Abrar Anwar

Intern, NVIDIA

PhD student, Computer Science, University of Southern California

Joined

May 2021

Names

Abrar Anwar (Preferred)

Emails

****@gmail.com (Confirmed)

****@usc.edu (Confirmed)

Personal Links

Career & Education History

Intern

NVIDIA (nvidia.com)

2024 – Present

PhD student

Computer Science, University of Southern California (usc.edu)

2021 – Present

Visiting Scholar

Computer Science, Cornell University (cornell.edu)

2022 – 2022

Undergrad student

Computer Science, University of Texas, Austin (utexas.edu)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Jesse Thomason

Present

Expertise

human-robot interaction

Present

robotics

Present

natural language processing

Present

evaluation

Present

Publications

Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
Anthony Liang, Yigit Korkmaz, Jiahui Zhang, Minyoung Hwang, Abrar Anwar, Sidhant Kaushik, Aditya Shah, Alex S Huang, Luke Zettlemoyer, Dieter Fox, Yu Xiang, Anqi Li, Andreea Bobu, Abhishek Gupta, Stephen Tu, Erdem Biyik, Jesse Zhang
- Robotics: Science and Systems (RSS) 2026
- Readers: Everyone
Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
Anthony Liang, Yigit Korkmaz, Jiahui Zhang, Minyoung Hwang, Abrar Anwar, Sidhant Kaushik, Aditya Shah, Alex S Huang, Luke Zettlemoyer, Dieter Fox, Yu Xiang, Anqi Li, Andreea Bobu, Abhishek Gupta, Stephen Tu, Erdem Biyik, Jesse Zhang
- ICRA 2026 Workshop RL4IL Oral
- Readers: Everyone
M3PT: A Transformer for Multimodal, Multi-Party Social Signal Prediction with Person-aware Blockwise Attention
Yiming Tang, Abrar Anwar, Jesse Thomason
- Multimodality, Social signals, Human-computer Interaction
- Readers: Everyone
Robotic Steering: Mechanistic Finetuning for Vision-Language-Action Models
Chancharik Mitra, Yusen Luo, Raj Saravanan, Dantong Niu, Anirudh Pai, Jesse Thomason, Trevor Darrell, Abrar Anwar, Deva Ramanan, Roei Herzig
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
SPUR: Scaling Reward Learning from Human Demonstrations
Anthony Liang, Yigit Korkmaz, Jiahui Zhang, Jesse Zhang, Abrar Anwar, Sidhant Kaushik, Yufei Wang, Yu Xiang, David Held, Dieter Fox, Abhishek Gupta, Stephen Tu, Erdem Biyik
- NeurIPS 2025 Workshop EWM
- Readers: Everyone
SPUR: Scaling Reward Learning from Human Demonstrations
Anthony Liang, Yigit Korkmaz, Jiahui Zhang, Jesse Zhang, Abrar Anwar, Sidhant Kaushik, Yufei Wang, Yu Xiang, David Held, Dieter Fox, Abhishek Gupta, Stephen Tu, Erdem Biyik
- CoRL 2025 Workshop LEAP (Rolling)
- Readers: Everyone
ReWiND: Learning New Tasks from Language Without New Demonstrations
Jiahui Zhang, Yusen Luo, Abrar Anwar, Sumedh Anand Sontakke, Joseph J Lim, Jesse Thomason, Erdem Biyik, Jesse Zhang
- IBRL @ RLC 2025
- Readers: Everyone
ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
Jiahui Zhang, Yusen Luo, Abrar Anwar, Sumedh Anand Sontakke, Joseph J Lim, Jesse Thomason, Erdem Biyik, Jesse Zhang
- OOD Workshop @ RSS2025
- Readers: Everyone
Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
Abrar Anwar, Rohan Gupta, Zain Merchant, Sayan Ghosh, Willie Neiswanger, Jesse Thomason
- RobotEvaluation@RSS 2025 Poster
- Readers: Everyone
Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
Abrar Anwar, Rohan Gupta, Zain Merchant, Sayan Ghosh, Willie Neiswanger, Jesse Thomason
- CoRL 2025 Poster
- Readers: Everyone

View all 20 publications

Co-Authors

View all 56 co-authors