Zobrazeno 1 - 10
of 1 010
pro vyhledávání: '"ZHANG, Shifeng"'
Autor:
Li, Zhuoyuan, Ai, Yubo, Lu, Jiahao, Wang, ChuXin, Deng, Jiacheng, Chang, Hanzhi, Liang, Yanzhe, Yang, Wenfei, Zhang, Shifeng, Zhang, Tianzhu
Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation cost high, limiting the number of points that can be processed simultaneously and impeding
Externí odkaz:
http://arxiv.org/abs/2406.17442
Autor:
Tudosiu, Petru-Daniel, Yang, Yongxin, Zhang, Shifeng, Chen, Fei, McDonagh, Steven, Lampouras, Gerasimos, Iacobacci, Ignacio, Parisot, Sarah
Text-to-image generation has achieved astonishing results, yet precise spatial controllability and prompt fidelity remain highly challenging. This limitation is typically addressed through cumbersome prompt engineering, scene layout conditioning, or
Externí odkaz:
http://arxiv.org/abs/2404.02790
The objective of the collaborative vehicle-to-everything perception task is to enhance the individual vehicle's perception capability through message communication among neighboring traffic agents. Previous methods focus on achieving optimal performa
Externí odkaz:
http://arxiv.org/abs/2403.16635
Autor:
Zhu, Yu, Sun, Chuxiong, Yang, Wenfei, Wei, Wenqiang, Tang, Bo, Zhang, Tianzhu, Li, Zhiyu, Zhang, Shifeng, Xiong, Feiyu, Hu, Jie, yang, Mingchuan
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values. However, existing RLHF methods require a high computational cost, one main reason being that RLHF assigns bot
Externí odkaz:
http://arxiv.org/abs/2403.04283
Autor:
Xue, Shuchen, Liu, Zhaoqiang, Chen, Fei, Zhang, Shifeng, Hu, Tianyang, Xie, Enze, Li, Zhenguo
Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order nu
Externí odkaz:
http://arxiv.org/abs/2402.17376
Autor:
Xue, Shuchen, Yi, Mingyang, Luo, Weijian, Zhang, Shifeng, Sun, Jiacheng, Li, Zhenguo, Ma, Zhi-Ming
Diffusion Probabilistic Models (DPMs) have achieved considerable success in generation tasks. As sampling from DPMs is equivalent to solving diffusion SDE or ODE which is time-consuming, numerous fast sampling methods built upon improved differential
Externí odkaz:
http://arxiv.org/abs/2309.05019
Due to the ease of training, ability to scale, and high sample quality, diffusion models (DMs) have become the preferred option for generative modeling, with numerous pre-trained models available for a wide variety of datasets. Containing intricate i
Externí odkaz:
http://arxiv.org/abs/2305.18455
Generative model based image lossless compression algorithms have seen a great success in improving compression ratio. However, the throughput for most of them is less than 1 MB/s even with the most advanced AI accelerated chips, preventing them from
Externí odkaz:
http://arxiv.org/abs/2206.05279
Variational autoencoders (VAEs) have witnessed great success in performing the compression of image datasets. This success, made possible by the bits-back coding framework, has produced competitive compression performance across many benchmarks. Howe
Externí odkaz:
http://arxiv.org/abs/2204.02071
Autor:
Wang, Liyuan, Zhang, Xingxing, Yang, Kuo, Yu, Longhui, Li, Chongxuan, Hong, Lanqing, Zhang, Shifeng, Li, Zhenguo, Zhong, Yi, Zhu, Jun
Publikováno v:
ICLR 2022
Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves the state-of-the-art (SOTA) performance. However, existing work is ma
Externí odkaz:
http://arxiv.org/abs/2202.06592