Dengyang Jiang

DyJiang's activity

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

upvoted a paper 1 day ago

OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

Paper • 2607.08766 • Published 3 days ago • 8

upvoted a paper 9 days ago

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

Paper • 2607.02508 • Published 10 days ago • 14

upvoted a paper 30 days ago

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

Paper • 2606.12575 • Published Jun 10 • 13

upvoted a paper about 1 month ago

Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions

Paper • 2606.09076 • Published Jun 8 • 65

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 • 29

upvoted a paper 4 months ago

Manifold-Aware Exploration for Reinforcement Learning in Video Generation

Paper • 2603.21872 • Published Mar 23 • 34

upvoted a paper 5 months ago

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

Paper • 2601.21037 • Published Jan 28 • 15

upvoted a paper 6 months ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 183

upvoted 3 papers 7 months ago

No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves

Paper • 2505.02831 • Published May 5, 2025 • 2

Distribution Matching Distillation Meets Reinforcement Learning

Paper • 2511.13649 • Published Nov 17, 2025 • 6

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

Paper • 2511.22699 • Published Nov 27, 2025 • 248