14 papers · 1 filter
Real-Time Visual Attribution Streaming in Thinking Model
Seil Kang, Woojung Han, Junhyeok Kim +3
We present an amortized framework for real-time visual attribution streaming in multimodal thinking models. When these models generate code from a screenshot or solve math problems…
ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting
Yeonkyung Lee, Dayun Ju, Youngmin Kim +2
Recent advancements in Video Large Language Models (VideoLLMs) have enabled strong performance across diverse multimodal video tasks. To reduce the high computational cost of proce…
Anchoring and Rescaling Attention for Semantically Coherent Inbetweening
Tae Eun Choi, Sumin Shim, Junhyeok Kim +1
Generative inbetweening (GI) seeks to synthesize realistic intermediate frames between the first and last keyframes beyond mere interpolation. As sequences become sparser and motio…
Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
Youngjun Jun, Seil Kang, Woojung Han +1
Video Diffusion Transformers (DiTs) have been synthesizing high-quality video with high fidelity from given text descriptions involving motion. However, understanding how Video DiT…
Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models
Jinyeong Kim, Seil Kang, Jiwoo Park +2
Large Vision-Language Models (LVLMs) answer visual questions by transferring information from images to text through a series of attention heads. While this image-to-text informati…
Interpreting vision transformers via residual replacement model
Jinyeong Kim, Junhyeok Kim, Yumin Shim +3
How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across al…