|
Udita Ghosh
I am a third-year Ph.D. student in the Vision and Learning Group at the University of California, Riverside, under the supervision of Dr. Amit K. Roy-Chowdhury.
My PhD research focuses on developing sample-efficient algorithms for sequential decision-making agents, with particular emphasis on offline imitation learning and preference-based learning. Additionally, I explore robust uncertainty quantification methods and investigate how large foundation models can enhance planning capabilities in autonomous systems.
Prior to my doctoral studies, I worked as a data scientist for three years after earning my Master's in Computer Science from the Indian Statistical Institute.
Email  / 
CV  / 
Google Scholar  / 
LinkedIn  / 
GitHub
|
|
|
Recent News
  April 2025: Paper accepted at TMLR!
  Feb 2025: Paper accepted at CVPR 2025!
|
Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning
Udita Ghosh, Dripta S Raychaudhuri, Jiachen Li, Konstantinos Karydis and Amit K. Roy-Chowdhury
Under review, 2025
|
Robust Offline Imitation Learning from Diverse Auxiliary Data
Udita Ghosh, Dripta S Raychaudhuri, Jiachen Li, Konstantinos Karydis and Amit K. Roy-Chowdhury
Transactions on Machine Learning Research (TMLR), 2025
|
Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation
Sayak Nag, Udita Ghosh, Calvin-Khang Ta, Sarosij Bose, Jiachen Li and Amit K. Roy-Chowdhury
IEEE/CVF Conference on Computer Vision and Pattern Recognition,, 2025
|
Graph-based Modelling of Superpixels for Identification of Empty Shelves
Bikash Santra*, Udita Ghosh* and Dipti Prasad Mukherjee
Pattern Recognition, 2022
|
Deciphering Environmental Air Pollution with Large Scale City Data
Mayukh Bhattacharyya, Sayan Nag and Udita Ghosh
Thirty-First International Joint Conference on Artificial Intelligence, 2022
|
|