Two-Stage Mixture-of-LoRA for Multi-Task Medical Vision-Language Learning
The proposed framework uses a shared-specific Mixture-of-LoRA architecture comprising one shared LoRA and six task-specific expert LoRAs, together with a two-stage training procedure, and achieves good results in the FLARE 2026 Task 3 test sets.
Zhang-Hao Chen, Yuan-Yuan Li, Zhen-Yu Lu et al.
· 0 citations