Zobrazeno 1 - 10
of 160
pro vyhledávání: '"Liu, Xingchao"'
Diffusion models excel in high-quality generation but suffer from slow inference due to iterative sampling. While recent methods have successfully transformed diffusion models into one-step generators, they neglect model size reduction, limiting thei
Externí odkaz:
http://arxiv.org/abs/2407.12718
Autor:
Yang, Ling, Zhang, Zixiang, Zhang, Zhilong, Liu, Xingchao, Xu, Minkai, Zhang, Wentao, Meng, Chenlin, Ermon, Stefano, Cui, Bin
Flow matching (FM) is a general framework for defining probability paths via Ordinary Differential Equations (ODEs) to transform between noise and data samples. Recent approaches attempt to straighten these flow trajectories to generate high-quality
Externí odkaz:
http://arxiv.org/abs/2407.02398
Autor:
Li, Zhimin, Zhang, Jianwei, Lin, Qin, Xiong, Jiangfeng, Long, Yanxin, Deng, Xinchi, Zhang, Yingfang, Liu, Xingchao, Huang, Minbin, Xiao, Zedong, Chen, Dayou, He, Jiajun, Li, Jiahao, Li, Wenyue, Zhang, Chen, Quan, Rongwei, Lu, Jianxiang, Huang, Jiabin, Yuan, Xiaoyan, Zheng, Xiaoxiao, Li, Yixuan, Zhang, Jihong, Zhang, Chao, Chen, Meng, Liu, Jie, Fang, Zheng, Wang, Weiyan, Xue, Jinbao, Tao, Yangyu, Zhu, Jianchen, Liu, Kai, Lin, Sihuan, Sun, Yifu, Li, Yun, Wang, Dongdong, Chen, Mingtao, Hu, Zhichao, Xiao, Xiao, Chen, Yan, Liu, Yuhong, Liu, Wei, Wang, Di, Yang, Yong, Jiang, Jie, Lu, Qinglin
We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build f
Externí odkaz:
http://arxiv.org/abs/2405.08748
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via the reflow
Externí odkaz:
http://arxiv.org/abs/2405.07510
Recent works have demonstrated success in controlling sentence attributes ($e.g.$, sentiment) and structure ($e.g.$, syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for generating high
Externí odkaz:
http://arxiv.org/abs/2403.16995
Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient policy generato
Externí odkaz:
http://arxiv.org/abs/2402.04292
Diffusion models have revolutionized text-to-image generation with its exceptional quality and creativity. However, its multi-step sampling process is known to be slow, often requiring tens of inference steps to obtain satisfactory results. Previous
Externí odkaz:
http://arxiv.org/abs/2309.06380
AI tasks encompass a wide range of domains and fields. While numerous AI models have been designed for specific tasks and applications, they often require considerable human efforts in finding the right model architecture, optimization algorithm, and
Externí odkaz:
http://arxiv.org/abs/2305.02499
Autor:
Wu, Lemeng, Wang, Dilin, Gong, Chengyue, Liu, Xingchao, Xiong, Yunyang, Ranjan, Rakesh, Krishnamoorthi, Raghuraman, Chandra, Vikas, Liu, Qiang
Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the co
Externí odkaz:
http://arxiv.org/abs/2212.01747
Retriever-reader models achieve competitive performance across many different NLP tasks such as open question answering and dialogue conversations. In this work, we notice these models easily overfit the top-rank retrieval passages and standard train
Externí odkaz:
http://arxiv.org/abs/2211.00915