Full Professor, Texas A&M
3 papers at NeurIPS 2025
We propose Contextual Low-Rank Adaptation (C-LoRA), an uncertainty-aware, parameter-efficient fine-tuning approach by developing lightweight, data-dependent LoRA modules that dynamically adapt uncertainties for robust and calibrated predictions.
Graph-based symbolic regression that captures expression equivalences on graph representations and incorporate constrained search utilizing hybrid neural-guided Monte-Carlo tree search.
