Post
599
New release from Ant Group 🔥
inclusionAI/ming-v2-68ddea4954413c128d706630
✨MingTok (Vision & Audio): continuous unified tokenizer, no quantization, preserves semantic & perceptual fidelity, enables faster convergence.
✨Ming-UniVision: MLLM unifying image understanding + generation, supports multi-round editing & visualized CoT.
✨Ming-UniAudio: unified speech LLM for ASR, TTS & free-form editing, integrates semantic + acoustic features for high-fidelity audio.
inclusionAI/ming-v2-68ddea4954413c128d706630
✨MingTok (Vision & Audio): continuous unified tokenizer, no quantization, preserves semantic & perceptual fidelity, enables faster convergence.
✨Ming-UniVision: MLLM unifying image understanding + generation, supports multi-round editing & visualized CoT.
✨Ming-UniAudio: unified speech LLM for ASR, TTS & free-form editing, integrates semantic + acoustic features for high-fidelity audio.