Dongyang Liu (Chris Liu)

Cxxs's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 days ago

From SRA to Self-Flow: Data Augmentation or Self-Supervision?

Paper • 2607.02508 • Published 5 days ago • 11

upvoted 2 papers 25 days ago

High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation

Paper • 2606.12575 • Published 27 days ago • 13

Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions

Paper • 2606.09076 • Published 29 days ago • 65

upvoted a paper about 2 months ago

L2P: Unlocking Latent Potential for Pixel Generation

Paper • 2605.12013 • Published May 12 • 36

upvoted a paper 2 months ago

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

Paper • 2605.05204 • Published May 6 • 28

upvoted 2 papers 7 months ago

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

Paper • 2511.22699 • Published Nov 27, 2025 • 248

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

Paper • 2511.22677 • Published Nov 27, 2025 • 36

upvoted a collection almost 2 years ago

Lumina-mGPT Family

Collection

8 items • Updated Sep 9, 2025 • 5

upvoted 2 papers almost 2 years ago

Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Paper • 2408.02657 • Published Aug 5, 2024 • 35

SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

Paper • 2311.07575 • Published Nov 13, 2023 • 15