Munawar Hayat

9

Papers

36

Total Citations

Papers (9)

Erasing Undesirable Influence in Diffusion Models

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

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

Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning

MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans

OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation

HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories

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

Understanding Personal Concept in Open-Vocabulary Semantic Segmentation