OpenMOSS

Team

university

http://openmoss.sii.edu.cn/

OpenMOSS

Activity Feed Request to join this org

AI & ML interests

LLM

Recent Activity

kiiic updated a collection 3 days ago

MOSS-Live

kiiic published an article 3 days ago

MOSS-Live: A Full-Duplex Real-Time Interaction System

zylin12 new activity 6 days ago

OpenMOSS-Team/MOSS-Transcribe-Diarize:Model enters a repetitive generation loop on music-only audio until the token limit is reached

View all activity

Papers

MOSS-Image Technical Report

Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position

View all Papers

Articles

MOSS-Live: A Full-Duplex Real-Time Interaction System

3 days ago

• 6

OpenMOSS-Team 's collections 23

EasyWAM

OpenMOSS-Team/EasyWAM-MoT-Wan22

Robotics • Updated Sep 22 • 4
OpenMOSS-Team/EasyWAM-Unified-Wan22

Robotics • Updated Sep 22 • 3
OpenMOSS-Team/EasyWAM-Hidden-Wan22

Robotics • Updated Sep 22 • 3
OpenMOSS-Team/libero-lerobot-v3.0

Viewer • Updated Sep 22 • 279k • 478 • 4

MOSS Transcribe

A unified multimodal large language model for end-to-end speaker-attributed, time-stamped transcription.

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

Paper • 2601.01554 • Published Jan 4 • 66
Running

Agents

Featured

106

MOSS Transcribe Diarize

🏢

106

Transcribe audio or video with speaker diarization
OpenMOSS-Team/MOSS-Transcribe-preview-2B

Automatic Speech Recognition • 2B • Updated Jun 26 • 315 • 54
OpenMOSS-Team/MOSS-Transcribe-Diarize

Audio-Text-to-Text • 0.9B • Updated 10 days ago • 133k • 518

MOSS-Video-Preview

OpenMOSS-Team/moss-video-preview-base

Video-Text-to-Text • 11B • Updated Aug 4 • 42 • 16
OpenMOSS-Team/moss-video-preview-sft

Video-Text-to-Text • 11B • Updated Aug 4 • 86 • 18
OpenMOSS-Team/moss-video-preview-realtime-sft

Video-Text-to-Text • 11B • Updated Aug 4 • 64 • 29
OpenMOSS-Team/Realtime-QA-100K

Viewer • Updated Jun 10 • 100k • 347 • 8

MOSS-TTS

OpenMOSS-Team/MOSS-TTS

Text-to-Speech • 8B • Updated Mar 20 • 4.4k • 437
OpenMOSS-Team/MOSS-TTS-Local-Transformer

Text-to-Speech • 3B • Updated Mar 20 • 151k • 32
OpenMOSS-Team/MOSS-TTS-Realtime

Text-to-Speech • 2B • Updated Jul 27 • 19.7k • 120
OpenMOSS-Team/MOSS-TTS-Nano-100M

Text-to-Speech • Updated Apr 13 • 120k • 252

Llama Scope 2

Opensource Lorsas and Transcoders

OpenMOSS-Team/Llama-Scope-2

Updated Feb 10 • 1
OpenMOSS-Team/Llama-Scope-2-Qwen3-1.7B

Updated Apr 2 • 3

MOSS-TTSD

OpenMOSS-Team/MOSS-TTSD-v1.0

Text-to-Speech • 8B • Updated Feb 14 • 12k • 64
OpenMOSS-Team/MOSS-TTSD-v0.7

Text-to-Speech • 2B • Updated Nov 11, 2025 • 236 • 18
OpenMOSS-Team/MOSS-TTSD-v0.5

Text-to-Speech • 2B • Updated Sep 2, 2025 • 282 • 54
OpenMOSS-Team/MOSS-TTSD-v0

Text-to-Speech • 2B • Updated Jun 20, 2025 • 35 • 28

ABC-Bench

Evaluating Agentic Backend Coding Capabilities in Real-World Development Scenarios

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

Paper • 2601.11077 • Published Jan 16 • 67
OpenMOSS-Team/ABC-Bench

Viewer • Updated Jan 20 • 224 • 279 • 4
OpenMOSS-Team/Qwen3-32B-ABC

Text Generation • 33B • Updated Jan 20 • 27 • 3
OpenMOSS-Team/Qwen3-8B-ABC

Text Generation • 8B • Updated Jan 20 • 1.08k • 3

Game-RL

[ICLR 2026] Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning

OpenMOSS-Team/GameQA-140K

Viewer • Updated Oct 2 • 300 • 2.54k • 23
OpenMOSS-Team/GameQA-5K

Preview • Updated Jun 22, 2025 • 280 • 2
OpenMOSS-Team/Game-RL-Qwen2.5-VL-7B

Image-Text-to-Text • 8B • Updated Jul 27, 2025 • 1.16k • 4
OpenMOSS-Team/Game-RL-InternVL3-8B

8B • Updated Jun 17, 2025 • 957 • 2

DiRL

An Efficient Training Framework for Diffusion Language Models

OpenMOSS-Team/DiRL-8B-Instruct

Text Generation • 8B • Updated Jan 20 • 91 • 14

MOSS Embodied Planner

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Paper • 2503.10480 • Published Mar 13, 2025 • 55
Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning

Paper • 2506.23127 • Published Jun 29, 2025 • 2
World-aware Planning Narratives Enhance Large Vision-Language Model Planner

Paper • 2506.21230 • Published Jun 26, 2025 • 1
OpenMOSS-Team/Embodied_R1-ScienceWorld

8B • Updated Jun 30, 2025 • 19 • 1

MHA2MLA-refactor

The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs"

OpenMOSS-Team/SmolLM-135M-MLA-d_kv_8-refactor

Text Generation • 0.1B • Updated Jun 23, 2025 • 28 • 1
OpenMOSS-Team/SmolLM-135M-MLA-d_kv_32-refactor

Text Generation • 0.1B • Updated Jun 17, 2025 • 21 • 1
OpenMOSS-Team/SmolLM-135M-MLA-d_kv_16-refactor

Text Generation • 0.1B • Updated Jun 17, 2025 • 23 • 1
OpenMOSS-Team/SmolLM-360M-MLA-d_kv_8-refactor

Text Generation • 0.3B • Updated Jun 17, 2025 • 23 • 1

MOSS

OpenMOSS-Team/moss-moon-003-sft-plugin

Text Generation • Updated May 27 • 195 • 72
OpenMOSS-Team/moss-moon-003-sft

Text Generation • Updated May 27 • 254 • 129
OpenMOSS-Team/moss-moon-003-base

Text Generation • Updated May 27 • 222 • 132
OpenMOSS-Team/moss-moon-003-sft-int4

Text Generation • Updated May 27 • 174 • 41

OpenETA

openeta: embodied task agent

ETA: A New Agentic Paradigm for Embodied Tasks

Paper • 2608.03924 • Published Aug 4 • 11

MOSS-Audio

An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex

Running

Agents

30

MOSS Audio 8B Thinking

🐢

30

Generate answers from uploaded audio or video
OpenMOSS-Team/MOSS-Audio-4B-Instruct

Audio-Text-to-Text • 5B • Updated Sep 25 • 2.29k • 90
OpenMOSS-Team/MOSS-Audio-4B-Thinking

Audio-Text-to-Text • 5B • Updated Sep 25 • 592 • 41
OpenMOSS-Team/MOSS-Audio-8B-Instruct

Audio-Text-to-Text • 9B • Updated Sep 25 • 1.58k • 56

MOSS-VL

OpenMOSS-Team/MOSS-VL-Instruct-0408

Video-Text-to-Text • 11B • Updated Sep 23 • 195 • 108
OpenMOSS-Team/MOSS-VL-Base-0408

Video-Text-to-Text • 11B • Updated Sep 23 • 352 • 64
OpenMOSS-Team/MOSS-VL-Instruct-0708

Video-Text-to-Text • 11B • Updated Sep 23 • 327 • 34
OpenMOSS-Team/MOSS-VL-Base-0708

Video-Text-to-Text • 11B • Updated Sep 23 • 104 • 19

AI Can Learn Scientific Taste

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 302
OpenMOSS-Team/SciJudgeBench

Viewer • Updated Sep 22 • 732k • 406 • 11
OpenMOSS-Team/SciJudge-4B-2605

Text Generation • 4B • Updated Jul 2 • 90 • 6
OpenMOSS-Team/SciJudge-30B-2605

Text Generation • 31B • Updated Jul 2 • 1.27k • 4

MOVA

OpenMOSS-Team/MOVA-360p

Image-to-Video • Updated Feb 15 • 183k • 219
OpenMOSS-Team/MOVA-720p

Any-to-Any • Updated Feb 11 • 308 • 134
MOVA: Towards Scalable and Synchronized Video-Audio Generation

Paper • 2602.08794 • Published Feb 9 • 159

MOSS-Speech

True Speech-to-Speech Langugage Model

OpenMOSS-Team/MOSS-Speech

9B • Updated Sep 30, 2025 • 277 • 24
OpenMOSS-Team/MOSS-Speech-Codec

0.9B • Updated Oct 1, 2025 • 128 • 7
Running on Zero

Agents

22

MOSS-Speech Demo

🚀

22

True Speech-to-Speech Language Model
MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Paper • 2510.00499 • Published Oct 1, 2025 • 23

FutureOmni

First Omni-modal Future Forecasting Benchmark

OpenMOSS-Team/FutureOmni

Viewer • Updated Jan 22 • 1.03k • 508 • 7
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Paper • 2601.13836 • Published Jan 20 • 37

FRoM-W1

https://github.com/OpenMOSS/FRoM-W1

OpenMOSS-Team/FRoM-W1

Updated Feb 4 • 11
OpenMOSS-Team/FRoM-W1-Datasets

Viewer • Updated Jan 29 • 166k • 257 • 8
FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

Paper • 2601.12799 • Published Jan 19 • 4

RoboOmni

Proactive Robot Manipulation in Omni-modal Context

OpenMOSS-Team/RoboOmni

Robotics • 5B • Updated Oct 30, 2025 • 65 • 16
OpenMOSS-Team/OmniAction

Updated Mar 27 • 205k • 295
OpenMOSS-Team/OmniAction-LIBERO

Updated Mar 27 • 6.52k • 70
OpenMOSS-Team/RoboOmni-LIBERO-Spatial

Robotics • 5B • Updated Oct 31, 2025 • 34 • 3

Low Rank Sparse Attention

Open source weights of Lorsa modules introduced in "Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition".

OpenMOSS-Team/Lorsa

Updated Apr 28, 2025 • 2
OpenMOSS-Team/Lorsa-Pythia-160M

Updated May 8, 2025 • 1
OpenMOSS-Team/Lorsa-Llama-3.1-8B

Updated May 8, 2025 • 1

MHA2MLA

The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs"

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

Paper • 2502.14837 • Published Feb 20, 2025 • 4
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_16

Text Generation • 6B • Updated Mar 13, 2025 • 27 • 1
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_32

Text Generation • 6B • Updated Mar 13, 2025 • 26 • 1
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_64

Text Generation • 7B • Updated Mar 13, 2025 • 33 • 1

EasyWAM

OpenMOSS-Team/EasyWAM-MoT-Wan22

Robotics • Updated Sep 22 • 4
OpenMOSS-Team/EasyWAM-Unified-Wan22

Robotics • Updated Sep 22 • 3
OpenMOSS-Team/EasyWAM-Hidden-Wan22

Robotics • Updated Sep 22 • 3
OpenMOSS-Team/libero-lerobot-v3.0

Viewer • Updated Sep 22 • 279k • 478 • 4

OpenETA

openeta: embodied task agent

ETA: A New Agentic Paradigm for Embodied Tasks

Paper • 2608.03924 • Published Aug 4 • 11

MOSS Transcribe

A unified multimodal large language model for end-to-end speaker-attributed, time-stamped transcription.

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

Paper • 2601.01554 • Published Jan 4 • 66
Running

Agents

Featured

106

MOSS Transcribe Diarize

🏢

106

Transcribe audio or video with speaker diarization
OpenMOSS-Team/MOSS-Transcribe-preview-2B

Automatic Speech Recognition • 2B • Updated Jun 26 • 315 • 54
OpenMOSS-Team/MOSS-Transcribe-Diarize

Audio-Text-to-Text • 0.9B • Updated 10 days ago • 133k • 518

MOSS-Audio

An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex

Running

Agents

30

MOSS Audio 8B Thinking

🐢

30

Generate answers from uploaded audio or video
OpenMOSS-Team/MOSS-Audio-4B-Instruct

Audio-Text-to-Text • 5B • Updated Sep 25 • 2.29k • 90
OpenMOSS-Team/MOSS-Audio-4B-Thinking

Audio-Text-to-Text • 5B • Updated Sep 25 • 592 • 41
OpenMOSS-Team/MOSS-Audio-8B-Instruct

Audio-Text-to-Text • 9B • Updated Sep 25 • 1.58k • 56

MOSS-Video-Preview

OpenMOSS-Team/moss-video-preview-base

Video-Text-to-Text • 11B • Updated Aug 4 • 42 • 16
OpenMOSS-Team/moss-video-preview-sft

Video-Text-to-Text • 11B • Updated Aug 4 • 86 • 18
OpenMOSS-Team/moss-video-preview-realtime-sft

Video-Text-to-Text • 11B • Updated Aug 4 • 64 • 29
OpenMOSS-Team/Realtime-QA-100K

Viewer • Updated Jun 10 • 100k • 347 • 8

MOSS-VL

OpenMOSS-Team/MOSS-VL-Instruct-0408

Video-Text-to-Text • 11B • Updated Sep 23 • 195 • 108
OpenMOSS-Team/MOSS-VL-Base-0408

Video-Text-to-Text • 11B • Updated Sep 23 • 352 • 64
OpenMOSS-Team/MOSS-VL-Instruct-0708

Video-Text-to-Text • 11B • Updated Sep 23 • 327 • 34
OpenMOSS-Team/MOSS-VL-Base-0708

Video-Text-to-Text • 11B • Updated Sep 23 • 104 • 19

MOSS-TTS

OpenMOSS-Team/MOSS-TTS

Text-to-Speech • 8B • Updated Mar 20 • 4.4k • 437
OpenMOSS-Team/MOSS-TTS-Local-Transformer

Text-to-Speech • 3B • Updated Mar 20 • 151k • 32
OpenMOSS-Team/MOSS-TTS-Realtime

Text-to-Speech • 2B • Updated Jul 27 • 19.7k • 120
OpenMOSS-Team/MOSS-TTS-Nano-100M

Text-to-Speech • Updated Apr 13 • 120k • 252

AI Can Learn Scientific Taste

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 302
OpenMOSS-Team/SciJudgeBench

Viewer • Updated Sep 22 • 732k • 406 • 11
OpenMOSS-Team/SciJudge-4B-2605

Text Generation • 4B • Updated Jul 2 • 90 • 6
OpenMOSS-Team/SciJudge-30B-2605

Text Generation • 31B • Updated Jul 2 • 1.27k • 4

Llama Scope 2

Opensource Lorsas and Transcoders

OpenMOSS-Team/Llama-Scope-2

Updated Feb 10 • 1
OpenMOSS-Team/Llama-Scope-2-Qwen3-1.7B

Updated Apr 2 • 3

MOVA

OpenMOSS-Team/MOVA-360p

Image-to-Video • Updated Feb 15 • 183k • 219
OpenMOSS-Team/MOVA-720p

Any-to-Any • Updated Feb 11 • 308 • 134
MOVA: Towards Scalable and Synchronized Video-Audio Generation

Paper • 2602.08794 • Published Feb 9 • 159

MOSS-TTSD

OpenMOSS-Team/MOSS-TTSD-v1.0

Text-to-Speech • 8B • Updated Feb 14 • 12k • 64
OpenMOSS-Team/MOSS-TTSD-v0.7

Text-to-Speech • 2B • Updated Nov 11, 2025 • 236 • 18
OpenMOSS-Team/MOSS-TTSD-v0.5

Text-to-Speech • 2B • Updated Sep 2, 2025 • 282 • 54
OpenMOSS-Team/MOSS-TTSD-v0

Text-to-Speech • 2B • Updated Jun 20, 2025 • 35 • 28

MOSS-Speech

True Speech-to-Speech Langugage Model

OpenMOSS-Team/MOSS-Speech

9B • Updated Sep 30, 2025 • 277 • 24
OpenMOSS-Team/MOSS-Speech-Codec

0.9B • Updated Oct 1, 2025 • 128 • 7
Running on Zero

Agents

22

MOSS-Speech Demo

🚀

22

True Speech-to-Speech Language Model
MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Paper • 2510.00499 • Published Oct 1, 2025 • 23

ABC-Bench

Evaluating Agentic Backend Coding Capabilities in Real-World Development Scenarios

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

Paper • 2601.11077 • Published Jan 16 • 67
OpenMOSS-Team/ABC-Bench

Viewer • Updated Jan 20 • 224 • 279 • 4
OpenMOSS-Team/Qwen3-32B-ABC

Text Generation • 33B • Updated Jan 20 • 27 • 3
OpenMOSS-Team/Qwen3-8B-ABC

Text Generation • 8B • Updated Jan 20 • 1.08k • 3

FutureOmni

First Omni-modal Future Forecasting Benchmark

OpenMOSS-Team/FutureOmni

Viewer • Updated Jan 22 • 1.03k • 508 • 7
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Paper • 2601.13836 • Published Jan 20 • 37

Game-RL

[ICLR 2026] Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning

OpenMOSS-Team/GameQA-140K

Viewer • Updated Oct 2 • 300 • 2.54k • 23
OpenMOSS-Team/GameQA-5K

Preview • Updated Jun 22, 2025 • 280 • 2
OpenMOSS-Team/Game-RL-Qwen2.5-VL-7B

Image-Text-to-Text • 8B • Updated Jul 27, 2025 • 1.16k • 4
OpenMOSS-Team/Game-RL-InternVL3-8B

8B • Updated Jun 17, 2025 • 957 • 2

FRoM-W1

https://github.com/OpenMOSS/FRoM-W1

OpenMOSS-Team/FRoM-W1

Updated Feb 4 • 11
OpenMOSS-Team/FRoM-W1-Datasets

Viewer • Updated Jan 29 • 166k • 257 • 8
FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

Paper • 2601.12799 • Published Jan 19 • 4

DiRL

An Efficient Training Framework for Diffusion Language Models

OpenMOSS-Team/DiRL-8B-Instruct

Text Generation • 8B • Updated Jan 20 • 91 • 14

RoboOmni

Proactive Robot Manipulation in Omni-modal Context

OpenMOSS-Team/RoboOmni

Robotics • 5B • Updated Oct 30, 2025 • 65 • 16
OpenMOSS-Team/OmniAction

Updated Mar 27 • 205k • 295
OpenMOSS-Team/OmniAction-LIBERO

Updated Mar 27 • 6.52k • 70
OpenMOSS-Team/RoboOmni-LIBERO-Spatial

Robotics • 5B • Updated Oct 31, 2025 • 34 • 3

MOSS Embodied Planner

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Paper • 2503.10480 • Published Mar 13, 2025 • 55
Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning

Paper • 2506.23127 • Published Jun 29, 2025 • 2
World-aware Planning Narratives Enhance Large Vision-Language Model Planner

Paper • 2506.21230 • Published Jun 26, 2025 • 1
OpenMOSS-Team/Embodied_R1-ScienceWorld

8B • Updated Jun 30, 2025 • 19 • 1

Low Rank Sparse Attention

Open source weights of Lorsa modules introduced in "Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition".

OpenMOSS-Team/Lorsa

Updated Apr 28, 2025 • 2
OpenMOSS-Team/Lorsa-Pythia-160M

Updated May 8, 2025 • 1
OpenMOSS-Team/Lorsa-Llama-3.1-8B

Updated May 8, 2025 • 1

MHA2MLA-refactor

The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs"

OpenMOSS-Team/SmolLM-135M-MLA-d_kv_8-refactor

Text Generation • 0.1B • Updated Jun 23, 2025 • 28 • 1
OpenMOSS-Team/SmolLM-135M-MLA-d_kv_32-refactor

Text Generation • 0.1B • Updated Jun 17, 2025 • 21 • 1
OpenMOSS-Team/SmolLM-135M-MLA-d_kv_16-refactor

Text Generation • 0.1B • Updated Jun 17, 2025 • 23 • 1
OpenMOSS-Team/SmolLM-360M-MLA-d_kv_8-refactor

Text Generation • 0.3B • Updated Jun 17, 2025 • 23 • 1

MHA2MLA

The MHA2MLA model published in the paper "Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-Based LLMs"

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

Paper • 2502.14837 • Published Feb 20, 2025 • 4
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_16

Text Generation • 6B • Updated Mar 13, 2025 • 27 • 1
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_32

Text Generation • 6B • Updated Mar 13, 2025 • 26 • 1
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_64

Text Generation • 7B • Updated Mar 13, 2025 • 33 • 1

MOSS

OpenMOSS-Team/moss-moon-003-sft-plugin

Text Generation • Updated May 27 • 195 • 72
OpenMOSS-Team/moss-moon-003-sft

Text Generation • Updated May 27 • 254 • 129
OpenMOSS-Team/moss-moon-003-base

Text Generation • Updated May 27 • 222 • 132
OpenMOSS-Team/moss-moon-003-sft-int4

Text Generation • Updated May 27 • 174 • 41

AI & ML interests

Recent Activity

Papers

Articles

MOSS-Live: A Full-Duplex Real-Time Interaction System

Team members 59

OpenMOSS-Team 's collections 23

MOSS Transcribe Diarize

MOSS Audio 8B Thinking

MOSS-Speech Demo

MOSS Transcribe Diarize

MOSS Audio 8B Thinking

MOSS-Speech Demo