Prateek Chanda - Home Page
|
I am a 3rd 4th year Ph.D. student at the Indian Institute of Technology
Bombay, CSE Department
advised by Ganesh Ramakrishnan and Pratik Jawanpuria, working on large scale
efficient machine learning, generously supported by the Prime Minister Research Fellowship (2022-2027)
and the Microsoft PhD Award (2025-2026).
I have been a part-time Student Researcher twice at Google Deepmind India hosted by Pradeep Shenoy during (July 2023-Nov 2023 & Dec 2023-May 2024) working on Efficient
Pretraining of Large Language Models and Knowledge Distillation for Large Language Models for proprietary Gemini and LaMDA models. During my time at
Deepmind, I had the pleasure of working with and being mentored by Dheeraj Nagaraj, Arun Suggala and Prateek Jain.
Trajectory
Before Ph.D., I was a research software engineer (SCAI Fellow) at Microsoft Research India Bangalore, hosted by Amit Sharma and Vageesh Chandramouli. Before this I completed my undergrad at IIEST Shibpur where I was advised by Prof. Susanta Chakrabarty (former Dean) and Prof. Asit Kr. Das.
Recent Papers
-
UniPROT: UNIform PRototype selection via Partial Optimal Transport with Submodular Guarantees (AISTATS 2026)
-
Bandit Guided Submodular Curriculum for Adaptive Subset Selection (NeurIPS 2025)
-
Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning (Preprint)(ICLR 2026)
-
FairPO: Fair Preference Optimization for Multi-Label Learning (NeurIPS OPT 2025)
-
Bayesian Coreset Optimization for Personalized Federated Learning (ICLR 2024)
-
Probabilistic Graphical Modelling for Language Model Finetuning (Under Submission)
-
Improving Distillation Robustness via Early Layer Readouts (Under Submission)
Current Research Interests
- Large language models: efficient pretraining, constrained fine-tuning, and continual learning
- Knowledge distillation, model compression and robustness
- Representation learning, submodular subset selection and coresets
- Optimization for large-scale models and scalable training
- Federated and personalized learning
News
-
[Jan 26, 2026] 1 paper accepted at ICLR 2026
-
[Jan 22, 2026] 1 paper accepted at AISTATS 2026
-
[Dec 5, 2025] Invited to Google PhD Networking Reception@NeurIPS Event Link
-
[Dec 1- Dec7, 2025] Attending NeurIPS 2025 at the beautiful city of San Diego
-
[Sep 12, 2025] 1 paper accepted at NeurIPS 2025
-
[Jun 12, 2025] Awarded Microsoft Research Award and Qualcomm Innovation Fellowship Finalist
-
[Sep 20, 2024] 1 Paper accepted to EMNLP 2024 Findings
-
[Aug 15, 2024] Reviewing for ICLR 2025
-
[Jun 5, 2024] Reviewing for Neurips 2024
- [May 06, 2024] Attending ICLR at Vienna. Please reach out.
- [Apr 17, 2024] Awarded ICLR Travel Grant.
- [Apr 10, 2024] Awarded NASA Agency Awards-NASA Group Achievement Award for our work on SunPy
-
[Feb 17, 2024] Reviewing for GCLR @ AAAI 2024
-
[Jan 15, 2024] Our paper on Bayesian Coreset Optimization for Personalized Federated Learning has been accepted at ICLR 2024
-
[Jul 15, 2023] Started internship at Google Deepmind India, hosted by Pradeep Shenoy
-
[Aug 27, 2022] Received the prestigous Prime Minister Research Fellowship as a Direct Entry
-
[Dec 09, 2021] Reviewing for AISTATS 2022
-
[Jan 15, 2021] Program Committe Member for KDD 2021 OOD (W)
Reviewer Assignments
- AAAI 25 (By Conf. submission)
- TMLR 2025 (By Invitation)
- LoG 2024 (By Invitation)
- ICLR 2025 (By Conf. submission+Invitation from 2024 Conf. Acceptance)
- Neurips 2025 (By Invitation)
Trivias & Musings
- Still Procastinating what to share here