Zobrazeno 1 - 10
of 99
pro vyhledávání: '"Jin, Yanzi"'
Autor:
Horton, Maxwell, Cao, Qingqing, Sun, Chenfan, Jin, Yanzi, Mehta, Sachin, Rastegari, Mohammad, Nabi, Moin
Inference with transformer-based language models begins with a prompt processing step. In this step, the model generates the first output token and stores the KV cache needed for future generation steps. This prompt processing step can be computation
Externí odkaz:
http://arxiv.org/abs/2410.08391
This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant strides in imp
Externí odkaz:
http://arxiv.org/abs/2409.09018
Autor:
Mehta, Sachin, Sekhavat, Mohammad Hossein, Cao, Qingqing, Horton, Maxwell, Jin, Yanzi, Sun, Chenfan, Mirzadeh, Iman, Najibi, Mahyar, Belenko, Dmitry, Zatloukal, Peter, Rastegari, Mohammad
The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and enabling investigations into data and model biases, as well as potential risks. To this end, we releas
Externí odkaz:
http://arxiv.org/abs/2404.14619
Over the past several years, the synchronization between audio and visual signals has been leveraged to learn richer audio-visual representations. Aided by the large availability of unlabeled videos, many unsupervised training frameworks have demonst
Externí odkaz:
http://arxiv.org/abs/2310.03937
Autor:
Chen, Rong, Li, Mengyun, Tan, Bofei, Li, Sihui, Jia, Xiaodan, Zhang, Qing, Xu, Xianrui, Liu, Qiang, Ma, Zeli, Li, Xuan, Wang, Ying, Tian, Nan, Jin, Yanzi
Publikováno v:
In Epilepsy & Behavior October 2024 159
Publikováno v:
In Journal of Power Sources 30 September 2024 615
Autor:
Tan, Bofei, Xu, Xianrui, Liu, Qiang, Chen, Rong, Chen, Qiuyan, Qin, Yameng, Li, Mengyun, Wang, Xu, Yang, Ping, Jin, Yanzi, Jia, Xiaodan, Zhang, Qing
Publikováno v:
In Epilepsy & Behavior September 2024 158
We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independent layer-wise compressions. We show how to efficiently generate layer-
Externí odkaz:
http://arxiv.org/abs/2011.09058
Autor:
Tan, Bofei, Liu, Qiang, Qin, Yameng, Chen, Qiuyan, Chen, Rong, Jin, Yanzi, Li, Mengyun, Jia, Xiaodan, Xu, Xianrui, Zhang, Qing
Publikováno v:
In Epilepsy & Behavior January 2024 150
Autor:
Liu, Qiang, Tan, Bofei, Zhang, Jie, Jin, Yanzi, Lei, Pingping, Wang, Xu, Li, Mengyun, Jia, Xiaodan, Zhang, Qing
Publikováno v:
In Epilepsy Research November 2023 197