Let More Experts Speak: Balancing Exploration and Exploitation in PEFT for Mixture-of-Experts Models

Authors: Yi-Zeng Fang, Juinn-Dar Huang
Publication: ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Published: May 3, 2026
Source: Crossref
Back to Search View Original Cite This Article

Related Articles

Physics-guided world models for long horizon electromagnetic dynamics under partial observability

Ziheng Guo, Maoxiong Zhao et al. - May 2026

Read More
Parallax-Aware Spatial Transformer: Fusing Physics and Learning for Terahertz Near-Field Localization

Zhi Zeng, Chong Han - May 2026

Read More
ViTex: Visual Texture Control for Multi-Track Symbolic Music Generation via Discrete Diffusion Models

Xiaoyu Yi, Qi He et al. - May 2026

Read More
PI-GNN: A Physics-Informed Graph Neural Network for Spatio-Temporal Diffusion Prediction

Zimo Wen, Cheng Zeng et al. - May 2026

Read More
Dynamic Spectrogram Analysis with Local-Aware Graph Networks for Audio Anti-Spoofing

Yingdong Li, Chengxin Chen et al. - May 2026

Read More