1. Clip-adapter: Better vision-language models with feature adapters;gao;ArXiv Preprint,2021
2. Cpt: Colorful prompt tuning for pre-trained vision-language models;yao;ArXiv Preprint,2021
3. Efficiently identifying task groupings for multi-task learning;fifty;Advances in Neural IInformation Processing Systems,2021
4. End-to-end multi-modal multi-task vehicle con-trol for self-driving cars with visual perceptions;yang;24th Inter-national Conference on Pattern Recognition (ICPR),0
5. Multi-Task Self-Training for Learning General Representations