Skip to content
@OpenMOSS

OpenMOSS (SII)

OpenMOSS Team is a research group under the Shanghai Innovation Institution (SII), working in close collaboration with Fudan University and MOSI Intelligence.
README.md

Introduction 👋

OpenMOSS Team is a research group under the Shanghai Innovation Institution (SII), working in close collaboration with Fudan University and MOSI Intelligence. Led by Prof. Xipeng Qiu, the team conducts cutting-edge research on large language models (LLMs), advancing the frontiers of model architecture, evaluation, and application with a strong commitment to open, collaborative, and impactful AI innovation.

We warmly welcome researchers, students, and collaborators who share our vision to join us in pushing the boundaries of LLM technology. For inquiries or collaboration opportunities, please contact us at openmoss@sii.edu.cn .

🌐 Website: https://openmoss.github.io/ or http://openmoss.sii.edu.cn/

💻 GitHub: https://github.com/OpenMOSS

  • SII is dedicated to fostering innovation in education and research in the field of artificial intelligence.

Pinned Loading

  1. MOSS MOSS Public

    An open-source tool-augmented conversational language model from Fudan University

    Python 12.1k 1.1k

  2. MOSS-TTS MOSS-TTS Public

    MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenario…

    Python 919 86

  3. MOVA MOVA Public

    MOVA: Towards Scalable and Synchronized Video–Audio Generation

    Python 832 53

  4. MOSS-TTSD MOSS-TTSD Public

    MOSS-TTSD is a spoken dialogue generation model designed for expressive multi-speaker synthesis. It features long-context modeling, flexible speaker control, and multilingual support, while enablin…

    Python 1.2k 116

  5. AnyGPT AnyGPT Public

    Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

    Python 874 75

  6. Language-Model-SAEs Language-Model-SAEs Public

    Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.

    Python 200 24

Repositories

Showing 10 of 41 repositories
  • OurClaw Public

    Institutional OpenClaw Solution. Share One Claw with Others.

    OpenMOSS/OurClaw’s past year of commit activity
    TypeScript 10 MIT 0 0 0 Updated Mar 16, 2026
  • TTSD-eval Public
    OpenMOSS/TTSD-eval’s past year of commit activity
    Python 2 0 0 0 Updated Mar 16, 2026
  • MOSS-TTS Public

    MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.

    OpenMOSS/MOSS-TTS’s past year of commit activity
    Python 919 Apache-2.0 86 11 1 Updated Mar 16, 2026
  • Language-Model-SAEs Public

    Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.

    OpenMOSS/Language-Model-SAEs’s past year of commit activity
    Python 200 24 11 (1 issue needs help) 0 Updated Mar 16, 2026
  • mlx-audio Public Forked from Blaizzy/mlx-audio

    A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

    OpenMOSS/mlx-audio’s past year of commit activity
    Python 2 MIT 502 0 0 Updated Mar 16, 2026
  • MOVA Public

    MOVA: Towards Scalable and Synchronized Video–Audio Generation

    OpenMOSS/MOVA’s past year of commit activity
    Python 832 Apache-2.0 53 24 0 Updated Mar 14, 2026
  • sglang Public
    OpenMOSS/sglang’s past year of commit activity
    Python 1 Apache-2.0 0 0 0 Updated Mar 13, 2026
  • BandPO Public

    Official implementation of BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning. BandPO replaces canonical clipping (PPO/GRPO) with dynamic bounds to resolve exploration bottlenecks and prevent entropy collapse.

    OpenMOSS/BandPO’s past year of commit activity
    Python 43 GPL-3.0 4 0 0 Updated Mar 9, 2026
  • MOSS-TTSD Public

    MOSS-TTSD is a spoken dialogue generation model designed for expressive multi-speaker synthesis. It features long-context modeling, flexible speaker control, and multilingual support, while enabling zero-shot voice cloning from short audio references.

    OpenMOSS/MOSS-TTSD’s past year of commit activity
    Python 1,203 Apache-2.0 116 49 0 Updated Mar 6, 2026
  • MOSS-Audio-Tokenizer Public

    MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming and variable bitrates, delivering SOTA reconstruction and strong performance in generation and understanding—serving as a unified interface for next-generation native audio language models.

    OpenMOSS/MOSS-Audio-Tokenizer’s past year of commit activity
    Python 148 Apache-2.0 11 2 0 Updated Mar 6, 2026
View all repositories