Zobrazeno 1 - 10
of 1 124
pro vyhledávání: '"CAI, Han"'
Autor:
Cai, Han
Large foundation models play a central role in achieving recent fundamental breakthroughs in artificial intelligence. By simultaneously scaling up the dataset and model size to an unprecedented level, these foundation models demonstrate remarkable pe
Externí odkaz:
https://hdl.handle.net/1721.1/156318
FP8 training has emerged as a promising method for improving training efficiency. Existing frameworks accelerate training by applying FP8 computation to linear layers while leaving optimizer states and activations in higher precision, which fails to
Externí odkaz:
http://arxiv.org/abs/2410.19313
Autor:
Tang, Haotian, Wu, Yecheng, Yang, Shang, Xie, Enze, Chen, Junsong, Chen, Junyu, Zhang, Zhuoyang, Cai, Han, Lu, Yao, Han, Song
We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in image generation quality. Existing AR models face limitations due to t
Externí odkaz:
http://arxiv.org/abs/2410.10812
Autor:
Chen, Junyu, Cai, Han, Chen, Junsong, Xie, Enze, Yang, Shang, Tang, Haotian, Li, Muyang, Lu, Yao, Han, Song
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio (e.g., 8x)
Externí odkaz:
http://arxiv.org/abs/2410.10733
Autor:
Xie, Enze, Chen, Junsong, Chen, Junyu, Cai, Han, Tang, Haotian, Lin, Yujun, Zhang, Zhekai, Li, Muyang, Zhu, Ligeng, Lu, Yao, Han, Song
We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096$\times$4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on l
Externí odkaz:
http://arxiv.org/abs/2410.10629
Autor:
Liu, Xiao, Wang, Jiefei, Mao, Ruosong, Hu, Huizhu, Zhu, Shi-Yao, Xu, Xingqi, Cai, Han, Wang, Da-Wei
Topological physics provides novel insights for designing functional photonic devices, such as magnetic-free optical diodes, which are important in optical engineering and quantum information processing. Past efforts mostly focus on the topological e
Externí odkaz:
http://arxiv.org/abs/2409.17559
Landau levels (LLs) are of great importance for understanding the quantum Hall effect and associated many-body physics. Recently, their three-dimensional (3D) counterparts, i.e., dispersionless 3D LLs with well-defined quantum numbers, have attracted
Externí odkaz:
http://arxiv.org/abs/2409.10785
Autor:
Yang, Jianyu, Li, Nan, Pan, Yuyao, Yang, Jing, Chen, Zhiming, Cai, Han, Wang, Yuliang, Han, Chuankun, Chen, Xingfan, Liu, Cheng, Hu, Huizhu
As a typical application of photon momentum transfer, optical levitation systems are known for their ideal isolation from mechanical dissipation and thermal noise. These characters offer extraordinary potential for acceleration precision sensing and
Externí odkaz:
http://arxiv.org/abs/2408.07348
Multiple optically levitated particles in vacuum can exhibit electrostatic interactions, optical binding, and non-reciprocal light-induced dipole-dipole interactions, making them promising platforms for exploring mesoscopic entanglement and complex i
Externí odkaz:
http://arxiv.org/abs/2408.06256
In this paper, we consider the convertible codes with the maximum distance separable (MDS) property, which can adjust the code rate according to the failure rates of devices. We first extend the notion of convertible codes to allow initial and final
Externí odkaz:
http://arxiv.org/abs/2407.14304