About Me

I’m a 2nd year Ph.D. student at Georgia Tech, advised by Judy Hoffman, where my research centers on developing fundamental techniques and algorithms to enhance the efficiency and robustness of deep learning models. Specifically, my interests span efficient deep learning, model merging, transfer learning, bias detection, and robustness. Recently, my work has revolved around fusing fine-tuned models in settings such as multi-task learning, federated learning and continual learning. I have been awarded the Herbert P. Haley fellowship by Georgia Tech for the years 2023-2024.

I earned my masters in ECE in 2022 at Georgia Tech, advised by Rishikesan Kamaleswaran where I worked on machine translation on clinical sensor data as a research assistant.

Research Interest

• Efficient Deep Learning
• Model Merging
• Transfer Learning
• Bias detection & Robustness

email | google scholar | github | linkedin | cv

---

Publications

ZipIt! Merging Models From Different Tasks without Training

George Stoica, Daniel Bolya, Jakob Brandt Bjorner, Pratik Ramesh, Taylor Hearn, Judy Hoffman
International Conference on Learning Representation (ICLR) 2024
(Also presented as an Oral at Workshop on Unifying Representations in Neural Models, NeurIPS 2023)

---

FACTS: First Amplify Correlations and Then Slice to Discover Bias

Sriram Yenamandra, Pratik Ramesh, Viraj Prabhu, Judy Hoffman
International Conference on Computer Vision (ICCV) 2023

---

Locally Aggregated Hierarchical Decomposition-based Ensemble Learning for Robust Face Recognition

Vinay A, Rahul Ragesh, Nikitha Rao, Pratik R, Natarajan S and K.N Balasubramanya Murthy
International Conference on Sustainable Computing in Science, Technology and Management, 2019

---

Face Recognition using Interest Points and Ensemble of Classifiers

A Vinay, Pratik Rajesh Sampat, Sagar V Belavadi, Pratik R, Nikitha Rao B S, Rahul Ragesh, K N Balasubramanya Murthy and S Natarajan
International Conference on Sustainable Computing in Science, Technology and Management, 2019

---