Ponkshe, Kaustubh

7 publications

ICLR 2026 ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak, Praneeth Vepakomma

TMLR 2026 Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak, Lav R. Varshney, Praneeth Vepakomma

ICLR 2026 Safety Subspaces Are Not Linearly Distinct: A Fine-Tuning Case Study Kaustubh Ponkshe, Shaan Shah, Raghav Singhal, Praneeth Vepakomma

ICLRW 2025 FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models Raghav Singhal, Kaustubh Ponkshe, Praneeth Vepakomma

ICLRW 2025 Initialization Using Update Approximation Is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning Kaustubh Ponkshe, Raghav Singhal, Eduard Gorbunov, Alexey Tumanov, Samuel Horváth, Praneeth Vepakomma

NeurIPS 2025 TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs Parjanya Prajakta Prashant, Kaustubh Ponkshe, Babak Salimi

NeurIPSW 2024 FedEx-LoRA: Exact Aggregation for Federated Parameter-Efficient Fine-Tuning of Foundation Models Raghav Singhal, Kaustubh Ponkshe, Praneeth Vepakomma