Jiayu Wang

5

Papers

81

Total Citations

Papers (5)

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation

NeurIPS 2025arXiv

FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network

Highlight What You Want: Weakly-Supervised Instance-Level Controllable Infrared-Visible Image Fusion

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning