2 code implementations • 5 Mar 2024 • Weihao Tan, Ziluo Ding, Wentao Zhang, Boyu Li, Bohan Zhou, Junpeng Yue, Haochong Xia, Jiechuan Jiang, Longtao Zheng, Xinrun Xu, Yifei Bi, Pengjie Gu, Xinrun Wang, Börje F. Karlsson, Bo An, Zongqing Lu
Despite the success in specific tasks and scenarios, existing foundation agents, empowered by large models (LMs) and advanced tools, still cannot generalize to different scenarios, mainly due to dramatic differences in the observations and actions across scenarios.
no code implementations • 11 Feb 2024 • Muqun Niu, Yuan Ren, Boyu Li, Chenchen Ding
Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques.
no code implementations • 14 Dec 2023 • Yixuan Zhang, Boyu Li, Zenan Ling, Feng Zhou
In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning.
no code implementations • 13 Dec 2023 • Peiqi Duan, Boyu Li, Yixin Yang, Hanyue Lou, Minggui Teng, Yi Ma, Boxin Shi
Event cameras are emerging imaging technology that offers advantages over conventional frame-based imaging sensors in dynamic range and sensing speed.
1 code implementation • 11 Dec 2023 • Binxiao Huang, Jason Chun Lok Li, Jie Ran, Boyu Li, Jiajun Zhou, Dahai Yu, Ngai Wong
Conventional super-resolution (SR) schemes make heavy use of convolutional neural networks (CNNs), which involve intensive multiply-accumulate (MAC) operations, and require specialized hardware such as graphics processing units.
no code implementations • 15 Nov 2023 • Jin Qiu, Lu Huang, Boyu Li, Jun Zhang, Lu Lu, Zejun Ma
Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 21 Aug 2023 • Boyu Li, Robert Simon Fong, Peter Tiňo
Reservoir computation models form a subclass of recurrent neural networks with fixed non-trainable input and dynamic coupling weights.
no code implementations • 7 Jun 2023 • Lu Huang, Boyu Li, Jun Zhang, Lu Lu, Zejun Ma
Domain adaptation using text-only corpus is challenging in end-to-end(E2E) speech recognition.
no code implementations • 24 Feb 2023 • Jiajun Zhou, Jiajun Wu, Yizhao Gao, Yuhao Ding, Chaofan Tao, Boyu Li, Fengbin Tu, Kwang-Ting Cheng, Hayden Kwok-Hay So, Ngai Wong
To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched.
no code implementations • 11 Feb 2023 • Xin Liu, Yaran Chen, Haoran Li, Boyu Li, Dongbin Zhao
CRPTpro significantly outperforms the next best Proto-RL(C) on 11/12 cross-domain downstream tasks with only 54\% wall-clock pre-training time, exhibiting state-of-the-art pre-training performance with greatly improved pre-training efficiency.
no code implementations • ICCV 2023 • Jinxiu Liang, Yixin Yang, Boyu Li, Peiqi Duan, Yong Xu, Boxin Shi
With frame-based cameras, capturing fast-moving scenes without suffering from blur often comes at the cost of low SNR and low contrast.
no code implementations • 15 Nov 2022 • Jinsong Chen, Boyu Li, Kun He
The decoupled Graph Convolutional Network (GCN), a recent development of GCN that decouples the neighborhood aggregation and feature transformation in each convolutional layer, has shown promising performance for graph representation learning.
1 code implementation • 23 Sep 2022 • Zhongwei Wan, Xin Liu, Benyou Wang, Jiezhong Qiu, Boyu Li, Ting Guo, Guangyong Chen, Yang Wang
The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.
no code implementations • 21 Jun 2022 • Jinsong Chen, Boyu Li, Qiuting He, Kun He
However, they follow the traditional structure-aware propagation strategy of GCNs, making it hard to capture the attribute correlation of nodes and sensitive to the structure noise described by edges whose two endpoints belong to different categories.
1 code implementation • 22 Dec 2021 • Sofia Broomé, Ernest Pokropek, Boyu Li, Hedvig Kjellström
Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes.
no code implementations • 8 Dec 2021 • Meng Wang, Boyu Li, Kun He, John E. Hopcroft
We theoretically show that our method can avoid some situations that a broken community and the local community are regarded as one community in the subgraph, leading to the inaccuracy on detection which can be caused by global hidden community detection methods.
2 code implementations • 8 Jul 2020 • Junhua Zou, Yexin Duan, Boyu Li, Wu Zhang, Yu Pan, Zhisong Pan
Fast gradient sign attack series are popular methods that are used to generate adversarial examples.