Amrith Setlur

PhD student, School of Computer Science, Carnegie Mellon University

PhD student, Carnegie Mellon University

Joined

June 2020

Names

Amrith Setlur (Preferred)

Emails

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

****@berkeley.edu (Confirmed)

****@apple.com (Confirmed)

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

Personal Links

Career & Education History

PhD student

School of Computer Science, Carnegie Mellon University (cs.cmu.edu)

2022 – Present

PhD student

Carnegie Mellon University (cmu.edu)

2021 – 2026

Advisors, Relations & Conflicts

No relations added

Expertise

generalization

Present

robustness

Present

Publications

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
Amrith Setlur, Zijian Wang, Andrew Cohen, Paria Rashidinejad, Sang Michael Xie
- SPOT
- Readers: Everyone
Reasoning Cache: Learning to Extrapolate to Long Lengths via Short-Length RL
Ian Wu, Yuxiao Qu, Amrith Setlur, Aviral Kumar
- ICLR 2026 Workshop RSI Poster
- Readers: Everyone
Reasoning Cache: Learning to Extrapolate to Long Lengths via Short-Length RL
Ian Wu, Yuxiao Qu, Amrith Setlur, Aviral Kumar
- SPOT
- Readers: Everyone
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
Zhoujun Cheng, Yutao Xie, Yuxiao Qu, Amrith Setlur, Shibo Hao, Varad Pimpalkhute, Tongtong Liang, Feng Yao, Zhengzhong Liu, Eric P. Xing, Virginia Smith, Ruslan Salakhutdinov, Zhiting Hu, Taylor W. Killian, Aviral Kumar
- SPOT
- Readers: Everyone
Patching Gaps In LLM Reasoning With Interventional Training
Matthew Y. R. Yang, Hao Bai, Ian Wu, Gene Yang, Amrith Setlur, Aviral Kumar
- MATH-AI 2025 Poster
- Readers: Everyone
Learning to Reason on Hard Problems with Privileged On-Policy Exploration
Yuxiao Qu, Amrith Setlur, Virginia Smith, Ruslan Salakhutdinov, Aviral Kumar
- MATH-AI 2025 Poster
- Readers: Everyone
Lower Bounds for Public-Private Learning under Distribution Shift
Amrith Setlur, Pratiksha Thaker, Jonathan Ullman
- AISTATS 2026 Poster
- Readers: Everyone
InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning
Matthew Y. R. Yang, Hao Bai, Ian Wu, Gene Yang, Amrith Setlur, Aviral Kumar
- ICLR 2026 Poster
- Readers: Everyone
Learning to Reason on Hard Problems with Privileged On-Policy Exploration
Yuxiao Qu, Amrith Setlur, Virginia Smith, Ruslan Salakhutdinov, Aviral Kumar
- Submitted to ICLR 2026
- Readers: Everyone
RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Setlur, Ruslan Salakhutdinov, Chelsea Finn, Aviral Kumar
- ICLR 2026 Poster
- Readers: Everyone

View all 60 publications

Co-Authors

View all 86 co-authors