Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation Paper • 2510.24821 • Published Oct 28, 2025 • 41
view post Post 4438 At the close of the National Holiday🇨🇳, Antgroup drops a new SoTA model.Ling-1T 🔥 the trillion-parameter flagship of the Ling 2.0 series. inclusionAI/Ling-1T✨1T total / 50B active params per token ✨20T+ reasoning-dense tokens (Evo-CoT)✨128K context via YaRN ✨FP8 training: 15%+ faster, same precision as BF16 ✨Hybrid Syntax-Function-Aesthetics reward for front-end & visual generation See translation 1 reply · 🔥 8 8 + Reply
Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer Paper • 2510.06590 • Published Oct 8, 2025 • 77
Ming-V2 Collection Ming is the multi-modal series of any-to-any models developed by Ant Ling team. • 14 items • Updated 17 days ago • 35