Fatih Porikli

9

Papers

50

Total Citations

Papers (9)

Distilling Multi-modal Large Language Models for Autonomous Driving

Clockwork Diffusion: Efficient Generation With Model-Step Distillation

DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions

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

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

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

Understanding Personal Concept in Open-Vocabulary Semantic Segmentation

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

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