3 papers
cs.CV2026
OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space
Zhuding Liang, Tianyi Yan, Dubing Chen +6
Generative world models increasingly rely on 4D occupancy for realistic autonomous driving simulation. However, existing generation frameworks depend on rigid geometric conditions…
cs.LG2025
STGAtt: A Spatial-Temporal Unified Graph Attention Network for Traffic Flow Forecasting
Zhuding Liang, Jianxun Cui, Qingshuang Zeng +3
Accurate and timely traffic flow forecasting is crucial for intelligent transportation systems. This paper presents a novel deep learning model, the Spatial-Temporal Unified Graph…
cs.CV2024
UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control
Wenzhang Sun, Xiang Li, Donglin Di +5
Recently, animating portrait images using audio input is a popular task. Creating lifelike talking head videos requires flexible and natural movements, including facial and head dy…