Tongyi-MAI

AI & ML interests

None defined yet.

Recent Activity

DyJiang submitted a paper about 3 hours ago

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

DyJiang authored a paper about 1 month ago

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

DyJiang authored a paper about 1 month ago

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

View all activity

Papers

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees

View all Papers

Tongyi-MAI 's Papers 5

Submitted by

Dengyang Jiang

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Tongyi-MAI

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