8 papers
Towards Continuous Sign Language Conversation from Isolated Signs
Youngmin Kim, Kyobin Choo, Jiwoo Park +4
Sign language is the primary language for many Deaf and Hard-of-Hearing (DHH) signers, yet most conversational AI systems still mediate interaction through spoken or written langua…
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…
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…
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…
Backbone Augmented Training for Adaptations
Jae Wan Park, Junhyeok Kim, Youngjun Jun +2
Adaptations facilitate efficient training of large backbone models, including diffusion models for image generation and transformer-based language models. While various adaptation…