6 papers
Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
Taekyung Ki, Sangwon Jang, Jaehyeong Jo +2
Talking head generation creates lifelike avatars from static portraits for virtual communication and content creation. However, current models do not yet convey the feeling of trul…
Self-Refining Video Sampling
Sangwon Jang, Taekyung Ki, Jaehyeong Jo +3
Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additio…
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
Woongyeong Yeo, Kangsan Kim, Jaehong Yoon +1
Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highl…
Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
Sangwon Jang, Taekyung Ki, Jaehyeong Jo +4
Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tunin…
Continual Learning: Forget-free Winning Subnetworks for Video Representations
Haeyong Kang, Jaehong Yoon, Sung Ju Hwang +1
Inspired by the Lottery Ticket Hypothesis (LTH), which highlights the existence of efficient subnetworks within larger, dense networks, a high-performing Winning Subnetwork (WSN) i…
Concept-skill Transferability-based Data Selection for Large Vision-Language Models
Jaewoo Lee, Boyang Li, Sung Ju Hwang
Instruction tuning, or supervised finetuning on extensive task-specific data, is necessary for Large Vision-Language Models (LVLMs) to generalize well across a broad range of visio…