Vineet Jain

PhD student, McGill University

Joined

September 2021

Names

Vineet Jain (Preferred)

Emails

****@gmail.com (Confirmed)

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

****@mila.quebec (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

PhD student

McGill University (mcgill.ca)

2021 – Present

MS student

School of Computer Science, Carnegie Mellon University (cs.cmu.edu)

2019 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Siamak Ravanbakhsh

2021 – Present

Expertise

Reinforcement learning

Present

Representation learning

Present

Self-supervised learning

Present

Uncertainty estimation

Present

Bayesian inference

Present

Publications

A Comedy of Estimators: On KL Regularization in RL Training of LLMs
Vedant Shah, Johan Obando-Ceron, Vineet Jain, Brian R. Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Nikolay Malkin, Moksh Jain, Siddarth Venkatraman, Aaron Courville
- Submitted to ICLR 2026
- Readers: Everyone
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
Siddarth Venkatraman, Vineet Jain, Sarthak Mittal, Vedant Shah, Johan Obando-Ceron, Yoshua Bengio, Brian R. Bartoldson, Bhavya Kailkhura, Guillaume Lajoie, Glen Berseth, Nikolay Malkin, Moksh Jain
- Submitted to ICLR 2026
- Readers: Everyone
Long-Horizon Model-Based Offline Reinforcement Learning Without Conservatism
Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
- Submitted to ICLR 2026
- Readers: Everyone
Deep Thinking via Recursive Self-Aggregation
Siddarth Venkatraman, Vineet Jain, Sarthak Mittal, Moksh Jain, Vedant Shah, Johan Obando-Ceron, Yoshua Bengio, Brian R. Bartoldson, Bhavya Kailkhura, Guillaume Lajoie, Glen Berseth, Nikolay Malkin
- FoRLM 2025
- Readers: Everyone
Long-Horizon Model-Based Offline Reinforcement Learning Without Conservatism
Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
- ARLET
- Readers: Everyone
Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models
Vineet Jain, Kusha Sareen, Mohammad Pedramfar, Siamak Ravanbakhsh
- PUT at ICML 2025 Poster
- Readers: Everyone
Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models
Vineet Jain, Kusha Sareen, Mohammad Pedramfar, Siamak Ravanbakhsh
- NeurIPS 2025 poster
- Readers: Everyone
Sampling from Energy-based Policies using Diffusion
Vineet Jain, Tara Akhound-Sadegh, Siamak Ravanbakhsh
- RLC 2025
- Readers: Everyone
Scaling Laws and Efficient Inference for Ternary Language Models
Tejas Vaidhya, Ayush Kaushal, Vineet Jain, Francis Couture-Harpin, Prashant Shishodia, Majid Behbahani, Irina Rish, Yuriy Nevmyvaka
- SLLM
- Readers: Everyone
Sampling from Energy-based Policies using Diffusion
Vineet Jain, Tara Akhound-Sadegh, Siamak Ravanbakhsh
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

View all 19 publications

Co-Authors

View all 35 co-authors