Post
268
InternVL3.5 🔥 New family of multimodal model by Shanghai AI lab
OpenGVLab/internvl35-68ac87bd52ebe953485927fb
✨ 1B · 2B · 4B · 8B · 14B · 38B ｜ MoE → 20B-A4B · 30B-A3B · 241B-A28B 📄Apache 2.0
✨ +16% reasoning performance, 4.05× speedup vs InternVL3
✨ Cascade RL (offline + online) : stronger reasoning
✨ ViR: efficient visual token routing
✨ DvD: calable vision–language deployment
✨ Supports GUI & embodied agency 🤖
OpenGVLab/internvl35-68ac87bd52ebe953485927fb
✨ 1B · 2B · 4B · 8B · 14B · 38B ｜ MoE → 20B-A4B · 30B-A3B · 241B-A28B 📄Apache 2.0
✨ +16% reasoning performance, 4.05× speedup vs InternVL3
✨ Cascade RL (offline + online) : stronger reasoning
✨ ViR: efficient visual token routing
✨ DvD: calable vision–language deployment
✨ Supports GUI & embodied agency 🤖