OpenMOSS (SII)
Change the repository type filter
All
Repositories list
39 repositories
- 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…
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
- MOVA: Towards Scalable and Synchronized Video–Audio Generation
- MOSS-TTSD is a spoken dialogue generation model designed for expressive multi-speaker synthesis. It features long-context modeling, flexible speaker control, a…
- 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…
DiRL
PublicFRoM-W1
Public[ArXiv 26] FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions- MOSS-Speech is a true speech-to-speech large language model without text guidance.
RoboJuDo
PublicFutureOmni
PublicEmbodied-Planner-R1
PublicLongLLaDA
Public[AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs.github
PublicVLABench
PublicOfficial repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.ReAttention
Public[ICLR2025] ReAttention, a training-free approach to break the maximum context length in length extrapolationVehicleWorld
PublicUnifiedToolHub
PublicUnifiedToolHub is a comprehensive project supporting LLM-based tool use, designed to unify various tool-use dataset formats and provide training preparation, an…LongSafety
Public- a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation