10 papers
Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang +6
While on-policy distillation offers dense supervision for training small reasoning models, its optimization dynamics in the multimodal domain remain under-explored. In this work, w…
TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
Tri Ton, Ji Woo Hong, Chang D. Yoo
This paper introduces Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning (TARO), a novel framework for high-fidelity and temporally coherent video-to-audio sy…
Occlusion-robust Stylization for Drawing-based 3D Animation
Sunjae Yoon, Gwanhyeong Koo, Younghwan Lee +2
3D animation aims to generate a 3D animated video from an input image and a target 3D motion sequence. Recent advances in image-to-3D models enable the creation of animations direc…
FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields
Gwanhyeong Koo, Sunjae Yoon, Younghwan Lee +2
Drag-based editing allows precise object manipulation through point-based control, offering user convenience. However, current methods often suffer from a geometric inconsistency p…
ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On
Ji Woo Hong, Tri Ton, Trung X. Pham +3
This paper introduces ITA-MDT, the Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (IVTON), designed to overcome the limitations of pr…
Selective Query-guided Debiasing for Video Corpus Moment Retrieval
Sunjae Yoon, Ji Woo Hong, Eunseop Yoon +4
Video moment retrieval (VMR) aims to localize target moments in untrimmed videos pertinent to a given textual query. Existing retrieval systems tend to rely on retrieval bias as a…