Manifold-Aware Exploration for Reinforcement Learning in Video Generation
Paper • 2603.21872 • Published • 33
Dengyang Jiang
DyJiang
AI & ML interests
computer vision
deep learning
Recent Activity
liked a dataset about 15 hours ago
GenSearcher/Train-Data authored a paper 6 days ago
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning authored a paper 6 days ago
SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion TrainingOrganizations
upvoted a paper 8 days ago
upvoted a paper about 2 months ago
upvoted a paper 2 months ago
upvoted 3
papers 4 months ago
No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
Paper • 2505.02831 • Published • 2
Distribution Matching Distillation Meets Reinforcement Learning
Paper • 2511.13649 • Published • 6
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 244