2 citations · 2 across the 2 of their papers we have counts for
5 papers
ReState: Noise-Level-Aware State Correction for Training-Free Object Removal in Few-Step Diffusion Models
Donghwan Lee, Sanghyun Jo, Sihyun Kim +2
Training-free object removal commonly redirects self-attention away from the target region, but on few-step distilled diffusion models this often leaves object-shaped residuals. We…
Depth-to-RGB: Repurposing a Frozen Depth Estimator for Geometry-Guided Compositing
Sanghyun Jo, Chae Yeon Lim, Donghwan Lee +3
Reference-based object compositing inserts or replaces an object using a background image, a reference image, and a 2D compositing mask. These inputs guide appearance and placement…
EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
Sanghyun Jo, Donghwan Lee, Eunji Jung +2
Object removal must prevent the masked target from reappearing and reconstruct the occluded background with structural and contextual fidelity, rather than merely filling a hole pl…
Adaptive Policy Backbone via Shared Network
Bumgeun Park, Donghwan Lee
Reinforcement learning (RL) has achieved impressive results across domains, yet learning an optimal policy typically requires extensive interaction data, limiting practical deploym…
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
Behrad Moniri, Donghwan Lee, Hamed Hassani +1
Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks u…