no code implementations • 31 Jan 2024 • Zhitian Xie, Yinger Zhang, Chenyi Zhuang, Qitao Shi, Zhining Liu, Jinjie Gu, Guannan Zhang
However, the gate's routing mechanism also gives rise to narrow vision: the individual MoE's expert fails to use more samples in learning the allocated sub-task, which in turn limits the MoE to further improve its generalization ability.
1 code implementation • 6 Oct 2023 • Yinger Zhang, Hui Cai, Xeirui Song, Yicheng Chen, Rui Sun, Jing Zheng
While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting without fine-tuning.
no code implementations • 15 Oct 2022 • Yinger Zhang, Zhouyi Wu, Peiying Lin, Yang Pan, Yuting Wu, Liufang Zhang, Jiangtao Huangfu
It is created specifically for raw video captured by a lensless camera and has the ability to properly extract and combine temporal and spatial features.
no code implementations • 9 Oct 2022 • Yinger Zhang, Zhouyi Wu, Peiying Lin, Yuting Wu, Lusong Wei, Zhengjie Huang, Jiangtao Huangfu
Lensless cameras are characterized by several advantages (e. g., miniaturization, ease of manufacture, and low cost) as compared with conventional cameras.
3 code implementations • 18 May 2021 • Dongbo Xi, Zhen Chen, Peng Yan, Yinger Zhang, Yongchun Zhu, Fuzhen Zhuang, Yu Chen
While considerable multi-task efforts have been made in this direction, a long-standing challenge is how to explicitly model the long-path sequential dependence among audience multi-step conversions for improving the end-to-end conversion.