| Proj No. | A3217-251 |
| Title | Data-Efficient Tuning of Vision-Language Action Models |
| Summary | Vision-Language-Action (VLA) models have demonstrated significant potential in integrating visual and textual information to guide robotic actions. However, current VLA models often require extensive datasets and computational resources for effective training and tuning, posing challenges for data efficiency and scalability. This final-year project aims to develop data-efficient tuning techniques for VLA models, focusing on reducing the dependency on large-scale datasets while enhancing model performance. |
| Supervisor | Ast/P Wang Ziwei (Loc:S2 > S2 B2C > S2 B2C 83, Ext: +65 67906366) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Centre for Information Sciences & System (CISS) (Loc: S2-B4b-05) |
| Single/Group: | Single |
| Area: | Intelligent Systems and Control Engineering |
| ISP/RI/SMP/SCP?: |