Pixel-space diffusion learns visual representations and image generation jointly in a single end-to-end training stage, without a separately pretrained visual encoder. However, plain pixel-space Transformers still trail leading two-stage latent diffusion models in generation quality and training efficiency. We hypothes...
Xiao-Yu Wu, Yi-Fei Wang, Wei-Hang Guo et al.· 0 citations
Edge intelligence requires models to sense continuously in real time and to keep adapting on-device, all under tight compute, energy, and memory budgets. Although spiking neural networks (SNNs) enable efficient event-driven inference, standard surrogate-gradient backpropagation (BP) serializes updates and blocks ongoin...
Yan-Xun Zhang, Yi-Fei Wang, Chang-Ze Lv et al.· 0 citations
Diffusion distillation is widely adopted to accelerate sampling, and the resulting few-step models are broadly believed to match or even surpass their multi-step teachers in generation. However, standard evaluations such as GenEval2 typically draw only one sample per prompt, so improved scores may fail to reveal losses...
Yi-Fei Wang, Xiao-Yu Wu, Tsu-Jui Fu et al.· 0 citations
Prediction-Aligned Context Compaction (PACC), which uses a learned compressor to aggregate information across past frames into compact memory tokens, shows that learning to compact historical context can improve long-video memory without modifying the underlying generator.
Xiao-Yu Wu, Wei-Hang Guo, Yi-Fei Wang et al.· arXiv.org· 0 citations
The results show that representation need not remain a by-product of generation or merely a tool for improving it: it can be directly optimized as a first-class capability of diffusion pretraining alongside generation.
Xiao-Yu Wu, Yi-Fei Wang, Chen Wei· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.