Cassidy Laidlaw
Cassidy Laidlaw
Researcher, Transluce
PhD student, Electrical Engineering and Computer Science, University of California Berkeley
Joined
December 2019
Names
Emails
****@umd.edu (Confirmed)
****@tue.mpg.de (Confirmed)
****@tuebingen.mpg.de (Confirmed)
****@cs.berkeley.edu (Confirmed)
****@berkeley.edu (Confirmed)
****@transluce.org (Confirmed)
Personal Links
Career & Education History
Researcher
Transluce (transluce.org)
2025 – Present
PhD student
Electrical Engineering and Computer Science, University of California Berkeley (berkeley.edu)
2020 – Present
Undergrad student
Computer Science, University of Maryland, College Park (umd.edu)
2014 – 2018
Advisors, Relations & Conflicts
Expertise
reinforcement learning theory
, RL theory
2021 – Present
preference learning
, reward learning
, inverse reinforcement learning
, ai alignment
, ai safety
2020 – Present
multiagent systems
, multiagent RL
, human modeling
2020 – Present
robustness
, adversarial examples
, adversarial attacks
2019 – 2022
Publications
Co-Authors
- Anand Siththaranjan
- Anca D. Dragan
- Anca Dragan
- Anurag Ranjan
- Banghua Zhu
- Daniel Cudeiro
- Daniel Khalil
- Dylan Feng
- Dylan Hadfield-Menell
- Edwin Zhang
- Eli Bronstein
- Finale Doshi-Velez
- Harvey Klyne
- Jacob Steinhardt
- Justin Svegliato
- Laker Newhouse
- Lauren H. Cooke
- Lukas Berglund
- Michael J. Black
- Michelle Li
- Milind Tambe
- Pragya Srivastava
- Sahil Singla
- Shivam Singhal
- Soheil Feizi