Zaiwen Feng — accepted AI-conference papers

2026

LightAVSeg: Lightweight Audio-Visual Segmentation

Qing Zhong, Guodong Ding, Lingqiao Liu, Zaiwen Feng, Lin Wu, Angela Yao

ICML 2026poster

Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-modal attention with quadratic computational cost, limiting their suitability for resource efficient deployment. Most efficiency oriented methods focu…

Cited by 0 Source ↗Scholar ↗

2026

XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series Forecasting with Exogenous Inputs

Xinyang Chen, Huidong Jin, Yu Huang, Zaiwen Feng

AAAI 2026technical

Despite the prevalent assumption of uniform variable importance in long-term time series forecasting models, real-world applications often exhibit asymmetric causal relationships and varying data acquisition costs. Specifically, cost‐effective exogenous data (e.g., local weather) can unilaterally in

Cited by 0 Source ↗PDF ↗Scholar ↗