Rebecca Roelofs

Research scientist, Google

Joined

July 2019

Names

Rebecca Roelofs

Emails

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

****@gmail.com (Confirmed)

****@google.com (Confirmed)

Personal Links

DBLP

Career & Education History

Research scientist

Google (google.com)

2019 – Present

PhD student

University of California Berkeley (berkeley.edu)

2013 – 2019

Undergrad student

Swarthmore College (swarthmore.edu)

2009 – 2013

Advisors, Relations & Conflicts

PhD Advisor

Benjamin Recht

2013 – 2019

Expertise

model robustness under distribution shift

Present

dataset construction for robustness benchmarks

Present

bias in calibration error estimation

Present

adaptive overfitting due to test set reuse

Present

Publications

Training Language Models to Self-Correct via Reinforcement Learning
Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal Behbahani, Aleksandra Faust
- ICLR 2025 Oral
- Readers: Everyone
Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
Yiren Lu, Justin Fu, George Tucker, Xinlei Pan, Eli Bronstein, Rebecca Roelofs, Benjamin Sapp, Brandyn White, Aleksandra Faust, Shimon Whiteson, Dragomir Anguelov, Sergey Levine
- 25 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
Cole Gulino, Justin Fu, Wenjie Luo, George Tucker, Eli Bronstein, Yiren Lu, Jean Harb, Xinlei Pan, Yan Wang, Xiangyu Chen, John D Co-Reyes, Rishabh Agarwal, Rebecca Roelofs, Yao Lu, Nico Montali, Paul Mougin, Zoey Zeyu Yang, Brandyn White, Aleksandra Faust, Rowan Thomas McAllister et al. (2 additional authors not shown)
- NeurIPS 2023 Datasets and Benchmarks Poster
- Readers: Everyone
CausalAgents: A Robustness Benchmark for Motion Forecasting Using Causal Relationships
Rebecca Roelofs, Liting Sun, Benjamin Caine, Khaled S. Refaat, Benjamin Sapp, Scott Ettinger, Wei Chai
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
Anders Johan Andreassen, Yasaman Bahri, Behnam Neyshabur, Rebecca Roelofs
- Accepted by TMLR
- Readers: Everyone
When does dough become a bagel?Analyzing the remaining mistakes on ImageNet
Vijay Vasudevan, Benjamin Caine, Raphael Gontijo-Lopes, Sara Fridovich-Keil, Rebecca Roelofs
- 04 Jun 2022 (modified: 30 Dec 2025)
- Shift Happens 2022 ContributedTalk
- Readers: Everyone
Spectral Bias in Practice: The Role of Function Frequency in Generalization
Sara Fridovich-Keil, Raphael Gontijo-Lopes, Rebecca Roelofs
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
When does dough become a bagel? Analyzing the remaining mistakes on ImageNet
Vijay Vasudevan, Benjamin Caine, Raphael Gontijo-Lopes, Sara Fridovich-Keil, Rebecca Roelofs
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, Ludwig Schmidt
- 2022 (modified: 10 May 2022)
- CoRR 2022
- Readers: Everyone
Robust fine-tuning of zero-shot models
Mitchell Wortsman, Gabriel Ilharco, Jong Wook Kim, Mike Li, Simon Kornblith, Rebecca Roelofs, Raphael Gontijo-Lopes, Hanna Hajishirzi, Ali Farhadi, Hongseok Namkoong, Ludwig Schmidt
- Published: 02 Dec 2021, Last Modified: 04 May 2025
- NeurIPS 2021 Workshop DistShift Poster
- Readers: Everyone

View all 37 publications

Co-Authors

View all 106 co-authors