Lead of Q-Future: https://github.com/Q-Future. I love MLLMs/LMMs/LVLMs/(any names you call them). Part of two great MoE VLMs as core contributors: Kimi-VL & Aria.
✨3B with MIT license ✨Long context windows up to 128K ✨Strong multimodal reasoning (36.8% on MathVision, on par with 10x larger models) and agent skills (34.5% on ScreenSpot-Pro)