Koyel Mukherjee

My research interests are primarily in Algorithms and Optimization, with a focus on scheduling, resource allocation, cost and performance optimization problems. I am also interested in neural networks and predictive modelling, and in particular, in automating and generalising training algorithms for deep neural networks.

I obtained my Ph.D. in Computer Science from University of Maryland, College Park in December, 2013. Prior to Adobe, I have been with Xerox Research (2014-2016), IBM Research (2017-2020) and Games24x7 (2020-2021).

In Adobe, I am currently working in the Systems area, designing algorithms and models for optimising costs as well as performance for data storage. I am also interested in Data Summarization and Data Story Telling from an algorithmic viewpoint.

Apart from work, I love travelling, music and spending time with my family.

AI & Machine Learning Data Intelligence Intelligent Agents & Assistants

Publications

July 2, 2026 Association for Computational Linguistics Findings (ACL 2026)

An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA

Saransh Sharma, Aparna Garimella, Koyel Mukherjee, Sharma

November 4, 2025 Conference on Empirical Methods in Natural Language Processing Findings (EMNLP 2025)

FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction

Akriti Jain, Saransh Sharma, Koyel Mukherjee, Soumyabrata Pal

August 1, 2025 ACL 2025

From Selection to Generation: A Survey of LLM-based Active Learning

Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu, Xintong Li, Ryan Aponte, Hanjia Lyu, Joe Barrow, Hongjie Chen, Franck Dernoncourt, Branislav Kveton, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Sungchul Kim, Zhengmian Hu, Yue Zhao, Nedim Lipka, David Seunghyun Yoon, Ting-Hao Kenneth Huang, Zichao Wang, Puneet Mathur, Soumyabrata Pal, Koyel Mukherjee, Zhehao Zhang, Namyong Park, Thien Huu Nguyen, Jiebo Luo, Ryan A. Rossi, Julian McAuley

April 29, 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)

PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks

Soumya Suvra Ghosal, Soumyabrata Pal, Koyel Mukherjee, Dinesh Manocha

June 9, 2024 International Conference on Management of Data (SIGMOD)

Koyel Mukherjee

Publications

An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA

FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction

From Selection to Generation: A Survey of LLM-based Active Learning

PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks

R2D2: Reducing Redundancy and Duplication in Data Lakes

Approximate Caching for Efficiently Serving Diffusion Models

Flash: Concept Drift Adaptation in Federated Learning

Towards Optimizing Storage Costs on the Cloud