8 papers
Transferability Between Understanding and Generation in Unified Multimodal Models
Jiwon Kang, Heeji Yoon, Jaewoo Jung +5
Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied. We investigate $\bo…
VideoMaMa: Mask-Guided Video Matting via Generative Prior
Sangbeom Lim, Seoung Wug Oh, Jiahui Huang +3
Generalizing video matting models to real-world videos remains a significant challenge due to the scarcity of labeled data. To address this, we present Video Mask-to-Matte Model (V…
Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
Jung Yi, Wooseok Jang, Paul Hyunbin Cho +3
Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion decelerati…
Visual Representation Alignment for Multimodal Large Language Models
Heeji Yoon, Jaewoo Jung, Junwan Kim +10
Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tas…
Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
Chaehyun Kim, Heeseong Shin, Eunbeen Hong +5
Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechani…
URECA: Unique Region Caption Anything
Sangbeom Lim, Junwan Kim, Heeji Yoon +2
Region-level captioning aims to generate natural language descriptions for specific image regions while highlighting their distinguishing features. However, existing methods strugg…