Ziyuan's picture

Ziyuan

zyhuangnus

·

AI & ML interests

None yet

Recent Activity

authored a paper 7 days ago

Vision-Centric Activation and Coordination for Multimodal Large Language Models

authored a paper 7 days ago

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

authored a paper 7 days ago

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders

View all activity

Organizations

upvoted a paper 8 days ago

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders

Paper • 2604.07340 • Published 9 days ago • 16

upvoted a paper 5 months ago

Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

Paper • 2510.24821 • Published Oct 28, 2025 • 41

upvoted 2 papers 6 months ago

ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

Paper • 2510.20803 • Published Oct 23, 2025 • 12

Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer

Paper • 2510.06590 • Published Oct 8, 2025 • 77

upvoted a collection 7 months ago

Ming-V2

Ming is the multi-modal series of any-to-any models developed by Ant Ling team. • 14 items • Updated 23 days ago • 35