3 papers
cs.CV2026
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
Hanbo Cheng, Limin Lin, Ruo Zhang +2
Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing…
cs.CV2025
From Structure to Detail: Hierarchical Distillation for Efficient Diffusion Model
Hanbo Cheng, Peng Wang, Kaixiang Lei +4
The inference latency of diffusion models remains a critical barrier to their real-time application. While trajectory-based and distribution-based step distillation methods offer s…
cs.CV2025
DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation
Hanbo Cheng, Limin Lin, Chenyu Liu +5
Talking head generation intends to produce vivid and realistic talking head videos from a single portrait and speech audio clip. Although significant progress has been made in diff…