Tongyi-MAI

AI & ML interests

None defined yet.

Recent Activity

DyJiang authored a paper 2 days ago

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

DyJiang authored a paper 2 days ago

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

DyJiang authored a paper 2 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 Papers 4

Submitted by

taesiri

SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees

Tongyi-MAI

Submitted by

Zhen Li

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

Tongyi-MAI

Submitted by

Dongyang Liu (Chris Liu)

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

Tongyi-MAI

2

Distribution Matching Distillation Meets Reinforcement Learning

Tongyi-MAI