Xinyu Zhang
- CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
- FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
- Generalizing Experience for Language Agents with Hierarchical MetaFlows
- Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation
- Scaling Diffusion Transformers Efficiently via $\mu$P
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception