Skip to content

Home Search Authors Pakistan News Saved

SciRah

SciRah does not host or store research papers. Results come live from free, official scholarly APIs, and every paper links back to its original source.

Data sources

OpenAlex
Semantic Scholar
Crossref
CORE
arXiv
PubMed

Privacy policy Terms of service

Amrith Rajagopal Setlur · SciRah

Researcher profile · Semantic Scholar

Amrith Rajagopal Setlur

Carnegie Mellon University

Share profile

Amrith Rajagopal Setlur — researcher profile on SciRah

ORCID iD 0000-0002-7061-3094

h-index: 16
Works: 54
Citations: 1,477

Most-cited papers

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
Amrith Rajagopal Setlur, Chirag Nagpal, Adam Fisch, Xin-Yang Geng +5 more
2024International Conference on Learning Representations313 citations
Semantic Scholar
Politeness Transfer: A Tag and Generate Approach
Aman Madaan, Amrith Rajagopal Setlur, Tanmay Parekh, B. Póczos +5 more
2020Annual Meeting of the Association for Computational Linguistics178 citations Open access
Semantic Scholar
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
Amrith Rajagopal Setlur, Saurabh Garg, Xin-Yang Geng, Naman Garg +2 more
2024Neural Information Processing Systems146 citations
Semantic Scholar
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
Yuxiao Qu, Matthew Y. R. Yang, Amrith Rajagopal Setlur, Lewis Tunstall +3 more
2025International Conference on Machine Learning140 citations
Semantic Scholar
Scaling Test-Time Compute Without Verification or RL is Suboptimal
Amrith Rajagopal Setlur, Nived Rajaraman, Sergey Levine, Aviral Kumar
2025International Conference on Machine Learning104 citations
Semantic Scholar
Explaining The Efficacy of Counterfactually-Augmented Data
Divyansh Kaushik, Amrith Rajagopal Setlur, E. Hovy, Zachary Chase Lipton
2020International Conference on Learning Representations93 citations
Semantic Scholar
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
Amrith Rajagopal Setlur, Matthew Y. R. Yang, C. Snell, Jeremy Greer +4 more
2025arXiv.org70 citations
Semantic Scholar
An Efficient Fault Tolerant Workflow Scheduling Approach using Replication Heuristics and Checkpointing in the Cloud
Amrith Rajagopal Setlur, S. Nirmala, H. Singh, Sudhanshu Khoriya
2018J. Parallel Distributed Comput.45 citations Open access
Semantic Scholar
POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
Yuxiao Qu, Amrith Rajagopal Setlur, Virginia Smith, R. Salakhutdinov +1 more
2026arXiv.org43 citations
Semantic Scholar
Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
Junhong Shen, Hao Bai, Lunjun Zhang, Yifei Zhou +7 more
2025arXiv.org42 citations
Semantic Scholar
RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Rajagopal Setlur +3 more
2025arXiv.org27 citations
Semantic Scholar
What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?
Katie Kang, Amrith Rajagopal Setlur, Dibya Ghosh, Jacob Steinhardt +3 more
2024arXiv.org26 citations
Semantic Scholar
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions
Amrith Rajagopal Setlur, Benjamin Eysenbach, Virginia Smith, S. Levine
2022Neural Information Processing Systems26 citations Open access
Semantic Scholar
Exact Unlearning of Finetuning Data via Model Merging at Scale
Kevin Kuo, Amrith Rajagopal Setlur, K. Srinivas, Aditi Raghunathan +1 more
20252026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)17 citations Open access
Semantic Scholar
Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution
Amrith Rajagopal Setlur, Oscar Li, Virginia Smith
2021Neural Information Processing Systems17 citations
Semantic Scholar
Is Support Set Diversity Necessary for Meta-Learning?
Amrith Rajagopal Setlur, Oscar Li, Virginia Smith
2020arXiv.org17 citations
Semantic Scholar
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
Amrith Rajagopal Setlur, Zi-Jian Wang, Andrew Cohen, Paria Rashidinejad +1 more
2026arXiv.org16 citations
Semantic Scholar
InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning
Matthew Y. R. Yang, Hao Bai, Ian Wu, Gene Yang +2 more
2026arXiv.org15 citations
Semantic Scholar
Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
Ian Wu, Yuxiao Qu, Amrith Rajagopal Setlur, Aviral Kumar
2026arXiv.org15 citations
Semantic Scholar
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
Amrith Rajagopal Setlur, Don Kurian Dennis, Benjamin Eysenbach, Aditi Raghunathan +3 more
2023International Conference on Learning Representations13 citations Open access
Semantic Scholar
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
Saurabh Garg, Amrith Rajagopal Setlur, Zachary Chase Lipton, Sivaraman Balakrishnan +2 more
2023Neural Information Processing Systems13 citations
Semantic Scholar
Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features
Annie S. Chen, Yoonho Lee, Amrith Rajagopal Setlur, S. Levine +1 more
2023arXiv.org13 citations Open access
Semantic Scholar
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)
A. Bertie, Lambert Douwe, Aida Mostafazadeh Davani, D. Kiela +496 more
202111 citations Open access
Semantic Scholar
Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
Junhong Shen, Haoyu Bai, Lunjun Zhang, Yifei Zhou +7 more
2025Neural Information Processing Systems10 citations
Semantic Scholar
Robust Handwriting Recognition with Limited and Noisy Data
Hai Pham, Amrith Rajagopal Setlur, Saket Dingliwal, Tzu-Hsiang Lin +6 more
2020International Conference on Frontiers in Handwriting Recognition9 citations Open access
Semantic Scholar
Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
Annie S. Chen, Yoonho Lee, Amrith Rajagopal Setlur, S. Levine +1 more
2024International Conference on Learning Representations7 citations
Semantic Scholar
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
Pratiksha Thaker, Amrith Rajagopal Setlur, Steven Z. Wu, Virginia Smith
2023Neural Information Processing Systems7 citations Open access
Semantic Scholar
Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts
Annie S. Chen, Yoonho Lee, Amrith Rajagopal Setlur, S. Levine +1 more
2023arXiv.org7 citations Open access
Semantic Scholar
ReStGAN: A step towards visually guided shopper experience via text-to-image synthesis
Shiv Surya, Amrith Rajagopal Setlur, Arijit Biswas, Sumit Negi
2020IEEE Workshop/Winter Conference on Applications of Computer Vision7 citations
Semantic Scholar
L EARNING TO R EASON ON H ARD P ROBLEMS WITH P RIVILEGED O N -P OLICY E XPLORATION
Yuxiao Qu, Amrith Rajagopal Setlur, Virginia Smith, R. Salakhutdinov +1 more
7 citations
Semantic Scholar
QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
LM-Provers, Yuxiao Qu, Amrith Rajagopal Setlur, Jasper Dekoninck +5 more
2026arXiv.org6 citations
Semantic Scholar
Learning to Discover Abstractions for LLM Reasoning
Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Rajagopal Setlur +3 more
6 citations
Semantic Scholar
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
Zhoujun Cheng, Yutao Xie, Yuxiao Qu, Amrith Rajagopal Setlur +11 more
2026arXiv.org5 citations
Semantic Scholar
Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
Amrith Rajagopal Setlur, Saurabh Garg, Virginia Smith, Sergey Levine
2024International Conference on Machine Learning4 citations
Semantic Scholar
Semi-Supervised Confidence Network aided Gated Attention based Recurrent Neural Network for Clickbait Detection
Amrith Rajagopal Setlur
2018ICON4 citations
Semantic Scholar
What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning?
Katie Kang, Amrith Rajagopal Setlur, Dibya Ghosh, Jacob Steinhardt +3 more
2025International Conference on Machine Learning3 citations
Semantic Scholar
Contextual Reliability: When Different Features Matter in Different Contexts
Gaurav R. Ghosal, Amrith Rajagopal Setlur, Daniel S. Brown, A. Dragan +1 more
2023International Conference on Machine Learning3 citations Open access
Semantic Scholar
M AXIMIZING ENTROPY ON ADVERSARIAL EXAMPLES CAN IMPROVE GENERALIZATION
Amrith Rajagopal Setlur, Benjamin Eysenbach, Virginia Smith, S. Levine
20223 citations
Semantic Scholar
Multitask Learning Can Improve Worst-Group Outcomes
Atharva Kulkarni, L. Dery, Amrith Rajagopal Setlur, Aditi Raghunathan +2 more
2023Trans. Mach. Learn. Res.2 citations
Semantic Scholar
Nonlinear ISA with Auxiliary Variables for Learning Speech Representations
Amrith Rajagopal Setlur, B. Póczos, A. Black
2020Interspeech2 citations Open access
Semantic Scholar
Private and Personalized Frequency Estimation in a Federated Setting
Amrith Rajagopal Setlur, V. Feldman, Kunal Talwar
2024Neural Information Processing Systems1 citations
Semantic Scholar
Private and Personalized Histogram Estimation in a Federated Setting
Amrith Rajagopal Setlur, V. Feldman, Kunal Talwar
1 citations
Semantic Scholar
ExpRL: Exploratory RL for LLM Mid-Training
Violet Xiang, Amrith Rajagopal Setlur, Chase Blagden, Nick Haber +1 more
2026arXiv.org0 citations
Semantic Scholar
Lower Bounds for Public-Private Learning under Distribution Shift
Amrith Rajagopal Setlur, Pratiksha Thaker, Jonathan Ullman
2025arXiv.org0 citations
Semantic Scholar
Deep Neural Networks Tend To Extrapolate Predictably
Katie Kang, Amrith Rajagopal Setlur, Claire J. Tomlin, Sergey Levine
2023International Conference on Learning Representations0 citations Open access
Semantic Scholar
Towards Using Heterogeneous Relation Graphs for End-to-End TTS
Amrith Rajagopal Setlur, Aman Madaan, Tanmay Parekh, Yi-Ming Yang +1 more
2021Automatic Speech Recognition & Understanding0 citations
Semantic Scholar
Emotion Style Transfer with a Speciﬁed Intensity Using Deep Reinforcement Learning
Cecilia Ovesdotter Alm, Richard Sproat, L. Ana, Maria Bostan +27 more
20210 citations
Semantic Scholar
Lessons from Chasing Few-Shot Learning Benchmarks: Rethinking the Evaluation of Meta-Learning Methods
Amrith Rajagopal Setlur, Oscar Li, Virginia Smith
2021arXiv.org0 citations
Semantic Scholar
T ailor : Generating and Perturbing Text with Semantic Controls
L. Banarescu, C. Bonial, Madalina Shu Cai, Kira Georgescu +112 more
20210 citations
Semantic Scholar
Covariate Distribution Aware Meta-learning
Amrith Rajagopal Setlur, Saket Dingliwal, B. Póczos
2020arXiv.org0 citations
Semantic Scholar

Frequent co-authors

Invite them to SciRah by sharing their profile.

Aviral Kumar×18
Invite
Aviral Kumar — researcher profile on SciRah
Virginia Smith×8
Invite
Virginia Smith — researcher profile on SciRah
Yuxiao Qu×8
Invite
Yuxiao Qu — researcher profile on SciRah
R. Salakhutdinov×6
Invite
R. Salakhutdinov — researcher profile on SciRah

Virginia Smith×6

Invite

Virginia Smith — researcher profile on SciRah

Sergey Levine×5

Invite

Sergey Levine — researcher profile on SciRah

Invite

S. Levine — researcher profile on SciRah

Invite

Aman Madaan — researcher profile on SciRah

Tanmay Parekh×4

Invite

Tanmay Parekh — researcher profile on SciRah

Invite

B. Póczos — researcher profile on SciRah

Invite

A. Black — researcher profile on SciRah

Saurabh Garg×3

Invite

Saurabh Garg — researcher profile on SciRah