Alert button
Picture for Guanglu Wan

Guanglu Wan

Alert button

Learning or Self-aligning? Rethinking Instruction Fine-tuning

Feb 28, 2024
Mengjie Ren, Boxi Cao, Hongyu Lin, Liu Cao, Xianpei Han, Ke Zeng, Guanglu Wan, Xunliang Cai, Le Sun

Viaarxiv icon

A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training

Oct 01, 2023
Lucen Zhong, Hengtong Lu, Caixia Yuan, Xiaojie Wang, Jiashen Sun, Ke Zeng, Guanglu Wan

Viaarxiv icon

CPPF: A contextual and post-processing-free model for automatic speech recognition

Sep 21, 2023
Lei Zhang, Zhengkun Tian, Xiang Chen, Jiaming Sun, Hongyu Xiang, Ke Ding, Guanglu Wan

Figure 1 for CPPF: A contextual and post-processing-free model for automatic speech recognition
Figure 2 for CPPF: A contextual and post-processing-free model for automatic speech recognition
Figure 3 for CPPF: A contextual and post-processing-free model for automatic speech recognition
Viaarxiv icon

Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter

Sep 19, 2023
Song Li, Yongbin You, Xuezhi Wang, Ke Ding, Guanglu Wan

Figure 1 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Figure 2 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Figure 3 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Figure 4 for Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Viaarxiv icon

Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations

Jun 27, 2023
Yinyi Wei, Shuaipeng Liu, Hailei Yan, Wei Ye, Tong Mo, Guanglu Wan

Figure 1 for Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations
Figure 2 for Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations
Figure 3 for Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations
Figure 4 for Exploiting Pseudo Future Contexts for Emotion Recognition in Conversations
Viaarxiv icon

Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation

Apr 03, 2023
Yuncheng Hua, Xiangyu Xi, Zheng Jiang, Guanwei Zhang, Chaobo Sun, Guanglu Wan, Wei Ye

Figure 1 for Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation
Figure 2 for Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation
Figure 3 for Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation
Figure 4 for Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation
Viaarxiv icon

Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition

Dec 06, 2022
Zhiyuan Peng, Xuanji He, Ke Ding, Tan Lee, Guanglu Wan

Figure 1 for Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition
Figure 2 for Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition
Figure 3 for Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition
Figure 4 for Label-free Knowledge Distillation with Contrastive Loss for Light-weight Speaker Recognition
Viaarxiv icon

Covariance Regularization for Probabilistic Linear Discriminant Analysis

Dec 06, 2022
Zhiyuan Peng, Mingjie Shao, Xuanji He, Xu Li, Tan Lee, Ke Ding, Guanglu Wan

Figure 1 for Covariance Regularization for Probabilistic Linear Discriminant Analysis
Figure 2 for Covariance Regularization for Probabilistic Linear Discriminant Analysis
Figure 3 for Covariance Regularization for Probabilistic Linear Discriminant Analysis
Viaarxiv icon

MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts

Nov 25, 2022
Xiangyu Xi, Jianwei Lv, Shuaipeng Liu, Wei Ye, Fan Yang, Guanglu Wan

Figure 1 for MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
Figure 2 for MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
Figure 3 for MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
Figure 4 for MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
Viaarxiv icon