DConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding

Shidong Cao, Jing Ma, Wenhao Chai, Yuchen Tian, Lun Du, Da Zheng

arXiv preprint, 2026
[Paper]

• A context-parameterized compilation framework for exact and efficient constrained decoding in diffusion language models.

From Evidence to Action: How Tool-Using Agents Fail

Hongzhan Lin*, Shidong Cao*, Ziyang Luo, Wenhao Chai, Mong-Li Lee, Wynne Hsu

arXiv preprint, 2026
[Paper] [Code] [Project]

• SafeActBench evaluates whether tool-using agents establish the evidence required to support consequential actions and dependent workflows.

DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs

Shidong Cao, Hongzhan Lin, Yuxuan Gu, Ziyang Luo, Jing Ma

Published in Findings of the Association for Computational Linguistics: ACL, 2026
[Paper] [Code]

• A diffusion-styled framework for improving chain-of-thought reasoning in large language models.

A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision

Zhonghan Zhao, Wenhao Chai, Shengyu Hao, Wenhao Hu, Guanhong Wang, Shidong Cao, Mingli Song, Jenq-Neng Hwang, Gaoang Wang

Published in IEEE Transactions on Visualization and Computer Graphics, 2025
[Paper]

• A survey of deep learning applications in sports across perception, comprehension, and decision-making.

Efficient Transfer From Image-Based Large Multimodal Models to Video Tasks

Shidong Cao, Zhonghan Zhao, Shengyu Hao, Wenhao Chai, Jenq-Neng Hwang, Hongwei Wang, Gaoang Wang

Published in IEEE Transactions on Multimedia, 2025
[Paper]

• An efficient transfer approach for adapting image-based large multimodal models to fine-grained video tasks.

See and Think: Embodied Agent in Virtual Environment

Zhonghan Zhao, Wenhao Chai, Xuan Wang, Boyi Li, Shengyu Hao, Shidong Cao, Tian Ye, Gaoang Wang

Published in European Conference on Computer Vision, 2024
[Paper] [Code] [Project]

• An embodied agent framework that combines visual perception, language instruction, and executable code actions in Minecraft.

DiffFashion: Reference-Based Fashion Design With Structure-Aware Transfer by Diffusion Models

Shidong Cao, Wenhao Chai, Shengyu Hao, Yanting Zhang, Hangyue Chen, Gaoang Wang

Published in IEEE Transactions on Multimedia, 2024
[Paper] [Code]

• A diffusion model-based method for reference-based fashion design with structure-aware transfer.

UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning

Meiqi Sun, Zhonghan Zhao, Wenhao Chai, Hanjun Luo, Shidong Cao, Yanting Zhang, Jenq-Neng Hwang, Gaoang Wang

Published in AAAI Conference on Artificial Intelligence, 2024
[Paper] [Code] [Project]

• A universal animal perception model for few-shot pose estimation, segmentation, and classification.

AI Assisted Fashion Design: A Review

Ziyue Guo, Zongyang Zhu, Yizhi Li, Shidong Cao, Hangyue Chen, Gaoang Wang

Published in IEEE Access, 2023
[Paper]

• A review of artificial intelligence techniques for fashion detection, synthesis, and recommendation.

Image Reference-guided Fashion Design with Structure-aware Transfer by Diffusion Models

Shidong Cao, Wenhao Chai, Shengyu Hao, Gaoang Wang

Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023
[Paper] [Code]

• An unsupervised structure-aware diffusion framework for reference-guided fashion design.