MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping

Jun 1, 2026·

Yushi Huang

,

Zining Wang

,

Zhihang Yuan

,

Yifu Ding

Ruihao Gong

,

Jinyang Guo

,

Xianglong Liu

,

Jun Zhang

· 0 min read

Cite

Authors

Ruihao Gong

---

← LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit Jun 1, 2026

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing Jan 1, 2026 →