OpenMOSS

university

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

OpenMOSS

Activity Feed Request to join this org

AI & ML interests

LLM

Recent Activity

lkdhy updated a model about 6 hours ago

OpenMOSS-Team/SciThinker-30B

sinwang updated a dataset about 10 hours ago

OpenMOSS-Team/OmniAction

Frankstein73 updated a collection about 22 hours ago

Llama Scope 2

View all activity

Papers

AI Can Learn Scientific Taste

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

View all Papers

OpenMOSS-Team 's collections 18

AI Can Learn Scientific Taste

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published 4 days ago • 244
OpenMOSS-Team/SciJudgeBench

Preview • Updated 2 days ago • 23 • 4
OpenMOSS-Team/SciJudge-4B

Text Generation • 4B • Updated 2 days ago • 43 • 4
OpenMOSS-Team/SciJudge-30B

Text Generation • 31B • Updated 2 days ago • 43 • 6

MOSS-TTS

OpenMOSS-Team/MOSS-TTS

Text-to-Speech • 8B • Updated Feb 13 • 114k • 344
OpenMOSS-Team/MOSS-TTS-Realtime

Text-to-Speech • 2B • Updated Feb 15 • 87.4k • 65
OpenMOSS-Team/MOSS-TTS-Local-Transformer

Text-to-Speech • 3B • Updated 8 days ago • 68.2k • 21
OpenMOSS-Team/MOSS-Audio-Tokenizer

Feature Extraction • 2B • Updated Feb 13 • 87.6k • 37

MOSS-TTSD

OpenMOSS-Team/MOSS-TTSD-v1.0

Text-to-Speech • 8B • Updated Feb 14 • 15.4k • 49
OpenMOSS-Team/MOSS-TTSD-v0.7

Text-to-Speech • 2B • Updated Nov 11, 2025 • 257 • 17
OpenMOSS-Team/MOSS-TTSD-v0.5

Text-to-Speech • 2B • Updated Sep 2, 2025 • 1.56k • 53
OpenMOSS-Team/MOSS-TTSD-v0

Text-to-Speech • 2B • Updated Jun 20, 2025 • 4 • 27

MOSS-Speech

True Speech-to-Speech Langugage Model

OpenMOSS-Team/MOSS-Speech

9B • Updated Sep 30, 2025 • 55 • 18
OpenMOSS-Team/MOSS-Speech-Codec

0.9B • Updated Oct 1, 2025 • 25 • 5
Running on Zero

16

MOSS-Speech Demo

🚀

16

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

Paper • 2510.00499 • Published Oct 1, 2025 • 20

FutureOmni

First Omni-modal Future Forecasting Benchmark

OpenMOSS-Team/FutureOmni

Viewer • Updated Jan 22 • 1.03k • 243 • 3
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Paper • 2601.13836 • Published Jan 20 • 35

FRoM-W1

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

OpenMOSS-Team/FRoM-W1

Updated Feb 4 • 9
OpenMOSS-Team/FRoM-W1-Datasets

Viewer • Updated Jan 29 • 166k • 475 • 6
FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

Paper • 2601.12799 • Published Jan 19 • 3

RoboOmni

Proactive Robot Manipulation in Omni-modal Context

OpenMOSS-Team/RoboOmni

Robotics • Updated Oct 30, 2025 • 12 • 6
OpenMOSS-Team/RoboOmni-LIBERO-Spatial

Robotics • Updated Oct 31, 2025 • 11 • 2
OpenMOSS-Team/RoboOmni-LIBERO-Goal

Updated Oct 29, 2025 • 1
OpenMOSS-Team/RoboOmni-LIBERO-Object

Updated Oct 29, 2025 • 4

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

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 • 3
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_16

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

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

Text Generation • 7B • Updated Mar 13, 2025 • 20

Llama Scope 2

Opensource Lorsas and Transcoders

OpenMOSS-Team/Llama-Scope-2

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

Updated 20 days ago • 2

MOVA

OpenMOSS-Team/MOVA-360p

Image-to-Video • Updated Feb 15 • 32.3k • 210
OpenMOSS-Team/MOVA-720p

Any-to-Any • Updated Feb 11 • 515 • 124
MOVA: Towards Scalable and Synchronized Video-Audio Generation

Paper • 2602.08794 • Published Feb 9 • 156

MOSS Transcribe Diarize

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 • 58
Running

Featured

55

MOSS Transcribe Diarize

🏢

55

Transcribe audio/video with speaker diarization

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 • 66
OpenMOSS-Team/ABC-Bench

Viewer • Updated Jan 20 • 224 • 144 • 3
OpenMOSS-Team/Qwen3-32B-ABC

Text Generation • 33B • Updated Jan 20 • 3 • 1
OpenMOSS-Team/Qwen3-8B-ABC

Text Generation • 8B • Updated Jan 20 • 4 • 2

Game-RL

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

OpenMOSS-Team/GameQA-140K

Updated 16 days ago • 339 • 16
OpenMOSS-Team/GameQA-5K

Preview • Updated Jun 22, 2025 • 30 • 1
OpenMOSS-Team/Game-RL-Qwen2.5-VL-7B

Image-Text-to-Text • 8B • Updated Jul 27, 2025 • 45
OpenMOSS-Team/Game-RL-InternVL3-8B

8B • Updated Jun 17, 2025 • 5 • 1

DiRL

An Efficient Training Framework for Diffusion Language Models

OpenMOSS-Team/DiRL-8B-Instruct

Text Generation • 8B • Updated Jan 20 • 12 • 12

MOSS Embodied Planner

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

Paper • 2503.10480 • Published Mar 13, 2025 • 56
Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning

Paper • 2506.23127 • Published Jun 29, 2025 • 1
World-aware Planning Narratives Enhance Large Vision-Language Model Planner

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

8B • Updated Jun 30, 2025 • 3

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 • 3
OpenMOSS-Team/SmolLM-135M-MLA-d_kv_32-refactor

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

Text Generation • 0.1B • Updated Jun 17, 2025 • 3
OpenMOSS-Team/SmolLM-360M-MLA-d_kv_8-refactor

Text Generation • 0.3B • Updated Jun 17, 2025 • 2

MOSS

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

Text Generation • Updated Apr 25, 2023 • 22 • 69
OpenMOSS-Team/moss-moon-003-sft

Text Generation • Updated Apr 25, 2023 • 72 • 127
OpenMOSS-Team/moss-moon-003-base

Text Generation • Updated Apr 25, 2023 • 117 • 131
OpenMOSS-Team/moss-moon-003-sft-int4

Text Generation • Updated Apr 26, 2023 • 48 • 40

AI Can Learn Scientific Taste

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published 4 days ago • 244
OpenMOSS-Team/SciJudgeBench

Preview • Updated 2 days ago • 23 • 4
OpenMOSS-Team/SciJudge-4B

Text Generation • 4B • Updated 2 days ago • 43 • 4
OpenMOSS-Team/SciJudge-30B

Text Generation • 31B • Updated 2 days ago • 43 • 6

Llama Scope 2

Opensource Lorsas and Transcoders

OpenMOSS-Team/Llama-Scope-2

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

Updated 20 days ago • 2

MOSS-TTS

OpenMOSS-Team/MOSS-TTS

Text-to-Speech • 8B • Updated Feb 13 • 114k • 344
OpenMOSS-Team/MOSS-TTS-Realtime

Text-to-Speech • 2B • Updated Feb 15 • 87.4k • 65
OpenMOSS-Team/MOSS-TTS-Local-Transformer

Text-to-Speech • 3B • Updated 8 days ago • 68.2k • 21
OpenMOSS-Team/MOSS-Audio-Tokenizer

Feature Extraction • 2B • Updated Feb 13 • 87.6k • 37

MOVA

OpenMOSS-Team/MOVA-360p

Image-to-Video • Updated Feb 15 • 32.3k • 210
OpenMOSS-Team/MOVA-720p

Any-to-Any • Updated Feb 11 • 515 • 124
MOVA: Towards Scalable and Synchronized Video-Audio Generation

Paper • 2602.08794 • Published Feb 9 • 156

MOSS-TTSD

OpenMOSS-Team/MOSS-TTSD-v1.0

Text-to-Speech • 8B • Updated Feb 14 • 15.4k • 49
OpenMOSS-Team/MOSS-TTSD-v0.7

Text-to-Speech • 2B • Updated Nov 11, 2025 • 257 • 17
OpenMOSS-Team/MOSS-TTSD-v0.5

Text-to-Speech • 2B • Updated Sep 2, 2025 • 1.56k • 53
OpenMOSS-Team/MOSS-TTSD-v0

Text-to-Speech • 2B • Updated Jun 20, 2025 • 4 • 27

MOSS Transcribe Diarize

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 • 58
Running

Featured

55

MOSS Transcribe Diarize

🏢

55

Transcribe audio/video with speaker diarization

MOSS-Speech

True Speech-to-Speech Langugage Model

OpenMOSS-Team/MOSS-Speech

9B • Updated Sep 30, 2025 • 55 • 18
OpenMOSS-Team/MOSS-Speech-Codec

0.9B • Updated Oct 1, 2025 • 25 • 5
Running on Zero

16

MOSS-Speech Demo

🚀

16

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

Paper • 2510.00499 • Published Oct 1, 2025 • 20

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 • 66
OpenMOSS-Team/ABC-Bench

Viewer • Updated Jan 20 • 224 • 144 • 3
OpenMOSS-Team/Qwen3-32B-ABC

Text Generation • 33B • Updated Jan 20 • 3 • 1
OpenMOSS-Team/Qwen3-8B-ABC

Text Generation • 8B • Updated Jan 20 • 4 • 2

FutureOmni

First Omni-modal Future Forecasting Benchmark

OpenMOSS-Team/FutureOmni

Viewer • Updated Jan 22 • 1.03k • 243 • 3
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Paper • 2601.13836 • Published Jan 20 • 35

Game-RL

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

OpenMOSS-Team/GameQA-140K

Updated 16 days ago • 339 • 16
OpenMOSS-Team/GameQA-5K

Preview • Updated Jun 22, 2025 • 30 • 1
OpenMOSS-Team/Game-RL-Qwen2.5-VL-7B

Image-Text-to-Text • 8B • Updated Jul 27, 2025 • 45
OpenMOSS-Team/Game-RL-InternVL3-8B

8B • Updated Jun 17, 2025 • 5 • 1

FRoM-W1

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

OpenMOSS-Team/FRoM-W1

Updated Feb 4 • 9
OpenMOSS-Team/FRoM-W1-Datasets

Viewer • Updated Jan 29 • 166k • 475 • 6
FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

Paper • 2601.12799 • Published Jan 19 • 3

DiRL

An Efficient Training Framework for Diffusion Language Models

OpenMOSS-Team/DiRL-8B-Instruct

Text Generation • 8B • Updated Jan 20 • 12 • 12

RoboOmni

Proactive Robot Manipulation in Omni-modal Context

OpenMOSS-Team/RoboOmni

Robotics • Updated Oct 30, 2025 • 12 • 6
OpenMOSS-Team/RoboOmni-LIBERO-Spatial

Robotics • Updated Oct 31, 2025 • 11 • 2
OpenMOSS-Team/RoboOmni-LIBERO-Goal

Updated Oct 29, 2025 • 1
OpenMOSS-Team/RoboOmni-LIBERO-Object

Updated Oct 29, 2025 • 4

MOSS Embodied Planner

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

Paper • 2503.10480 • Published Mar 13, 2025 • 56
Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning

Paper • 2506.23127 • Published Jun 29, 2025 • 1
World-aware Planning Narratives Enhance Large Vision-Language Model Planner

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

8B • Updated Jun 30, 2025 • 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

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 • 3
OpenMOSS-Team/SmolLM-135M-MLA-d_kv_32-refactor

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

Text Generation • 0.1B • Updated Jun 17, 2025 • 3
OpenMOSS-Team/SmolLM-360M-MLA-d_kv_8-refactor

Text Generation • 0.3B • Updated Jun 17, 2025 • 2

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 • 3
OpenMOSS-Team/Llama-2-7B-MLA-d_kv_16

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

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

Text Generation • 7B • Updated Mar 13, 2025 • 20

MOSS

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

Text Generation • Updated Apr 25, 2023 • 22 • 69
OpenMOSS-Team/moss-moon-003-sft

Text Generation • Updated Apr 25, 2023 • 72 • 127
OpenMOSS-Team/moss-moon-003-base

Text Generation • Updated Apr 25, 2023 • 117 • 131
OpenMOSS-Team/moss-moon-003-sft-int4

Text Generation • Updated Apr 26, 2023 • 48 • 40

AI & ML interests

Recent Activity

Papers

Team members 31

OpenMOSS-Team 's collections 18

MOSS-Speech Demo

MOSS Transcribe Diarize

MOSS Transcribe Diarize

MOSS-Speech Demo