collaborators

13 papers

cs.CL2025

Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs

Ayush Gupta, Ramneet Kaur, Anirban Roy +3

We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain…

cs.LG2025

Privacy Preserving In-Context-Learning Framework for Large Language Models

Bishnu Bhusal, Manoj Acharya, Ramneet Kaur +5

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive in…

cs.LG2025

Taylor-Model Physics-Informed Neural Networks (PINNs) for Ordinary Differential Equations

Chandra Kanth Nagesh, Sriram Sankaranarayanan, Ramneet Kaur +2

We study the problem of learning neural network models for Ordinary Differential Equations (ODEs) with parametric uncertainties. Such neural network models capture the solution to…

cs.LG2025

Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference

Colin Samplawski, Adam D. Cobb, Manoj Acharya +2

Despite their widespread use, large language models (LLMs) are known to hallucinate incorrect information and be poorly calibrated. This makes the uncertainty quantification of the…

cs.CV2025

TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision

Ayush Gupta, Anirban Roy, Rama Chellappa +3

We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question,…

cs.LG2025

Backpropagation-Free Metropolis-Adjusted Langevin Algorithm

Adam D. Cobb, Susmit Jha

Recent work on backpropagation-free learning has shown that it is possible to use forward-mode automatic differentiation (AD) to perform optimization on differentiable models. Forw…