2 papers
cs.LG2026
FedDis: A Causal Disentanglement Framework for Federated Traffic Prediction
Chengyang Zhou, Zijian Zhang, Chunxu Zhang +4
Federated learning offers a promising paradigm for privacy-preserving traffic prediction, yet its performance is often challenged by the non-identically and independently distribut…
cs.CV2025
DAPE: Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Video Editing with Diffusion Models
Junhao Xia, Chaoyang Zhang, Yecheng Zhang +4
Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches…