OpenMOSS (SII)
Repositories list
72 repositories
- A unified audio-video variational autoencoder with cross-modal alignment for joint reconstruction and generation
- A foundation model that generates synchronized video and audio in a single model
- A unified framework for training, fine-tuning, and evaluating World Action Models
- Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
- Source code for the OpenMOSS website and research project pages
- A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness
- OpenMOSS organization profile and shared GitHub community files
- An embodied task agent that connects perception, action, verification, and learning in a continuous physical-world loop
- An open-weight 11B model series for long-form and real-time video understanding
- A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods
- A benchmark for testing whether coding agents can resolve engineering tasks in scientific software
- Public assignments and submissions for the 2026 OpenMOSS summer training program
- A curated collection of papers, explainers, and resources on World Action Models for embodied AI
- Legacy OpenMOSS website fork with pages for people, projects, positions, and resources
- Interactive web demo for MOSS-VL video understanding models
- A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and zero-shot voice cloning
- Interactive web demo for MOSS-TTS-Nano speech generation
- A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation
- An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
- An open-source model for understanding speech, environmental sounds, and music through captioning, question answering, and reasoning
- An open-source, tool-augmented conversational language model from Fudan University
- Assignments and exercises for the Fall 2024 Pattern Recognition and Machine Learning course at Fudan University
ProTip! When viewing an organization's repositories, you can use the
props. filter to filter by custom property.