Prasanna Parthasarathi

Researcher, Noah's Ark Lab, Huawei Technologies Ltd.

Joined

January 2020

Names

Prasanna Parthasarathi (Preferred)

Emails

****@mail.mcgill.ca (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Researcher

Noah's Ark Lab, Huawei Technologies Ltd. (huawei.com)

2022 – Present

PhD student

McGill University (mcgill.ca)

2016 – 2022

MS student

Indian Institute of Technology Madras (iitm.ac.in)

2014 – 2016

Advisors, Relations & Conflicts

PhD Advisor

Joelle Pineau

2016 – 2020

Expertise

Natural Language Processing

2016 – 2020

Reinforcement Learning

2014 – 2020

Robotics

2009 – 2014

Publications

INFMEM: Learning System-2 Memory Control for Long-Context Agent
Xinyu Wang, Mingze Li, Peng Lu, Xiao-Wen Chang, Lifeng Shang, Jinpeng Li, Fei Mi, Prasanna Parthasarathi, Yufei Cui
- ICLR 2026 Workshop MemAgents Oral
- Readers: Everyone
DimPO: Dimensionality Reduction for Attention using Preference Optimization
Vojtěch Lanz, Yufei Cui, Prasanna Parthasarathi
- Submitted to ICLR 2026
- Readers: Everyone
GRPO-$\lambda$: Credit Assignment improves LLM Reasoning
Prasanna Parthasarathi, Mathieu Reymond, Boxing Chen, Yufei Cui, Sarath Chandar
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
Maxime Heuillet, Yufei Cui, Boxing Chen, Audrey Durand, Prasanna Parthasarathi
- NeurIPS 2025 ER Workshop
- Readers: Everyone
EWEK-QA : Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems
Mohammad Dehghan, Mohammad Ali Alomrani, Sunyam Bagga, David Alfonso-Hermelo, Khalil Bibi, Abbas Ghaddar, Yingxue Zhang, Xiaoguang Li, Jianye HAO, Qun Liu, Jimmy Lin, Boxing Chen, Prasanna Parthasarathi, Mahdi Biparva, Mehdi Rezagholizadeh
- Association for Computational Linguistics
- Readers: Everyone
Resona: Improving Context Copying in Linear Recurrence Models with Retrieval
Xinyu Wang, Linrui Ma, Jerry Huang, Peng Lu, Prasanna Parthasarathi, Xiao-Wen Chang, Boxing Chen, Yufei Cui
- COLM 2025
- Readers: Everyone
Language Model-In-The-Loop: Data Optimal Approach to Recommend Actions in Text Games
Arjun V Sudhakar, Prasanna Parthasarathi, Janarthanan Rajendran, Sarath Chandar
- ICML 2024 FM-Wild Workshop Poster
- Readers: Everyone
Language Model-In-The-Loop: Data Optimal Approach to Recommend Actions in Text Games
Arjun V Sudhakar, Prasanna Parthasarathi, Janarthanan Rajendran, Sarath Chandar
- TAFM@RLC 2024
- Readers: Everyone
Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
Abdelrahman Zayed, Prasanna Parthasarathi, Goncalo Mordido, Hamid Palangi, Samira Shabanian, Sarath Chandar
- 27 Jun 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
EpiK-Eval: Evaluation for Language Models as Epistemic Models
Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, Sarath Chandar
- EMNLP 2023 Main
- Readers: Everyone

View all 17 publications

Co-Authors

View all 50 co-authors