5 papers
The Anatomy of Uncertainty in LLMs
Aditya Taparia, Ransalu Senanayake, Kowshik Thopalli +1
Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment. Current approaches, which either provide a single uncerta…
Improving Robustness In Sparse Autoencoders via Masked Regularization
Vivek Narayanaswamy, Kowshik Thopalli, Bhavya Kailkhura +1
Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for i…
On The Role of Prompt Construction In Enhancing Efficacy and Efficiency of LLM-Based Tabular Data Generation
Banooqa Banday, Kowshik Thopalli, Tanzima Z. Islam +1
LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that en…
Leveraging Registers in Vision Transformers for Robust Adaptation
Srikar Yellapragada, Kowshik Thopalli, Vivek Narayanaswamy +5
Vision Transformers (ViTs) have shown success across a variety of tasks due to their ability to capture global image representations. Recent studies have identified the existence o…
Physics-Informed Transformation Toward Improving the Machine-Learned NLTE Models of ICF Simulations
Min Sang Cho, Paul E. Grabowski, Kowshik Thopalli +11
The integration of machine learning techniques into Inertial Confinement Fusion (ICF) simulations has emerged as a powerful approach for enhancing computational efficiency. By repl…