Debasmit Das

4

Papers

12

Total Citations

Papers (4)

LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation

CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation

DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization

ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints