![profile picture](https://assets.underline.io/profile/152709/square_avatar/medium-662aa06d2fa6e98c69263b2749f777cf.jpg)
Zhiyuan Ma
Graduate student @ Huazhong University of Science & Technology
task-oriented dialog
visual question answering
multi-hop reasoning
multimodal
prompt tuning
intention-aware
fact verification
latent logical relations
structured evidence graph
human priors
4
presentations
2
number of views
SHORT BIO
Zhiyuan Ma is pursuing the PhD degree in the School of Computer Science, Huazhong University of Science and Technology, China. His research interests include dialog systems, multimodal learning and natural language inference.
Presentations
![](https://assets.underline.io/lecture/68420/poster/medium-2d6e9029e1b53a8b99a9578f52a49f14.jpg)
HybridPrompt: Bridging Language Models and Human Priors in Prompt Tuning for Visual Question Answering
Jianjun Li and 3 other authors
![](https://assets.underline.io/lecture/60033/poster_document_thumbnail_extract/medium-d419156ee2abccd8484bab75a31fecf3.jpg)
GLAF: Global-to-Local Aggregation and Fission Network for Semantic Level Fact Verification
Zhiyuan Ma and 3 other authors
![](https://assets.underline.io/lecture/50666/poster_document_thumbnail_extract/medium-583478f51770f144bfad6eb7e735fe07.jpg)
UniTranSeR: A Unified Transformer Semantic Representation Framework for Multimodal Task-Oriented Dialog System
Zhiyuan Ma and 3 other authors
![](https://assets.underline.io/lecture/37436/poster_document_thumbnail_extract/medium-add886bf7d2e531e99f26a531a37e4b3.jpg)
Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue
Zhiyuan Ma and 4 other authors