Alert button
Picture for Bei Li

Bei Li

Alert button

Soft Alignment of Modality Space for End-to-end Speech Translation

Dec 18, 2023
Yuhao Zhang, Kaiqi Kou, Bei Li, Chen Xu, Chunliang Zhang, Tong Xiao, Jingbo Zhu

Viaarxiv icon

Rethinking and Improving Multi-task Learning for End-to-end Speech Translation

Nov 07, 2023
Yuhao Zhang, Chen Xu, Bei Li, Hao Chen, Tong Xiao, Chunliang Zhang, Jingbo Zhu

Viaarxiv icon

Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs

Oct 26, 2023
Yuxin Zuo, Bei Li, Chuanhao Lv, Tong Zheng, Tong Xiao, Jingbo Zhu

Viaarxiv icon

PartialFormer: Modeling Part Instead of Whole

Oct 23, 2023
Tong Zheng, Bei Li, Huiwen Bao, Weiqiao Shan, Tong Xiao, Jingbo Zhu

Viaarxiv icon

Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation

Oct 22, 2023
Kun Wei, Bei Li, Hang Lv, Quan Lu, Ning Jiang, Lei Xie

Viaarxiv icon

Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Sep 15, 2023
Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, Yujiu Yang

Figure 1 for Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Figure 2 for Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Figure 3 for Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Figure 4 for Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Viaarxiv icon

ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation

Aug 04, 2023
Chenglong Wang, Hang Zhou, Yimin Hu, Yifu Huo, Bei Li, Tongran Liu, Tong Xiao, Jingbo Zhu

Figure 1 for ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Figure 2 for ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Figure 3 for ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Figure 4 for ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Viaarxiv icon

ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning

May 31, 2023
Xiao Xu, Bei Li, Chenfei Wu, Shao-Yen Tseng, Anahita Bhiwandiwalla, Shachar Rosenman, Vasudev Lal, Wanxiang Che, Nan Duan

Figure 1 for ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning
Figure 2 for ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning
Figure 3 for ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning
Figure 4 for ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning
Viaarxiv icon

Deliberate then Generate: Enhanced Prompting Framework for Text Generation

May 31, 2023
Bei Li, Rui Wang, Junliang Guo, Kaitao Song, Xu Tan, Hany Hassan, Arul Menezes, Tong Xiao, Jiang Bian, JingBo Zhu

Figure 1 for Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Figure 2 for Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Figure 3 for Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Figure 4 for Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Viaarxiv icon

Augmenting Large Language Model Translators via Translation Memories

May 27, 2023
Yongyu Mu, Abudurexiti Reheman, Zhiquan Cao, Yuchun Fan, Bei Li, Yinqiao Li, Tong Xiao, Chunliang Zhang, Jingbo Zhu

Figure 1 for Augmenting Large Language Model Translators via Translation Memories
Figure 2 for Augmenting Large Language Model Translators via Translation Memories
Figure 3 for Augmenting Large Language Model Translators via Translation Memories
Figure 4 for Augmenting Large Language Model Translators via Translation Memories
Viaarxiv icon