collaborators

7 papers

cs.LG2025

Power Mechanism: Private Tabular Representation Release for Model Agnostic Consumption

Praneeth Vepakomma, Kaustubh Ponkshe

Traditional collaborative learning approaches are based on sharing of model weights between clients and a server. However, there are advantages to resource efficiency through schem…

cs.CL2025

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Project Apertus, Alejandro Hernández-Cano, Alexander Hägele +100

We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingu…

cs.LG2025

Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning

Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak +2

Low-Rank Adaptation (LoRA) has become ubiquitous for efficiently fine-tuning foundation models. However, federated fine-tuning using LoRA is challenging due to suboptimal updates a…

cs.LG2025

A Lightweight Method to Disrupt Memorized Sequences in LLM

Parjanya Prajakta Prashant, Kaustubh Ponkshe, Babak Salimi

As language models scale, their performance improves dramatically across a wide range of tasks, but so does their tendency to memorize and regurgitate parts of their training data…

cs.CL2024

StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training

Kaustubh Ponkshe, Venkatapathy Subramanian, Natwar Modani +1

Most state-of-the-art techniques for Language Models (LMs) today rely on transformer-based architectures and their ubiquitous attention mechanism. However, the exponential growth i…

cs.CL2024

GUIDEQ: Framework for Guided Questioning for progressive informational collection and classification

Priya Mishra, Suraj Racha, Kaustubh Ponkshe +2

Question Answering (QA) is an important part of tasks like text classification through information gathering. These are finding increasing use in sectors like healthcare, customer…