Di Xiong — accepted AI-conference papers

2026

ArcDAE: Asymmetric Rectified Contrastive Diffusion Autoencoder for Unified Representation Learning

Ge Gao, Shuo Chen, Di Xiong, Zeke Xie, Jian Yang

ICML 2026poster

The unification of generative details and discriminative semantics presents a structural paradox in \textit{diffusion-based representation learning}. Early approaches decouple semantics from generation, inevitably compromising representational completeness (i.e., \textit{information split}). While r…

Cited by 0 Source ↗Scholar ↗

2025

Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning

Di Xiong, Shuoyuan Wang, Lei Zhang, Wenbo Huang, Chaolei Han

AAAI 2025technical

Human Activity Recognition (HAR) aims to recognize activities by training models on massive sensor data. In real-world deployment, a crucial aspect of HAR that has been largely overlooked is that the test sets may have different distributions from training sets due to inter-subject variability inclu…

Cited by 0 Source ↗PDF ↗Scholar ↗