Kshitij Gupta

Joined

May 2022

Names

Kshitij Gupta (Preferred)

Emails

****@mila.quebec (Confirmed)

,

****@gmail.com (Confirmed)

Personal Links

Career & Education History

MS student

Université de Montréal (umontreal.ca)

2021 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Present

PhD Advisor

Present

Expertise

Reinforcement Learning

Present

Publications

Robin: a Suite of Multi-Scale Vision-Language Models and the CHIRP Evaluation Benchmark
Alexis Roger, Daniel Z Kaplan, Prateek Humane, Kshitij Gupta, Qi Sun, George Adamopoulos, Jonathan Siu Chi Lim, Quentin Gregory Anthony, Edwin Fennell, Irina Rish
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Adam Ibrahim, Benjamin Thérien, Kshitij Gupta, Mats Leon Richter, Quentin Gregory Anthony, Eugene Belilovsky, Timothée Lesort, Irina Rish
- Accepted by TMLR
- Readers: Everyone
ARB: Advanced Reasoning Benchmark for Large Language Models
Tomohiro Sawada, Daniel Paleka, Alexander Havrilla, Pranav Tadepalli, Paula Vidas, Alexander Kranias, John Nay, Kshitij Gupta, Aran Komatsuzaki
- MATH-AI 23 Poster
- Readers: Everyone
Adaptive Memory Module for Sequential Planning and Reasoning
Kshitij Gupta, Sean Spinney, Xutong Zhao, Janarthanan Rajendran, Patricia Conrod, Irina Rish, Sarath Chandar
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
ARB: Advanced Reasoning Benchmark for Large Language Models
Tomohiro Sawada, Daniel Paleka, Alexander Havrilla, Pranav Tadepalli, Paula Vidas, Alexander Perikles Kranias, John J Nay, Kshitij Gupta, Aran Komatsuzaki
- Submitted to ICLR 2024
- Readers: Everyone
Continual Pre-Training of Large Language Models: How to re-warm your model?
Kshitij Gupta, Benjamin Thérien, Adam Ibrahim, Mats Leon Richter, Quentin Gregory Anthony, Eugene Belilovsky, Irina Rish, Timothée Lesort
- ES-FoMO 2023 Poster
- Readers: Everyone
Broken Neural Scaling Laws
Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger
- Published: 04 Mar 2023, Last Modified: 15 Feb 2026
- ME-FoMo 2023 Poster
- Readers: Everyone
Broken Neural Scaling Laws
Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger
- Published: 05 Dec 2022, Last Modified: 15 Feb 2026
- MLSW2022
- Readers: Everyone
Broken Neural Scaling Laws
Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- ICLR 2023 poster
- Readers: Everyone
Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
Aniket Rajiv Didolkar, Kshitij Gupta, Anirudh Goyal, Nitesh Bharadwaj Gundavarapu, Alex Lamb, Nan Rosemary Ke, Yoshua Bengio
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone

Co-Authors

View all 35 co-authors