Zobrazeno 1 - 10
of 4 063
pro vyhledávání: '"Wu, Shang"'
Autor:
Yu, Linhao, Leng, Yongqi, Huang, Yufei, Wu, Shang, Liu, Haixin, Ji, Xinmeng, Zhao, Jiahui, Song, Jinwang, Cui, Tingting, Cheng, Xiaoqing, Liu, Tao, Xiong, Deyi
What a large language model (LLM) would respond in ethically relevant context? In this paper, we curate a large benchmark CMoralEval for morality evaluation of Chinese LLMs. The data sources of CMoralEval are two-fold: 1) a Chinese TV program discuss
Externí odkaz:
http://arxiv.org/abs/2408.09819
Autor:
Li, Zhigen, Peng, Jianxiang, Wang, Yanmeng, Shen, Tianhao, Zhang, Minghui, Su, Linxi, Wu, Shang, Wu, Yihang, Wang, Yuqian, Wang, Ye, Hu, Wei, Li, Jianfeng, Wang, Shaojun, Xiao, Jing, Xiong, Deyi
Controllability and proactivity are crucial properties of autonomous conversational agents (CAs). Controllability requires the CAs to follow the standard operating procedures (SOPs), such as verifying identity before activating credit cards. Proactiv
Externí odkaz:
http://arxiv.org/abs/2407.03884
Multi-person pose estimation (MPPE), which aims to locate the key points for all persons in the frames, is an active research branch of computer vision. Variable human poses and complex scenes make MPPE dependent on local details and global structure
Externí odkaz:
http://arxiv.org/abs/2402.16640
Boosting the task accuracy of tiny neural networks (TNNs) has become a fundamental challenge for enabling the deployments of TNNs on edge devices which are constrained by strict limitations in terms of memory, computation, bandwidth, and power supply
Externí odkaz:
http://arxiv.org/abs/2310.19820
Generalizable Neural Radiance Fields (GNeRF) are one of the most promising real-world solutions for novel view synthesis, thanks to their cross-scene generalization capability and thus the possibility of instant rendering on new scenes. While adversa
Externí odkaz:
http://arxiv.org/abs/2306.06359
Instant on-device Neural Radiance Fields (NeRFs) are in growing demand for unleashing the promise of immersive AR/VR experiences, but are still limited by their prohibitive training time. Our profiling analysis reveals a memory-bound inefficiency in
Externí odkaz:
http://arxiv.org/abs/2305.05766
Despite the growing demand for tuning foundation vision transformers (FViTs) on downstream tasks, fully unleashing FViTs' potential under data-limited scenarios (e.g., few-shot tuning) remains a challenge due to FViTs' data-hungry nature. Common data
Externí odkaz:
http://arxiv.org/abs/2304.12520
Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks. However, the pretrained models are often prohibitively large for deliver
Externí odkaz:
http://arxiv.org/abs/2304.11834
Autor:
Dass, Jyotikrishna, Wu, Shang, Shi, Huihong, Li, Chaojian, Ye, Zhifan, Wang, Zhongfeng, Lin, Yingyan
Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention layers make it possible to embed information globally across the overa
Externí odkaz:
http://arxiv.org/abs/2211.05109