inclusionAI
Team
community
AI & ML interests
None defined yet.
Recent Activity
Papers
Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision
Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
Team members 96 private
Ring
-
robbyant/lingbot-world-base-cam
Image-to-Video • Updated • 341 -
robbyant/lingbot-world-base-act-preview
Image-to-Video • Updated • 21 -
robbyant/lingbot-world-fast
Image-to-Video • 19B • Updated • 10k • 22 -
robbyant/lingbot-world-fast-diffusers
Image-to-Video • 19B • Updated • 3.49k • 7
The newest flagship non-reasoning model series.
Ming is the multi-modal series of any-to-any models developed by Ant Ling team.
-
inclusionAI/Ming-flash-omni-2.0
Any-to-Any • 104B • Updated • 2.51k • 274 -
inclusionAI/Ming-omni-tts-16.8B-A3B
Text-to-Speech • 18B • Updated • 200 • 54 -
inclusionAI/Ming-omni-tts-0.5B
Text-to-Speech • 2B • Updated • 11.5k • 38 -
inclusionAI/Ming-omni-tts-tokenizer-12Hz
Audio-to-Audio • 0.8B • Updated • 39 • 10
-
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Paper • 2602.11858 • Published • 61 -
inclusionAI/ZwZ-4B
Image-Text-to-Text • 5B • Updated • 358 • 32 -
inclusionAI/ZwZ-8B
Image-Text-to-Text • 9B • Updated • 2.42k • 50 -
inclusionAI/ZwZ-RL-VQA
Viewer • Updated • 111k • 4.13k • 17
-
inclusionAI/Ling-1T
Text Generation • 1000B • Updated • 2.65k • • 544 -
inclusionAI/Ling-flash-2.0
Text Generation • 103B • Updated • 2.43k • 218 -
inclusionAI/Ling-mini-2.0
Text Generation • 16B • Updated • 11.7k • 198 -
inclusionAI/Ling-mini-2.0-GGUF
16B • Updated • 917 • 27
A collection of TwinFlow-accelerated diffusion models
GroveMoE is an open-source family of large language models developed by the AGI Center, Ant Research Institute.
-
inclusionAI/Ling-lite-1.5-2507
Text Generation • 17B • Updated • 124 • 77 -
inclusionAI/Ling-lite-1.5-2506
Text Generation • 17B • Updated • 78 • 52 -
inclusionAI/Ling-lite-1.5
Text Generation • 17B • Updated • 10.3k • 57 -
inclusionAI/Ling-lite-base-1.5
Text Generation • 17B • Updated • 72 • 33
AReaL-boba-2
Ling 3.0
Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
-
inclusionAI/SingGuard-NSFA-0.8B
Image-Text-to-Text • 1B • Updated • 1.65k • 7 -
inclusionAI/SingGuard-NSFA-2B
Image-Text-to-Text • 3B • Updated • 85 • 2 -
inclusionAI/SingGuard-NSFA-4B
Image-Text-to-Text • 5B • Updated • 694 • 3 -
inclusionAI/SingGuard-NSFA-9B
Image-Text-to-Text • 9B • Updated • 136 • 5
Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs.
-
inclusionAI/Ring-1T
Text Generation • 1000B • Updated • 289 • • 233 -
inclusionAI/Ring-flash-2.0
Text Generation • 103B • Updated • 209 • 102 -
inclusionAI/Ring-mini-2.0
Text Generation • 16B • Updated • 272 • 187 -
inclusionAI/Ring-mini-linear-2.0
Text Generation • 16B • Updated • 3.95k • 89
-
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 244 -
inclusionAI/LLaDA2.0-Uni
Any-to-Any • 16B • Updated • 4.51k • 250 -
inclusionAI/LLaDA2.0-Uni-FP8
Any-to-Any • 16B • Updated • 3.1k • 5 -
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
Paper • 2512.15745 • Published • 89
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.
The Agent Runtime for Self-Improvement
-
inclusionAI/UI-Venus-2-9B
Image-Text-to-Text • 1.47M • Updated • 1.38k • 17 -
UI-Venus-1.5 Technical Report
Paper • 2602.09082 • Published • 157 -
inclusionAI/UI-Venus-1.5-30B-A3B
Image-Text-to-Text • 31B • Updated • 2.66k • 36 -
inclusionAI/UI-Venus-1.5-8B
Image-Text-to-Text • 9B • Updated • 2.41k • 29
-
Ming-Omni: A Unified Multimodal Model for Perception and Generation
Paper • 2506.09344 • Published • 31 -
inclusionAI/Ming-Lite-Omni
Any-to-Any • 19B • Updated • 52 • 200 -
inclusionAI/Ming-Lite-Omni-1.5
Any-to-Any • 19B • Updated • 1.17k • 84 -
inclusionAI/Ming-UniAudio-16B-A3B
Any-to-Any • 18B • Updated • 58 • 80
Ling 3.0
Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
-
inclusionAI/SingGuard-NSFA-0.8B
Image-Text-to-Text • 1B • Updated • 1.65k • 7 -
inclusionAI/SingGuard-NSFA-2B
Image-Text-to-Text • 3B • Updated • 85 • 2 -
inclusionAI/SingGuard-NSFA-4B
Image-Text-to-Text • 5B • Updated • 694 • 3 -
inclusionAI/SingGuard-NSFA-9B
Image-Text-to-Text • 9B • Updated • 136 • 5
Ring
Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs.
-
robbyant/lingbot-world-base-cam
Image-to-Video • Updated • 341 -
robbyant/lingbot-world-base-act-preview
Image-to-Video • Updated • 21 -
robbyant/lingbot-world-fast
Image-to-Video • 19B • Updated • 10k • 22 -
robbyant/lingbot-world-fast-diffusers
Image-to-Video • 19B • Updated • 3.49k • 7
The newest flagship non-reasoning model series.
Ming is the multi-modal series of any-to-any models developed by Ant Ling team.
-
inclusionAI/Ming-flash-omni-2.0
Any-to-Any • 104B • Updated • 2.51k • 274 -
inclusionAI/Ming-omni-tts-16.8B-A3B
Text-to-Speech • 18B • Updated • 200 • 54 -
inclusionAI/Ming-omni-tts-0.5B
Text-to-Speech • 2B • Updated • 11.5k • 38 -
inclusionAI/Ming-omni-tts-tokenizer-12Hz
Audio-to-Audio • 0.8B • Updated • 39 • 10
-
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Paper • 2602.11858 • Published • 61 -
inclusionAI/ZwZ-4B
Image-Text-to-Text • 5B • Updated • 358 • 32 -
inclusionAI/ZwZ-8B
Image-Text-to-Text • 9B • Updated • 2.42k • 50 -
inclusionAI/ZwZ-RL-VQA
Viewer • Updated • 111k • 4.13k • 17
-
inclusionAI/Ring-1T
Text Generation • 1000B • Updated • 289 • • 233 -
inclusionAI/Ring-flash-2.0
Text Generation • 103B • Updated • 209 • 102 -
inclusionAI/Ring-mini-2.0
Text Generation • 16B • Updated • 272 • 187 -
inclusionAI/Ring-mini-linear-2.0
Text Generation • 16B • Updated • 3.95k • 89
-
inclusionAI/Ling-1T
Text Generation • 1000B • Updated • 2.65k • • 544 -
inclusionAI/Ling-flash-2.0
Text Generation • 103B • Updated • 2.43k • 218 -
inclusionAI/Ling-mini-2.0
Text Generation • 16B • Updated • 11.7k • 198 -
inclusionAI/Ling-mini-2.0-GGUF
16B • Updated • 917 • 27
-
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 244 -
inclusionAI/LLaDA2.0-Uni
Any-to-Any • 16B • Updated • 4.51k • 250 -
inclusionAI/LLaDA2.0-Uni-FP8
Any-to-Any • 16B • Updated • 3.1k • 5 -
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
Paper • 2512.15745 • Published • 89
A collection of TwinFlow-accelerated diffusion models
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.
The Agent Runtime for Self-Improvement
GroveMoE is an open-source family of large language models developed by the AGI Center, Ant Research Institute.
-
inclusionAI/UI-Venus-2-9B
Image-Text-to-Text • 1.47M • Updated • 1.38k • 17 -
UI-Venus-1.5 Technical Report
Paper • 2602.09082 • Published • 157 -
inclusionAI/UI-Venus-1.5-30B-A3B
Image-Text-to-Text • 31B • Updated • 2.66k • 36 -
inclusionAI/UI-Venus-1.5-8B
Image-Text-to-Text • 9B • Updated • 2.41k • 29
-
inclusionAI/Ling-lite-1.5-2507
Text Generation • 17B • Updated • 124 • 77 -
inclusionAI/Ling-lite-1.5-2506
Text Generation • 17B • Updated • 78 • 52 -
inclusionAI/Ling-lite-1.5
Text Generation • 17B • Updated • 10.3k • 57 -
inclusionAI/Ling-lite-base-1.5
Text Generation • 17B • Updated • 72 • 33
AReaL-boba-2
-
Ming-Omni: A Unified Multimodal Model for Perception and Generation
Paper • 2506.09344 • Published • 31 -
inclusionAI/Ming-Lite-Omni
Any-to-Any • 19B • Updated • 52 • 200 -
inclusionAI/Ming-Lite-Omni-1.5
Any-to-Any • 19B • Updated • 1.17k • 84 -
inclusionAI/Ming-UniAudio-16B-A3B
Any-to-Any • 18B • Updated • 58 • 80