Shanghai AI Laboratory just open-sourced InternLumina-U2, a 16.9B diffusion MoE model with only ~1.4B active parameters. It combines text QA, image generation, editing, video, and 3D understanding into a single framework using an 8-codebook discrete visual tokenizer.
Researchers from Shanghai Jiao Tong University and Shanghai AI Lab unveiled Warp-as-History, a method that guides AI video camera paths without heavy control modules. By disguising camera warps as visual history and tuning on just one video, it enables precise camera control across unseen scenes while naturally generating missing angles.
Shanghai AI Lab just open-sourced Intern-S1-Pro, a massive 1-trillion-parameter multimodal model tailored for scientific research. Built on a 512-expert MoE architecture that only activates 22B parameters per token, it tackles complex problems across chemistry, physics, and biology at Olympiad-level precision. It is free for commercial use, offering researchers a powerful open base for AI-driven discovery.
Shanghai AI Lab just open-sourced InternLM 2.5-7B, cramming a massive 1M token context window into a lightweight architecture. The model claims top scores for sub-12B models on Hugging Face's Open LLM Leaderboard, bringing heavy-duty reasoning and tool use to local hardware.
