9 citations · 19 across the 7 of their papers we have counts for
8 papers
Turn Down the Noise: Leveraging Diffusion Models for Test-time Adaptation via Pseudo-label Ensembling
Mrigank Raman, Rohan Shah, Akash Kannan +1
The goal of test-time adaptation is to adapt a source-pretrained model to a continuously changing target domain without relying on any source data. Typically, this is either done b…
Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks
Kousik Rajesh, Mrigank Raman, Mohammed Asad Karim +1
In recent times there has been a surge of multi-modal architectures based on Large Language Models, which leverage the zero shot generation capabilities of LLMs and project image e…
Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Mrigank Raman, Pratyush Maini, J. Zico Kolter +2
In recent years, NLP practitioners have converged on the following practice: (i) import an off-the-shelf pretrained (masked) language model; (ii) append a multilayer perceptron ato…
Domain Generalization via Inference-time Label-Preserving Target Projections
Prashant Pandey, Mrigank Raman, Sumanth Varambally +1
Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem. While many approaches hav…
Centralized active tracking of a Markov chain with unknown dynamics
Mrigank Raman, Ojal Kumar, Arpan Chattopadhyay
In this paper, selection of an active sensor subset for tracking a discrete time, finite state Markov chain having an unknown transition probability matrix (TPM) is considered. A t…
Learning Contextualized Knowledge Structures for Commonsense Reasoning
Jun Yan, Mrigank Raman, Aaron Chan +6
Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/…
Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
Mrigank Raman, Aaron Chan, Siddhant Agarwal +7
Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation. By using attention over…
Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors
Prashant Pandey, Mrigank Raman, Sumanth Varambally +1
Domain generalization (DG) deals with the problem of domain shift where a machine learning model trained on multiple-source domains fail to generalize well on a target domain with…