← Search

Yarong Wang

2 accepted papers

2026

Less Token, More Signal: MoE Expert Pruning via Critical Token Selection

ICML 2026poster

Mixture-of-Experts (MoE) architectures provide strong scalability for large language models, but their large expert parameter footprint poses challenges for efficient deployment. Expert pruning is widely used to reduce model size and inference cost; however, existing approaches are token-agnostic, t…

Cited by 0SourceScholar
2023

Performance Comparison of Typical Physics Engines Using Robot Models With Multiple Joints

RA-L 2023

Physics engines are essential components in simulating complex robotic systems. The accuracy and computational speed of these engines are crucial for reliable real-time simulation. This letter comprehensively evaluates the performance of five common physics engines, i.e., ODE, Bullet, DART, MuJoCo,

Cited by 9SourceScholar