2 code implementations • 11 Apr 2024 • Rishabh Ranjan, Saurabh Garg, Mrigank Raman, Carlos Guestrin, Zachary Chase Lipton
This phenomenon is especially prominent in high-noise settings.
no code implementations • 29 Nov 2023 • Mrigank Raman, Rohan Shah, Akash Kannan, Pranit Chawla
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.
no code implementations • 31 Jul 2023 • Kousik Rajesh, Mrigank Raman, Mohammed Asad Karim, Pranit Chawla
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 embeddings into the text space and then use the auto-regressive capacity to solve tasks such as VQA, captioning, and image retrieval.
1 code implementation • 13 Mar 2023 • Mrigank Raman, Pratyush Maini, J. Zico Kolter, Zachary C. Lipton, Danish Pruthi
Across 5 NLP datasets, 4 adversarial attacks, and 3 different models, MVP improves performance against adversarial substitutions by an average of 8% over standard methods and even outperforms adversarial training-based state-of-art defenses by 3. 5%.
no code implementations • CVPR 2021 • Prashant Pandey, Mrigank Raman, Sumanth Varambally, Prathosh AP
Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem.
no code implementations • 1 Mar 2021 • Prashant Pandey, Mrigank Raman, Sumanth Varambally, Prathosh AP
Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem.
no code implementations • 1 Jan 2021 • Jun Yan, Mrigank Raman, Tianyu Zhang, Ryan Rossi, Handong Zhao, Sungchul Kim, Nedim Lipka, Xiang Ren
Recently, neural-symbolic architectures have achieved success on commonsense reasoning through effectively encoding relational structures retrieved from external knowledge graphs (KGs) and obtained state-of-the-art results in tasks such as (commonsense) question answering and natural language inference.
no code implementations • 30 Oct 2020 • Mrigank Raman, Ojal Kumar, Arpan Chattopadhyay
A Lagrangian relaxation of the problem is solved by an artful blending of two tools: Gibbs sampling for MSE minimization and an on-line version of expectation maximization (EM) to estimate the unknown TPM.
1 code implementation • Findings (ACL) 2021 • Jun Yan, Mrigank Raman, Aaron Chan, Tianyu Zhang, Ryan Rossi, Handong Zhao, Sungchul Kim, Nedim Lipka, Xiang Ren
Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks.
1 code implementation • ICLR 2021 • Mrigank Raman, Aaron Chan, Siddhant Agarwal, Peifeng Wang, Hansen Wang, Sungchul Kim, Ryan Rossi, Handong Zhao, Nedim Lipka, Xiang Ren
Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation.
no code implementations • 28 Jul 2020 • Prashant Pandey, Mrigank Raman, Sumanth Varambally, Prathosh AP
Features extracted from this source domain are learned using a generative model whose latent space is used as a sampler to retrieve the nearest neighbors for the target data points.