Youngjae Yu

8

Papers

11

Total Citations

Papers (8)

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos

Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation

MASS: Overcoming Language Bias in Image-Text Matching

DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation

V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models

VAGUE: Visual Contexts Clarify Ambiguous Expressions