arxiv:2603.21872
Dengyang Jiang
DyJiang
AI & ML interests
computer vision
deep learning
Recent Activity
authored a paper 1 day ago
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning authored a paper 1 day ago
SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training authored a paper 1 day ago
Manifold-Aware Exploration for Reinforcement Learning in Video Generation