhurina, Igor Vasiljevic, Luca Soldaini, Jenia Jitsev, Alex Dimakis, Gabriel Ilharco, Pang Wei Koh, Shuran Song, Thomas Kollar et al. (5 additional authors not shown)
- ICLR 2025 Poster
- Readers: Everyone
DataComp-LM: In search of the next generation of training sets for language models
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Kumar Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee F Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton et al. (39 additional authors not shown)
- NeurIPS 2024 Track Datasets and Benchmarks Poster
- Readers: Everyone
A Critical Evaluation of AI Feedback for Aligning Large Language Models
Archit Sharma, Sedrick Keh, Eric Mitchell, Chelsea Finn, Kushal Arora, Thomas Kollar
- NeurIPS 2024 poster
- Readers: Everyone

View all 24 publications

Co-Authors

View all 131 co-authors