8 papers
Agentic Visual Generation: From Generative Models to Agentic Control
Yinming Huang, Shuyuan Tu, Xi Yan +7
Visual generation is evolving from generative models used through a single invocation into agentic control processes that can plan, select tools, inspect intermediate synthesized o…
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
Quanhao Li, Junqiu Yu, Kaixun Jiang +7
Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Exte…
FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance
Quanhao Li, Zhen Xing, Rui Wang +4
Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control al…
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
Shuyuan Tu, Yueming Pan, Yinming Huang +6
Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffus…
DeRA: Decoupled Representation Alignment for Video Tokenization
Pengbo Guo, Junke Wang, Zhen Xing +4
This paper presents DeRA, a novel 1D video tokenizer that decouples the spatial-temporal representation learning in video tokenization to achieve better training efficiency and per…
StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animation
Shuyuan Tu, Zhen Xing, Xintong Han +5
Current diffusion models for human image animation often struggle to maintain identity (ID) consistency, especially when the reference image and driving video differ significantly…
MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
Quanhao Li, Zhen Xing, Rui Wang +3
Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to…
Human2Robot: Learning Robot Actions from Paired Human-Robot Videos
Sicheng Xie, Haidong Cao, Zejia Weng +6
Distilling knowledge from human demonstrations is a promising way for robots to learn and act. Existing methods, which often rely on coarsely-aligned video pairs, are typically con…