Kavosh Asadi

Researcher, Amazon

Joined

July 2019

Names

Kavosh Asadi (Preferred)

Emails

****@brown.edu (Confirmed)

****@gmail.com (Confirmed)

****@amazon.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Amazon (amazon.com)

2021 – Present

PhD student

Brown University (brown.edu)

2015 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Michael Littman

2015 – 2020

Expertise

reinforcement learning

2013 – 2023

Publications

Structure Enables Effective Self-Localization of Errors in LLMs
Ankur Samanta, Akshayaa Magesh, Ayush Jain, Kavosh Asadi, Youliang Yu, Daniel Jiang, Boris Vidolov, Kaveh Hassani, Paul Sajda, Jalaj Bhandari, Yonathan Efroni
- ICLR 2026 Workshop RSI Poster
- Readers: Everyone
$$\texttt{C2-DPO}$$: Constrained Controlled Direct Preference Optimization
Kavosh Asadi, Xingzi Xu, Julien Han, Ege Beyazit, Idan Pipano, Dominique Perrault-Joncas, Shoham Sabach, Mohammad Ghavamzadeh, Karim Bouyarmane
- Accepted by TMLR
- Readers: Everyone
Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences
Idan Pipano, Shoham Sabach, Kavosh Asadi, Mohammad Ghavamzadeh
- ICLR 2026 Poster
- Readers: Everyone
Learning to Reason Efficiently with Discounted Reinforcement Learning
Alex Ayoub, Kavosh Asadi, Dale Schuurmans, Csaba Szepesvari, Karim Bouyarmane
- ICLR 2026 Poster
- Readers: Everyone
Activation sharding for scalable training of large models
Xingzi Xu, Amir Tavanaei, Kavosh Asadi, Karim Bouyarmane
- Accepted by TMLR
- Readers: Everyone
On Welfare-Centric Fair Reinforcement Learning
Cyrus Cousins, Kavosh Asadi, Elita Lobo, Michael Littman
- RLC 2024
- Readers: Everyone
Learning the Target Network in Function Space
Kavosh Asadi, Yao Liu, Shoham Sabach, Ming Yin, Rasool Fakoor
- ICML 2024 Poster
- Readers: Everyone
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Zuxin Liu, Jesse Zhang, Kavosh Asadi, Yao Liu, Ding Zhao, Shoham Sabach, Rasool Fakoor
- CoRL 2023 Workshop TGR Poster
- Readers: Everyone
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Zuxin Liu, Jesse Zhang, Kavosh Asadi, Yao Liu, Ding Zhao, Shoham Sabach, Rasool Fakoor
- FMDM@NeurIPS2023
- Readers: Everyone
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Zuxin Liu, Jesse Zhang, Kavosh Asadi, Yao Liu, Ding Zhao, Shoham Sabach, Rasool Fakoor
- ICLR 2024 poster
- Readers: Everyone

View all 32 publications

Co-Authors

View all 52 co-authors