Skip to main content

🏢 Metabrain AGI Lab

Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts
·2224 words·11 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Metabrain AGI Lab
Awaker2.5-VL: A novel Mixture-of-Experts architecture stably scales MLLMs, solving multi-task conflict with parameter efficiency and achieving state-of-the-art performance.