3 papers
cs.CV2026
Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
Sakuya Ota, Qing Yu, Kent Fujiwara +2
Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text. Motion is inherently temporal, especially in composit…
cs.CV2026
ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions
Huakun Liu, Qing Yu, Kent Fujiwara +2
Generating temporally continuous and socially coherent human motion from text remains a fundamental challenge, particularly in realistic streams where people act alone, enter inter…
cs.CV2026
InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation
Qing Yu, Kent Fujiwara
Text-conditioned human interaction generation must capture both long-range temporal causality within each individual and tightly coupled coordination between partners. Existing int…