Today we are releasing JST-2, the world's first full-stack physics-native world foundation model. Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D. Generate a 3D scene in seconds and expand it in real time. Create characters with motion built in, all through one general architecture.

🤗 MOSS-Transcribe-Diarize-0.9B is now open source on @huggingface. Built with an end-to-end audio-to-structured-transcript paradigm: >0.9B open-source ASR model >Apache license 2.0 >128k long-context transcription >Up to ~90-min audio input >Speaker labels + timestamps in one generation >Multi-speaker diarization for meetings, interruptions, and overlapping voices >Hotword biasing for names, terms, and domain-specific vocabulary >~100 token/s on NVIDIA RTX 4090, RTF ~0.017 Thank you @sgl_project @vllm_project @Prince_Canuma @lllucas for day-0 support! 🚀 Github: github.com/OpenMOSS/MOSS-Tra… Huggingface: huggingface.co/spaces/OpenMO… API: shorturl.at/DWwe3 Live demo: shorturl.at/wRZ3j Technical Report：arxiv.org/abs/2601.01554 HF Space: huggingface.co/spaces/OpenMO… AtomGit：ai.atomgit.com/OpenMOSS/MOSS… SGLang-Omni: github.com/sgl-project/sglan… vLLM: github.com/vllm-project/vllm MLX-audio: github.com/Blaizzy/mlx-audio Discord:discord.gg/SmVQHGffZU