Deep compression autoencoder for efficient high-resolution diffusion models

J Chen, H Cai, J Chen, E **e, S Yang, H Tang… - arxiv preprint arxiv …, 2024 - arxiv.org
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models
for accelerating high-resolution diffusion models. Existing autoencoder models have …

Real-time video generation with pyramid attention broadcast

X Zhao, X **, K Wang, Y You - arxiv preprint arxiv:2408.12588, 2024 - arxiv.org
We present Pyramid Attention Broadcast (PAB), a real-time, high quality and training-free
approach for DiT-based video generation. Our method is founded on the observation that …

Efficient diffusion models: A comprehensive survey from principles to practices

Z Ma, Y Zhang, G Jia, L Zhao, Y Ma, M Ma… - arxiv preprint arxiv …, 2024 - arxiv.org
As one of the most popular and sought-after generative models in the recent years, diffusion
models have sparked the interests of many researchers and steadily shown excellent …

Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models

M Li, Y Lin, Z Zhang, T Cai, X Li, J Guo, E **e… - arxiv preprint arxiv …, 2024 - arxiv.org
Diffusion models have been proven highly effective at generating high-quality images.
However, as these models grow larger, they require significantly more memory and suffer …

Linfusion: 1 gpu, 1 minute, 16k image

S Liu, W Yu, Z Tan, X Wang - arxiv preprint arxiv:2409.02097, 2024 - arxiv.org
Modern diffusion models, particularly those utilizing a Transformer-based UNet for
denoising, rely heavily on self-attention operations to manage complex spatial relationships …

Diffusion models meet remote sensing: Principles, methods, and perspectives

Y Liu, J Yue, S **a, P Ghamisi, W **e… - arxiv preprint arxiv …, 2024 - arxiv.org
As a newly emerging advance in deep generative models, diffusion models have achieved
state-of-the-art results in many fields, including computer vision, natural language …

Video-infinity: Distributed long video generation

Z Tan, X Yang, S Liu, X Wang - arxiv preprint arxiv:2406.16260, 2024 - arxiv.org
Diffusion models have recently achieved remarkable results for video generation. Despite
the encouraging performances, the generated videos are typically constrained to a small …

Artificial intelligence for biomedical video generation

L Li, J Qiu, A Saha, L Li, P Li, M He, Z Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
As a prominent subfield of Artificial Intelligence Generated Content (AIGC), video generation
has achieved notable advancements in recent years. The introduction of Sora-alike models …

How Far Are We From AGI

T Feng, C **, J Liu, K Zhu, H Tu, Z Cheng… - arxiv preprint arxiv …, 2024 - arxiv.org
The evolution of artificial intelligence (AI) has profoundly impacted human society, driving
significant advancements in multiple sectors. Yet, the escalating demands on AI have …

Ascan: Asymmetric convolution-attention networks for efficient recognition and generation

A Kag, H Coskun, J Chen, J Cao, W Menapace… - arxiv preprint arxiv …, 2024 - arxiv.org
Neural network architecture design requires making many crucial decisions. The common
desiderata is that similar decisions, with little modifications, can be reused in a variety of …