---

Publications

Below is a list of my recent publications. For a more complete list, please visit my Google Scholar.

2025

• Fundamental Limits of Perfect Concept Erasure
  Somnath Basu Roy Chowdhury, Avinava Dubey, Ahmad Beirami, Rahul Kidambi, Nicholas Monath, Amr Ahmed, Snigdha Chaturvedi.
  Proceedings of AISTATS, 2025.
  pdf code slides poster long


• Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
  Somnath Basu Roy Chowdhury, Krzysztof Choromanski, Arijit Sehanobish, Avinava Dubey, Snigdha Chaturvedi.
  Proceedings of ICLR, 2025.
  Preliminary version at Safe Gen AI Workshop, NeurIPS, 2024.
  pdf code slides poster long


• Exploring Safety-Utility Trade-Offs in Personalized Language Models
  Anvesh Rao Vijjini*, Somnath Basu Roy Chowdhury*, Snigdha Chaturvedi.
  Proceedings of NAACL, 2025.
  pdf code slides long Oral

2024

• Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
  Arijit Sehanobish*, Avinava Dubey*, Krzysztof Choromanski*, Somnath Basu Roy Chowdhury*, Deepali Jain, Vikas Sindhwani, S. Chaturvedi.
  Proceedings of NeurIPS, 2024.
  pdf code slides poster long


• Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
  Krzysztof Choromanski*, Arijit Sehanobish*, Somnath Basu Roy Chowdhury*, Han Lin*, Avinava Dubey*, Tamas Sarlos, Snigdha Chaturvedi.
  Proceedings of NeurIPS, 2024.
  pdf code slides poster long


• Embodied AI with Two Arms: Zero-shot Learning, Safety and Modularity
  Jake Varley*, Sumeet Singh*, Deepali Jain*, Krzysztof Choromanski*, Andy Zeng, Somnath Basu Roy Chowdhury, Avinava Dubey, Vikas Sindhwani.
  Proceedings of IROS, 2024.
  🏆 Best RoboCup Paper Award
  🏆 Nominated for the Best Safety, Security, and Rescue Robotics Papers
  pdf long Project Page Oral


• Incremental Extractive Opinion Summarization Using Cover Trees
  Somnath Basu Roy Chowdhury, Nicholas Monath, Avinava Dubey, Manzil Zaheer, Andrew McCallum, Amr Ahmed, Snigdha Chaturvedi.
  Proceedings of TMLR, 2024.
  pdf code long


• Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
  Somnath Basu Roy Chowdhury, Nicholas Monath, Ahmad Beirami, Rahul Kidambi, Avinava Dubey, Amr Ahmed, Snigdha Chaturvedi.
  Proceedings of ICLR, 2024.
  pdf code slides poster long Spotlight

2023

• Robust Concept Erasure via Kernelized Rate-Distortion Maximization
  Somnath Basu Roy Chowdhury, Nicholas Monath, Avinava Dubey, Amr Ahmed, Snigdha Chaturvedi.
  Proceedings of NeurIPS, 2023.
  pdf code slides poster long


• Unsupervised Opinion Summarization Using Approximate Geodesics
  Somnath Basu Roy Chowdhury, Nicholas Monath, Avinava Dubey, Amr Ahmed, Snigdha Chaturvedi.
  Proceedings of EMNLP Findings, 2023.
  pdf slides poster long


• Sustaining Fairness via Incremental Learning
  Somnath Basu Roy Chowdhury and Snigdha Chaturvedi.
  Proceedings of AAAI, 2023.
  pdf code slides poster long Oral


• Efficient Graph Field Integrators Meet Point Clouds
  Krzysztof Choromanski*, Arijit Sehanobish*, Han Lin*, Yunfan Zhao*, Eli Berger, Tetiana Parshakova, Alvin Pan, David Watkins, Tianyi Zhang, Valerii Likhosherstov, Somnath Basu Roy Chowdhury, Avinava Dubey, Deepali Jain, Tamas Sarlos, Snigdha Chaturvedi, Adrian Weller.
  Proceedings of ICML, 2023.
  pdf code slides poster long


• Aspect-aware Unsupervised Extractive Opinion Summarization
  Haoyuan Li, Somnath Basu Roy Chowdhury, Snigdha Chaturvedi.
  Proceedings of ACL Findings, 2023.
  pdf code slides long

2022

• Unsupervised Extractive Opinion Summarization Using Sparse Coding
  Somnath Basu Roy Chowdhury, Chao Zhao, Snigdha Chaturvedi.
  Proceedings of ACL, 2022.
  pdf code slides poster long


• Read Top News First: A Document Reordering Approach for Multi-document News Summarization
  Chao Zhao*, Tenghao Huang*, Somnath Basu Roy Chowdhury, M Chandrasekaran, Kathleen McKeown, Snigdha Chaturvedi.
  Proceedings of ACL Findings, 2022.
  pdf code slides poster short


• Learning Fair Representations via Rate-Distortion Maximization
  Somnath Basu Roy Chowdhury and Snigdha Chaturvedi.
  Proceedings of TACL, 2022.
  pdf code slides long MIT Press Oral (EMNLP '22)

2021

• Adversarial Scrubbing of Demographic Information for Text Classification
  Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier Oliva, Shashank Srivastava, Snigdha Chaturvedi.
  Proceedings of EMNLP, 2021.
  pdf code slides poster long


• Is Everything in Order? A Simple Way to Order Sentences
  Somnath Basu Roy Chowdhury*, Faeze Brahman*, Snigdha Chaturvedi.
  Proceedings of EMNLP, 2021.
  pdf code slides poster long


• Does Commonsense help in detecting Sarcasm?
  Somnath Basu Roy Chowdhury and Snigdha Chaturvedi.
  Proceedings of Insights from Negative Results in NLP Workshop @ EMNLP, 2021.
  pdf code slides short

2016-2019

(before PhD)

• Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural Language` Processing
  K M Annervaz*, Somnath Basu Roy Chowdhury*, Ambedkar Dukkipati.
  Proceedings of the NAACL, 2018.
  pdf code long Oral


• Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing
  Somnath Basu Roy Chowdhury, K M Annervaz, Ambedkar Dukkipati.
  Proceedings of DeepLo Workshop, EMNLP 2019.
  pdf code long


• AdGAP: Advanced Global Average Pooling
  Arna Ghosh, Biswarup Bhattacharya*, Somnath Basu Roy Chowdhury*.
  Proceedings of the AAAI 2018. (Student Abstract and Poster Program).
  pdf code poster


• Training Autoencoders in Sparse Domain
  Biswarup Bhattacharya, Arna Ghosh*, Somnath Basu Roy Chowdhury*.
  Proceedings of the AAAI 2018. (Student Abstract and Poster Program).
  pdf poster


• Handwriting Profiling using Generative Adversarial Networks
  Arna Ghosh*, Biswarup Bhattacharya*, Somnath Basu Roy Chowdhury*.
  Proceedings of the AAAI 2017. (Student Abstract and Poster Program).
  pdf poster


• SAD-GAN: Synthetic Autonomous Driving using Generative Adversarial Networks
  Arna Ghosh*, Biswarup Bhattacharya*, and Somnath Basu Roy Chowdhury*.
  Proceedings of the DLAI Workshop, NeurIPS 2016.
  pdf code short

(* = equal contribution)