Zobrazeno 1 - 10
of 949
pro vyhledávání: '"Li, YangGuang"'
Autor:
Li, Shilong, He, Yancheng, Guo, Hangyu, Bu, Xingyuan, Bai, Ge, Liu, Jie, Liu, Jiaheng, Qu, Xingwei, Li, Yangguang, Ouyang, Wanli, Su, Wenbo, Zheng, Bo
Long-context capabilities are essential for large language models (LLMs) to tackle complex and long-input tasks. Despite numerous efforts made to optimize LLMs for long contexts, challenges persist in robustly processing long inputs. In this paper, w
Externí odkaz:
http://arxiv.org/abs/2406.14550
Autor:
Zhuo, Le, Du, Ruoyi, Xiao, Han, Li, Yangguang, Liu, Dongyang, Huang, Rongjie, Liu, Wenze, Zhao, Lirui, Wang, Fu-Yun, Ma, Zhanyu, Luo, Xu, Wang, Zehan, Zhang, Kaipeng, Zhu, Xiangyang, Liu, Si, Yue, Xiangyu, Liu, Dingning, Ouyang, Wanli, Liu, Ziwei, Qiao, Yu, Li, Hongsheng, Gao, Peng
Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabili
Externí odkaz:
http://arxiv.org/abs/2406.18583
Autor:
Sheng, Jenny, Lin, Matthieu, Zhao, Andrew, Pruvost, Kevin, Wen, Yu-Hui, Li, Yangguang, Huang, Gao, Liu, Yong-Jin
This paper presents an exploration of preference learning in text-to-motion generation. We find that current improvements in text-to-motion generation still rely on datasets requiring expert labelers with motion capture systems. Instead, learning fro
Externí odkaz:
http://arxiv.org/abs/2404.09445
Autor:
He, Xianglong, Chen, Junyi, Peng, Sida, Huang, Di, Li, Yangguang, Huang, Xiaoshui, Yuan, Chun, Ouyang, Wanli, He, Tong
In recent years, 3D Gaussian splatting has emerged as a powerful technique for 3D reconstruction and generation, known for its fast and high-quality rendering capabilities. To address these shortcomings, this paper introduces a novel diffusion-based
Externí odkaz:
http://arxiv.org/abs/2403.12957
Autor:
Tochilkin, Dmitry, Pankratz, David, Liu, Zexiang, Huang, Zixuan, Letts, Adam, Li, Yangguang, Liang, Ding, Laforte, Christian, Jampani, Varun, Cao, Yan-Pei
This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architecture for fast feed-forward 3D generation, producing 3D mesh from a single image in under 0.5 seconds. Building upon the LRM network architecture, Tripo
Externí odkaz:
http://arxiv.org/abs/2403.02151
Autor:
Liu, Zexiang, Li, Yangguang, Lin, Youtian, Yu, Xin, Peng, Sida, Cao, Yan-Pei, Qi, Xiaojuan, Huang, Xiaoshui, Liang, Ding, Ouyang, Wanli
Recent advancements in text-to-3D generation technology have significantly advanced the conversion of textual descriptions into imaginative well-geometrical and finely textured 3D objects. Despite these developments, a prevalent limitation arises fro
Externí odkaz:
http://arxiv.org/abs/2312.08754
Autor:
Zou, Zi-Xin, Yu, Zhipeng, Guo, Yuan-Chen, Li, Yangguang, Liang, Ding, Cao, Yan-Pei, Zhang, Song-Hai
Recent advancements in 3D reconstruction from single images have been driven by the evolution of generative models. Prominent among these are methods based on Score Distillation Sampling (SDS) and the adaptation of diffusion models in the 3D domain.
Externí odkaz:
http://arxiv.org/abs/2312.09147
Autor:
Huang, Zehuan, Wen, Hao, Dong, Junting, Wang, Yaohui, Li, Yangguang, Chen, Xinyuan, Cao, Yan-Pei, Liang, Ding, Qiao, Yu, Dai, Bo, Sheng, Lu
Generating multiview images from a single view facilitates the rapid generation of a 3D mesh conditioned on a single image. Recent methods that introduce 3D global representation into diffusion models have shown the potential to generate consistent m
Externí odkaz:
http://arxiv.org/abs/2312.06725
Large language models (LLMs) have shown remarkable capabilities in various tasks. However their huge model size and the consequent demand for computational and memory resources also pose challenges to model deployment. Currently, 4-bit post-training
Externí odkaz:
http://arxiv.org/abs/2312.03788
Text-to-3D generation has made remarkable progress recently, particularly with methods based on Score Distillation Sampling (SDS) that leverages pre-trained 2D diffusion models. While the usage of classifier-free guidance is well acknowledged to be c
Externí odkaz:
http://arxiv.org/abs/2310.19415