AI & ML interests
None defined yet.
Recent Activity
Papers
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs.
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 ā¢ 104B ā¢ Updated ā¢ 2.75k ā¢ 266 -
inclusionAI/Ming-omni-tts-16.8B-A3B
Text-to-Speech ā¢ 18B ā¢ Updated ā¢ 86 ā¢ 34 -
inclusionAI/Ming-omni-tts-0.5B
Text-to-Speech ā¢ 2B ā¢ Updated ā¢ 3.84k ā¢ 37 -
inclusionAI/Ming-omni-tts-tokenizer-12Hz
Audio-to-Audio ā¢ 0.8B ā¢ Updated ā¢ 67 ā¢ 12
-
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Paper ā¢ 2602.11858 ā¢ Published ā¢ 64 -
inclusionAI/ZwZ-4B
Image-Text-to-Text ā¢ 5B ā¢ Updated ā¢ 490 ā¢ 33 -
inclusionAI/ZwZ-8B
Image-Text-to-Text ā¢ 9B ā¢ Updated ā¢ 391 ā¢ 45 -
inclusionAI/ZwZ-RL-VQA
Viewer ā¢ Updated ā¢ 111k ā¢ 2.49k ā¢ 13
-
inclusionAI/Ring-1T
Text Generation ā¢ 1000B ā¢ Updated ā¢ 121 ā¢ ā¢ 231 -
inclusionAI/Ring-1T-FP8
Text Generation ā¢ 1000B ā¢ Updated ā¢ 60 ā¢ 20 -
inclusionAI/Ring-1T-preview
Text Generation ā¢ 1000B ā¢ Updated ā¢ 68 ā¢ 268 -
inclusionAI/Ring-1T-preview-FP8
Text Generation ā¢ 1000B ā¢ Updated ā¢ 33 ā¢ 4
-
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper ā¢ 2604.20796 ā¢ Published ā¢ 243 -
inclusionAI/LLaDA2.0-Uni
Any-to-Any ā¢ 16B ā¢ Updated ā¢ 6.82k ā¢ 247 -
inclusionAI/LLaDA2.0-Uni-FP8
Any-to-Any ā¢ 16B ā¢ Updated ā¢ 5.68k ā¢ 5 -
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
Paper ā¢ 2512.15745 ā¢ Published ā¢ 90
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.
The Agent Runtime for Self-Improvement
-
UI-Venus-1.5 Technical Report
Paper ā¢ 2602.09082 ā¢ Published ā¢ 158 -
inclusionAI/UI-Venus-1.5-30B-A3B
Image-Text-to-Text ā¢ 31B ā¢ Updated ā¢ 2.25k ā¢ 28 -
inclusionAI/UI-Venus-1.5-8B
Image-Text-to-Text ā¢ 9B ā¢ Updated ā¢ 5.27k ā¢ 28 -
inclusionAI/UI-Venus-1.5-2B
Image-Text-to-Text ā¢ 2B ā¢ Updated ā¢ 2.13k ā¢ 38
-
Ming-Omni: A Unified Multimodal Model for Perception and Generation
Paper ā¢ 2506.09344 ā¢ Published ā¢ 33 -
inclusionAI/Ming-Lite-Omni
Any-to-Any ā¢ 19B ā¢ Updated ā¢ 50 ā¢ 200 -
inclusionAI/Ming-Lite-Omni-1.5
Any-to-Any ā¢ 19B ā¢ Updated ā¢ 339 ā¢ 86 -
inclusionAI/Ming-UniAudio-16B-A3B
Any-to-Any ā¢ 18B ā¢ Updated ā¢ 101 ā¢ 80
Ring
-
inclusionAI/DR-Venus-4B-SFT
4B ā¢ Updated ā¢ 438 ā¢ 7 -
inclusionAI/DR-Venus-4B-RL
4B ā¢ Updated ā¢ 614 ā¢ 13 -
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
Paper ā¢ 2604.19859 ā¢ Published ā¢ 53 -
inclusionAI/DR-Venus-4B-RL-GGUF
4B ā¢ Updated ā¢ 198 ā¢ 10
-
inclusionAI/Ling-1T
Text Generation ā¢ 1000B ā¢ Updated ā¢ 3.53k ā¢ ā¢ 541 -
inclusionAI/Ling-flash-2.0
Text Generation ā¢ 103B ā¢ Updated ā¢ 2.61k ā¢ 215 -
inclusionAI/Ling-mini-2.0
Text Generation ā¢ 16B ā¢ Updated ā¢ 44.5k ā¢ 193 -
inclusionAI/Ling-mini-2.0-GGUF
16B ā¢ Updated ā¢ 1.11k ā¢ 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 ā¢ 17B ā¢ Updated ā¢ 75 ā¢ 77 -
inclusionAI/Ling-lite-1.5-2506
Text Generation ā¢ 17B ā¢ Updated ā¢ 83 ā¢ 53 -
inclusionAI/Ling-lite-1.5
Text Generation ā¢ 17B ā¢ Updated ā¢ 49.6k ā¢ 58 -
inclusionAI/Ling-lite-base-1.5
Text Generation ā¢ 17B ā¢ Updated ā¢ 79 ā¢ 34
AReaL-boba-2
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.
-
inclusionAI/DR-Venus-4B-SFT
4B ā¢ Updated ā¢ 438 ā¢ 7 -
inclusionAI/DR-Venus-4B-RL
4B ā¢ Updated ā¢ 614 ā¢ 13 -
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
Paper ā¢ 2604.19859 ā¢ Published ā¢ 53 -
inclusionAI/DR-Venus-4B-RL-GGUF
4B ā¢ Updated ā¢ 198 ā¢ 10
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 ā¢ 104B ā¢ Updated ā¢ 2.75k ā¢ 266 -
inclusionAI/Ming-omni-tts-16.8B-A3B
Text-to-Speech ā¢ 18B ā¢ Updated ā¢ 86 ā¢ 34 -
inclusionAI/Ming-omni-tts-0.5B
Text-to-Speech ā¢ 2B ā¢ Updated ā¢ 3.84k ā¢ 37 -
inclusionAI/Ming-omni-tts-tokenizer-12Hz
Audio-to-Audio ā¢ 0.8B ā¢ Updated ā¢ 67 ā¢ 12
-
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Paper ā¢ 2602.11858 ā¢ Published ā¢ 64 -
inclusionAI/ZwZ-4B
Image-Text-to-Text ā¢ 5B ā¢ Updated ā¢ 490 ā¢ 33 -
inclusionAI/ZwZ-8B
Image-Text-to-Text ā¢ 9B ā¢ Updated ā¢ 391 ā¢ 45 -
inclusionAI/ZwZ-RL-VQA
Viewer ā¢ Updated ā¢ 111k ā¢ 2.49k ā¢ 13
-
inclusionAI/Ring-1T
Text Generation ā¢ 1000B ā¢ Updated ā¢ 121 ā¢ ā¢ 231 -
inclusionAI/Ring-1T-FP8
Text Generation ā¢ 1000B ā¢ Updated ā¢ 60 ā¢ 20 -
inclusionAI/Ring-1T-preview
Text Generation ā¢ 1000B ā¢ Updated ā¢ 68 ā¢ 268 -
inclusionAI/Ring-1T-preview-FP8
Text Generation ā¢ 1000B ā¢ Updated ā¢ 33 ā¢ 4
-
inclusionAI/Ling-1T
Text Generation ā¢ 1000B ā¢ Updated ā¢ 3.53k ā¢ ā¢ 541 -
inclusionAI/Ling-flash-2.0
Text Generation ā¢ 103B ā¢ Updated ā¢ 2.61k ā¢ 215 -
inclusionAI/Ling-mini-2.0
Text Generation ā¢ 16B ā¢ Updated ā¢ 44.5k ā¢ 193 -
inclusionAI/Ling-mini-2.0-GGUF
16B ā¢ Updated ā¢ 1.11k ā¢ 27
-
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper ā¢ 2604.20796 ā¢ Published ā¢ 243 -
inclusionAI/LLaDA2.0-Uni
Any-to-Any ā¢ 16B ā¢ Updated ā¢ 6.82k ā¢ 247 -
inclusionAI/LLaDA2.0-Uni-FP8
Any-to-Any ā¢ 16B ā¢ Updated ā¢ 5.68k ā¢ 5 -
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
Paper ā¢ 2512.15745 ā¢ Published ā¢ 90
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.
-
UI-Venus-1.5 Technical Report
Paper ā¢ 2602.09082 ā¢ Published ā¢ 158 -
inclusionAI/UI-Venus-1.5-30B-A3B
Image-Text-to-Text ā¢ 31B ā¢ Updated ā¢ 2.25k ā¢ 28 -
inclusionAI/UI-Venus-1.5-8B
Image-Text-to-Text ā¢ 9B ā¢ Updated ā¢ 5.27k ā¢ 28 -
inclusionAI/UI-Venus-1.5-2B
Image-Text-to-Text ā¢ 2B ā¢ Updated ā¢ 2.13k ā¢ 38
-
inclusionAI/Ling-lite-1.5-2507
Text Generation ā¢ 17B ā¢ Updated ā¢ 75 ā¢ 77 -
inclusionAI/Ling-lite-1.5-2506
Text Generation ā¢ 17B ā¢ Updated ā¢ 83 ā¢ 53 -
inclusionAI/Ling-lite-1.5
Text Generation ā¢ 17B ā¢ Updated ā¢ 49.6k ā¢ 58 -
inclusionAI/Ling-lite-base-1.5
Text Generation ā¢ 17B ā¢ Updated ā¢ 79 ā¢ 34
AReaL-boba-2
-
Ming-Omni: A Unified Multimodal Model for Perception and Generation
Paper ā¢ 2506.09344 ā¢ Published ā¢ 33 -
inclusionAI/Ming-Lite-Omni
Any-to-Any ā¢ 19B ā¢ Updated ā¢ 50 ā¢ 200 -
inclusionAI/Ming-Lite-Omni-1.5
Any-to-Any ā¢ 19B ā¢ Updated ā¢ 339 ā¢ 86 -
inclusionAI/Ming-UniAudio-16B-A3B
Any-to-Any ā¢ 18B ā¢ Updated ā¢ 101 ā¢ 80