Tongyi-MAI

AI & ML interests

None defined yet.

Recent Activity

DyJiang authored a paper 6 days ago

Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning

DyJiang authored a paper 6 days ago

SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training

DyJiang authored a paper 6 days ago

Manifold-Aware Exploration for Reinforcement Learning in Video Generation

View all activity

Papers

SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

View all Papers

Tongyi-MAI 's models 4

Tongyi-MAI/Z-Image-Turbo

Text-to-Image • Updated Jan 30 • 838k • • 4.37k

Tongyi-MAI/Z-Image

Text-to-Image • Updated Jan 28 • 52.1k • • 1.02k

Tongyi-MAI/MAI-UI-8B

Image-Text-to-Text • 9B • Updated Jan 9 • 4.77k • 187

Tongyi-MAI/MAI-UI-2B

Updated Dec 29, 2025 • 1.17k • 48