I am a AI enthusiast. I received my degree in Software Engineering from South China University of Technology in 2022. Currently, I’m pursuing a Master of Philosophy in the Thrust of Artificial Intelligence at The Hong Kong University of Science and Technology (Guangzhou) supervised By Prof. Hui Xiong and Junwei Liang.

My research interests lie in the intersection of action perception, manipulation and human-robotics interaction based on language. Previously, I interned at Tencent AI Lab, working on sign language translation in collaboration with Xing Wang and Wenxiang Jiao. Currently, I’m part of the Multimodal Human-Computer Interaction Group at HKUST-GZ, focusing on multimodal human-computer interaction and collaboration, in partnership with PhD candidate Weiyu Guo.

Recently, I am doing internship in Stanford Vision and Learning Lab working with the postdoc Manling Li and Prof Jiajun Wu.

Moving forward, I aim to make a significant impact by applying Language Model Learning (LLM) in various domains (LLM for X), like for human-robotics interaction. Intuitively, I am particularly interested in efficiently mapping LLM into finite instruction sets, which can drive intelligent agents and create a real-world impact, somehow part of Embodied AI. I envision a future where AI is not just seamlessly integrated into our lives, but also interacts with us in a real-time and autonomous manner.

I am currently exploring potential opportunities for internships and PhD positions.

News

• 0928: Excited to announce that our two projects clinched 1st and 2nd places in the Human-Machine Interaction track of the Pazhou Algorithm Contest! We’ve been awarded a total of 120,000 RMB and look forward to a big celebratory dinner. The relative works will be documented in upcoming papers. link

• Before 08/30/2023: […]

Publications

GeoDeformer: Geometric Deformable Transformer for Action Recognition
Jinhui Ye, Jiaming Zhou, Hui Xiong, Junwei Liang
Preprint 2023. [arXiv]
Spatial-Temporal Alignment Network for Action Recognition
Jinhui Ye, Junwei Liang
Preprint 2023. [arXiv]
Cross-modality Data Augmentation for End-to-End Sign Language Translation
Jinhui Ye, Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Hui Xiong
EMNLP 2023. [arXiv] [code]
Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation
Jinhui Ye, Wenxiang Jiao, Xing Wang, Zhaopeng Tu
EACL 2023. [paper] [code]
Aspect-Opinion Correlation Aware and Knowledge-Expansion Few Shot Cross-Domain Sentiment Classification
Haopeng Ren, Yi Cai, Yushi Zeng, Jinhui Ye, Ho-fung Leung, Qing Li
Transactions on Affective Computing 2022. [paper] [code]

Awards

• Outstanding Undergraduate Thesis in SCUT
• National Scholarship in China