4 papers
Shallow-Ï: Knowledge Distillation for Flow-based VLAs
Boseong Jeon, Yunho Choi, Taehan Kim
The growing demand for real-time robotic deployment necessitates fast and on-device inference for vision-language-action (VLA) models. Within the VLA literature, efficiency has bee…
CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement
Boseong Jeon, Junghyuk Lee, Jimin Park +4
Recent works on object removal and insertion have enhanced their performance by handling object effects such as shadows and reflections, using diffusion models trained on counterfa…
ControlFill: Spatially Adjustable Image Inpainting from Prompt Learning
Boseong Jeon
In this report, I present an inpainting framework named \textit{ControlFill}, which involves training two distinct prompts: one for generating plausible objects within a designated…
SPG: Improving Motion Diffusion by Smooth Perturbation Guidance
Boseong Jeon
This paper presents a test-time guidance method to improve the output quality of the human motion diffusion models without requiring additional training. To have negative guidance,…