4 papers
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
Ruoyu Wang, Jialun Liu, Huayang Huang +5
Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic fail…
Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment
Huayang Huang, Ruoyu Wang, Jinhui Zhao +5
Generative distillation significantly accelerates text-to-image (T2I) generation by compressing multi-step trajectories into few-step student models while preserving perceptual qua…
The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation
Ruoyu Wang, Huayang Huang, Ye Zhu +2
In this work, we introduce NoiseQuery as a novel method for enhanced noise initialization in versatile goal-driven text-to-image (T2I) generation. Specifically, we propose to lever…
SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
Yuhan Pei, Ruoyu Wang, Yongqi Yang +3
Originating from the diffusion phenomenon in physics, which describes the random movement and collisions of particles, diffusion generative models simulate a random walk in the dat…