SATO: Stable Text-to-Motion Framework

Wenshuo Chen#, Hongru Xiao#, Erhang Zhang#, Lijie Hu, Lei Wang, Mengyuan Liu, Chen Chen

Project Code

• We are the first work to discover the instability issue in text-to-motion models
• We successfully strike a balance between accuracy and stability, ensuring our model maintains high precision even in the face of perturbations
• Our work points to a novel direction for improving text-tomotion models, paving the way for the development of more robust models for real-world applications

Towards Multi-dimensional Explanation Alignment for Medical Classification

Lijie Hu#, Songning Lai#, Wenshuo Chen#, Hongru Xiao, Hongbin Lin, Lu Yu, Jingfeng Zhang, and Di Wang

• We proposed an end-to-end framework called Med-MICN, which leverages the strength of different XAI methods such as concept-based models, neural symbolic methods, saliency maps, and concept semantics.
• Our outputs are interpreted in multiple dimensions, including concept prediction, saliency maps, and concept reasoning rules, making it easier for experts to identify and correct errors.
• Med-MICN demonstrates superior performance and interpretability compared with other concept-based models and the black-box model baselines.

FTS: A FRAMEWORK TO FIND A FAITHFUL TIMESIEVE

Songning Lai#, Ninghui Feng#, Jiechao Gao, Hao Wang, Haochen Sui, Xin Zou, Jiayu Yang, Wenshuo Chen, Hang Zhao, Xuming Hu, Yutao Yue

• Our research provides faithful technical support and theoretical support to the field of time series forecasting, promising to advance the development and reliability of forecasting methods within the industry. Through these efforts, we aim to bolster the trustworthiness of models, ultimately supporting decision-making processes that rely on accurate and consistent predictions.