Mihir Thalanki

According to our database, Mihir Thalanki authored at least 3 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning.

Anh C. Pham, Mihir Thalanki, Michael Sun, Aditya Chaloo, Ankita Gupta, Tian Xia, Aditya Mate, Ehimwenma Nosakhare, Soundararajan Srinivasan

CoRR, October, 2025

How to Fine-Tune Safely on a Budget: Model Adaptation Using Minimal Resources.

Anh C. Pham, Mihir Thalanki, Michael Sun, Aditya Chaloo, Ankita Gupta, Tian Xia, Aditya Mate, Ehi Nosakhare, Soundararajan Srinivasan

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2023

Building Extensible Model for Healthcare Resource Allocation Using Model-Driven Approach.

Rizwan Parveen, Ashin Laurel R, Mihir Thalanki, Neena Goveas, Shubhangi K. Gawali

Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 2023