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. MOVA MOVA Public

    MOVA: Towards Scalable and Synchronized Video–Audio Generation

    Python 789 49

  3. 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 791 70

  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 112

  5. AnyGPT AnyGPT Public

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

    Python 870 75

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

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

    Python 198 24

Repositories

Showing 10 of 39 repositories
  • 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 130 Apache-2.0 10 2 0 Updated Mar 4, 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 791 Apache-2.0 70 25 1 Updated Mar 4, 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 0 GPL-3.0 0 0 0 Updated Mar 4, 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 198 24 11 (1 issue needs help) 0 Updated Mar 4, 2026
  • OpenMOSS.github.io Public
    OpenMOSS/OpenMOSS.github.io’s past year of commit activity
    JavaScript 2 2 0 0 Updated Mar 3, 2026
  • Website Public Forked from WillQvQ/testHomepage

    wangye

    OpenMOSS/Website’s past year of commit activity
    JavaScript 0 2 0 1 Updated Mar 2, 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 1,190 Apache-2.0 112 51 0 Updated Mar 2, 2026
  • TTSD-eval Public
    OpenMOSS/TTSD-eval’s past year of commit activity
    Python 2 0 0 0 Updated Feb 27, 2026
  • DiRL Public
    OpenMOSS/DiRL’s past year of commit activity
    Python 149 Apache-2.0 6 0 1 Updated Feb 25, 2026
  • MOVA Public

    MOVA: Towards Scalable and Synchronized Video–Audio Generation

    OpenMOSS/MOVA’s past year of commit activity
    Python 789 Apache-2.0 49 20 1 Updated Feb 20, 2026
View all repositories