|
Hi! I am Parikshit, a third-year Ph.D. candidate in the Computer Science Department at The University of Texas at Austin, advised by Prof. Sujay Sanghavi. My research focuses on principled methods for building efficient language models, with a current emphasis on diffusion-based language models. My work is supported by the Amazon AI Fellowship . Past life
|
|
|
|
Enabling Approximate Joint Sampling in Diffusion LMs
Parikshit Bansal, Sujay Sanghavi
Project Page ArXiv
Preprint
Context-Free Synthetic Data Mitigates Forgetting
Parikshit Bansal, Sujay Sanghavi
Preprint
|
|
Understanding Self-Supervised Learning via Gaussian Mixture Models
Parikshit Bansal, Ali Kavis, Sujay Sanghavi
NeurIPS, 2025Understanding the Training Speedup from Sampling with Approximate Losses
Rudrajit Das, Xi Chen, Bertram Ieong, Parikshit Bansal, Sujay Sanghavi
ICML, 2024Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers
Parikshit Bansal, Amit Sharma
ACL, 2023Missing Value Imputaton on Multidimensional Time Series
Parikshit Bansal, Prathamesh Deshpande, Sunita Sarawagi
VLDB, 2021
|
|
Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost
Parikshit Bansal, Amit Sharma
PreprintImproving Out-of-Distribution Generalization of Text-Matching Recommendation Systems
Parikshit Bansal, Yashoteja Prabhu, Emre Kiciman, Amit Sharma
NeurIPS CML4Impact Workshop, 2022