Taiyu Niu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Taiyu Niu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Geng Tu
Harbin Institute of Technology, Shenzhen, China
3 shared publications - Ruifeng Xu
Harbin Institute of Technology, Shenzhen, China
3 shared publications - Bin Liang
The Chinese University of Hong Kong, Hong Kong, China
1 shared publication - Erik Cambria
Nanyang technological university, Singapore, Singapore
1 shared publication - Min Zhang
Harbin Institute of Technology
1 shared publication - Pengtao Han
Harbin Institute of Technology, Shenzhen, China
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4199-4204
A Graph-Enhanced MLLM for Hierarchical Multimodal Emotion Understanding and Support in Conversations
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4199-4204
Open AccessA Graph-Enhanced MLLM for Hierarchical Multimodal Emotion Understanding and Support in Conversations
- Open Access
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 64-68
A Lightweight Multimodal Framework for Big Five Personality Trait Prediction
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 64-68
Open AccessA Lightweight Multimodal Framework for Big Five Personality Trait Prediction
- 30 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 39 (4) , 5-11
AdaCLF: An Adaptive Curriculum Learning Framework for Emotional Support Conversation
Emotional support conversation (ESC) aims to alleviate emotional distress using data-driven approaches trained on human-generated responses. However, the subjective and open-ended nature of human conversations presents challenges in training ESC models due to uneven complexities in query–response pairs. This uneven complexity impedes the efficiency and effectiveness of learning in ESC models. Based on this, we propose an adaptive curriculum learning framework (AdaCLF) to dynamically choose courses of varying complexity according to the learning status of the ESC model. AdaCLF consists of two main components: the student model (referred to as the ESC model) and the teacher model (responsible for selecting appropriate data to enhance the student model’s training). The framework operates within the reinforcement learning paradigm, where the teacher model utilizes feedback from the student model to optimize its teaching strategy, fostering collaborative evolution. Both automatic and human evaluations on benchmark datasets demonstrate that our framework significantly improves existing ESC methods, generating more effective supportive responses.
- 30 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 39 (4) , 5-11
AdaCLF: An Adaptive Curriculum Learning Framework for Emotional Support Conversation
Emotional support conversation (ESC) aims to alleviate emotional distress using data-driven approaches trained on human-generated responses. However, the subjective and open-ended nature of human conversations presents challenges in training ESC models due to uneven complexities in query–response pairs. This uneven complexity impedes the efficiency and effectiveness of learning in ESC models. Based on this, we propose an adaptive curriculum learning framework (AdaCLF) to dynamically choose courses of varying complexity according to the learning status of the ESC model. AdaCLF consists of two main components: the student model (referred to as the ESC model) and the teacher model (responsible for selecting appropriate data to enhance the student model’s training). The framework operates within the reinforcement learning paradigm, where the teacher model utilizes feedback from the student model to optimize its teaching strategy, fostering collaborative evolution. Both automatic and human evaluations on benchmark datasets demonstrate that our framework significantly improves existing ESC methods, generating more effective supportive responses.