OpenMOSS (SII)

All

39 repositories

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‑expressive…
audio text-to-speech multimodal
audio text-to-speech multimodal voice-cloning llm audio-tokenizer
Python
•
Apache License 2.0
•73•843•16•1•Updated Mar 10, 2026Mar 10, 2026
Language-Model-SAEs
Public
Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
sparse-autoencoders interpretability sparse-dictionary
sparse-autoencoders interpretability sparse-dictionary mechanistic-interpretability
Python
•24•200•11•0•Updated Mar 10, 2026Mar 10, 2026
MOVA
Public
MOVA: Towards Scalable and Synchronized Video–Audio Generation
multimodal diffusion-models sglang
multimodal diffusion-models sglang video-audio-generation
Python
•
Apache License 2.0
•52•812•23•0•Updated Mar 9, 2026Mar 9, 2026
BandPO
Public
Official implementation of BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning. BandPO replaces canoni…
Python
•
GNU General Public License v3.0
•4•37•0•0•Updated Mar 9, 2026Mar 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, a…
streaming finetune text-to-speeh
streaming finetune text-to-speeh large-language-models sglang speech-dialogue-generation
Python
•
Apache License 2.0
•115•1.2k•51•0•Updated Mar 6, 2026Mar 6, 2026
sglang
Public
Python
•
Apache License 2.0
•0•1•1•1•Updated Mar 6, 2026Mar 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 an…
audio music tokenizer
audio music tokenizer speech tts unified speech-representation
Python
•
Apache License 2.0
•10•136•2•0•Updated Mar 6, 2026Mar 6, 2026
OpenMOSS.github.io
Public
JavaScript
•1•2•0•0•Updated Mar 3, 2026Mar 3, 2026
Website
Public
wangye
JavaScript
•2•0•0•1•Updated Mar 2, 2026Mar 2, 2026
TTSD-eval
Public
Python
•0•2•0•0•Updated Feb 27, 2026Feb 27, 2026
DiRL
Public
Python
•
Apache License 2.0
•6•152•0•1•Updated Feb 25, 2026Feb 25, 2026
TransformerLens
Public
A library for mechanistic interpretability of GPT-style language models
Python
•
MIT License
•523•2•0•0•Updated Feb 18, 2026Feb 18, 2026
FRoM-W1
Public
[ArXiv 26] FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions
whole-body-control g1 humanoid-robots
whole-body-control g1 humanoid-robots h1 motion-generation foundation-models text-to-motion unitree fftai
Python
•
Apache License 2.0
•7•137•3•0•Updated Feb 13, 2026Feb 13, 2026
MOSS-Speech
Public
MOSS-Speech is a true speech-to-speech large language model without text guidance.
voice-assistant speech-to-speech large-language-models
voice-assistant speech-to-speech large-language-models
Python
•
Apache License 2.0
•7•127•2•0•Updated Feb 13, 2026Feb 13, 2026
RoboJuDo
Public
[ArXiv 26] The Depolyment Framework for the FRoM-W1 Project
Python
•
Other
•53•3•0•0•Updated Jan 28, 2026Jan 28, 2026
FutureOmni
Public
Python
•1•21•0•0•Updated Jan 22, 2026Jan 22, 2026
ABC-Bench
Public
ABC-Bench is a benchmark for Agentic Backend Coding. It evaluates whether code agents can explore real repositories, edit code, configure environments, deploy c…
2•25•0•0•Updated Jan 20, 2026Jan 20, 2026
Embodied-Planner-R1
Public
Embodied-Planner-R1: Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
Python
•
Apache License 2.0
•1•25•0•3•Updated Jan 5, 2026Jan 5, 2026
rope_pp
Public
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
Python
•4•33•0•0•Updated Dec 9, 2025Dec 9, 2025
LongLLaDA
Public
[AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
diffusion large-language-models long-context
diffusion large-language-models long-context length-extrapolation diffusion-language-models
Python
•5•53•2•0•Updated Dec 7, 2025Dec 7, 2025
.github
Public
0•0•0•0•Updated Nov 24, 2025Nov 24, 2025
RoboOmni
Public
Official code of "RoboOmni: Proactive Robot Manipulation in Omni-modal Context"
Python
•5•89•4•0•Updated Nov 17, 2025Nov 17, 2025
VLABench
Public
Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.
robotics embodied foundation-models
robotics embodied foundation-models
Python
•
MIT License
•27•397•30•0•Updated Nov 11, 2025Nov 11, 2025
Lorsa
Public
Python
•0•29•0•0•Updated Nov 9, 2025Nov 9, 2025
Sparse-dLLM
Public
Python
•2•27•3•0•Updated Oct 16, 2025Oct 16, 2025
ReAttention
Public
[ICLR2025] ReAttention, a training-free approach to break the maximum context length in length extrapolation
triton long-context large-language-model
triton long-context large-language-model length-extrapolation
Python
•
MIT License
•0•14•0•0•Updated Oct 6, 2025Oct 6, 2025
VehicleWorld
Public
VehicleWorld is the first comprehensive multi-device environment for intelligent vehicle interaction that accurately models the complex, interconnected systems …
Python
•0•21•0•0•Updated Sep 16, 2025Sep 16, 2025
UnifiedToolHub
Public
UnifiedToolHub is a comprehensive project supporting LLM-based tool use, designed to unify various tool-use dataset formats and provide training preparation, an…
tool-use llm function-calling
tool-use llm function-calling
Python
•4•19•0•0•Updated Jul 23, 2025Jul 23, 2025
LongSafety
Public
Python
•0•9•2•0•Updated Jun 16, 2025Jun 16, 2025
Thus-Spake-Long-Context-LLM
Public
a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation
training infrastructure architecture
training infrastructure architecture evaluation survey paper-list long-context large-language-model
1•61•1•0•Updated Mar 31, 2025Mar 31, 2025