Showing 2026Show all
2 papers · 1 filter
cs.CV2026
TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models
Chao Zhou, Yiling Chen, Qi Chu +3
Although pretrained joint audio-visual diffusion models offer rich control over \emph{what} to generate, they provide no explicit control over \emph{when} an utterance should occur…
cs.CV2026
Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping
Chao Zhou, Tianyi Wei, Yiling Chen +2
While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subjec…