1 citations · 1 across the 9 of their papers we have counts for
6 papers · 1 filter
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…
Towards One-step Causal Video Generation via Adversarial Self-Distillation
Yongqi Yang, Huayang Huang, Xu Peng +5
Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumul…
Implicit Bias Injection Attacks against Text-to-Image Diffusion Models
Huayang Huang, Xiangye Jin, Jiaxu Miao +1
The proliferation of text-to-image diffusion models (T2I DMs) has led to an increased presence of AI-generated images in daily life. However, biased T2I models can generate content…
Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models
Xiaoliu Guan, Yu Wu, Huayang Huang +3
Diffusion models, known for their tremendous ability to generate high-quality samples, have recently raised concerns due to their data memorization behavior, which poses privacy ri…
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…