2 citations · 2 across the 7 of their papers we have counts for
7 papers
Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
Anurag Roy, Riddhiman Moulick, Vinay Kumar Verma +2
In many real-world scenarios, encountering continual shifts in domain during inference is very common. Consequently, continual test-time adaptation (CTTA) techniques leveraging a t…
PRISM: Demystifying Retention and Interaction in Mid-Training
Bharat Runwal, Ashish Agrawal, Anurag Roy +1
We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four fa…
TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Zhangchen Xu, Adriana Meza Soria, Shawn Tan +4
Large Language Model (LLM) agents are rapidly emerging as powerful systems for automating tasks across domains. Yet progress in the open-source community is constrained by the lack…
Convolutional Prompting meets Language Models for Continual Learning
Anurag Roy, Riddhiman Moulick, Vinay K. Verma +2
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transfo…
Exemplar-Free Continual Transformer with Convolutions
Anurag Roy, Vinay Kumar Verma, Sravan Voonna +3
Continual Learning (CL) involves training a machine learning model in a sequential manner to learn new information while retaining previously learned tasks without the presence of…
Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasets
Anurag Roy, David Johnson Ekka, Saptarshi Ghosh +1
Generating natural language questions from visual scenes, known as Visual Question Generation (VQG), has been explored in the recent past where large amounts of meticulously labele…
ZSCRGAN: A GAN-based Expectation Maximization Model for Zero-Shot Retrieval of Images from Textual Descriptions
Anurag Roy, Vinay Kumar Verma, Kripabandhu Ghosh +1
Most existing algorithms for cross-modal Information Retrieval are based on a supervised train-test setup, where a model learns to align the mode of the query (e.g., text) to the m…