Siyu Zhou

FVG-PT: Adaptive Foreground View-Guided Prompt Tuning for Vision-Language Models

arXiv 2026

AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion

CVPR 2025 1

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

arXiv 2025

Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset

arXiv 2025

Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation

arXiv 2025

Qian He

Gen Li

Guodong Long

Jiawei Liu

Jing Jiang

Wanquan Feng

Bingchuan Li

Chao Wang

Chengqi Zhang

Deheng Ye