3 papers
cs.LG2026
MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation
Lie Li, Wen Li, Junxiao Shen +1
Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignores the well-documented heteroge…
cs.CV2025
Duo Streamers: A Streaming Gesture Recognition Framework
Boxuan Zhu, Sicheng Yang, Zhuo Wang +2
Gesture recognition in resource-constrained scenarios faces significant challenges in achieving high accuracy and low latency. The streaming gesture recognition framework, Duo Stre…
cs.CV2025
AutoMR: A Universal Time Series Motion Recognition Pipeline
Likun Zhang, Sicheng Yang, Zhuo Wang +2
In this paper, we present an end-to-end automated motion recognition (AutoMR) pipeline designed for multimodal datasets. The proposed framework seamlessly integrates data preproces…