Animesh Jha

I recently completed my MS in CS from Stanford, where I worked with Prof. Sanmi Koyejo on Machine Unlearning.

I interned at Cartesia AI, working with their Serving Infrastructure team. Previously, I was a Software Engineer at Rubrik (Core Infra Team). I completed my B.Tech in CSE at IIT Kharagpur in 2023.

My research interests lie in questions around efficiency, privacy, and robustness of systems. I have had a lot of fun exploring Optimization, Distributed Learning, Differential Privacy, Compilers, and Robotics through my various research experiences.

I helped create the daily word game References, do check it out!

Email  /  CV (June 2026)  /  Github  /  LinkedIn  /  Google Scholar

profile photo
Selected Publications
What to Forget in Unlearning? Forget Set Curation for Language Models
Animesh Jha*, Arpandeep Khatua*, Youssef Allouah, Sanmi Koyejo
MemFM Workshop, ICML 2026
[Paper]
Certified Unlearning for Neural Networks
Anastasia Koloskova*, Youssef Allouah*, Animesh Jha, Rachid Guerraoui, Sanmi Koyejo
ICML 2025
[Paper] [Code]
RL-Guided Data Selection for Language Model Finetuning
Animesh Jha*, Harshit Gupta*, Ananjan Nandi *
{Constrained Optimization for Machine Learning, Reliable ML from Unreliable Data} Workshop NeurIPS 2025
[Paper]
MAEB: Massive Audio Embedding Benchmark
A Assadi, I Chung, C Xiao, R Solomatin, A Jha, R Chand, S Singh, K Wang, A Khan, M Nasser, S Fong, P He, A Xiao, A Munot, A Shrivastava, A Gazizov, N Muennighoff, K Enevoldsen
Under Review NeurIPS 2026
[Paper] [Code]
Local NMPC on Global Optimised Path for Autonomous Racing
Dvij Kalaria*, Parv Maheshwari*, Animesh Jha*, Arnesh Kumar Issar*, Debashish Chakravarty, Sohel Anwar, Andres Tovar,  
OCAR Workshop, ICRA 2021
paper | code

Design and source code from Jon Barron