inclusionAI/Ming-flash-omni-Preview
Any-to-Any
•
104B
•
Updated
•
1.53k
•
65
Ming-V2
-
-
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
Paper • 2510.24821 • Published • 38 -
inclusionAI/MingTok-Vision
Image Feature Extraction • 0.7B • Updated • 232 • 31 -
inclusionAI/Ming-UniVision-16B-A3B
Any-to-Any • 19B • Updated • 50 • 62 -
inclusionAI/Ming-UniAudio-16B-A3B
Any-to-Any • 18B • Updated • 80 • 73 -
inclusionAI/Ming-UniAudio-16B-A3B-Edit
18B • Updated • 108 • 28 -
inclusionAI/MingTok-Audio
1B • Updated • 80 • 26 -
inclusionAI/Ming-Freeform-Audio-Edit-Benchmark
Viewer • Updated • 2.28k • 1.89k • 9 -
Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
Paper • 2510.06590 • Published • 73 -
Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation
Paper • 2511.05516 • Published • 10