Boyuan Wu

Zi'an Xu, Yin Dai, Fayu Liu et al.

Parotid gland tumor is a common type of head and neck tumor. Segmentation of the parotid glands and tumors by MR images is important for the treatment of parotid gland tumors. However, segmentation of the parotid glands is particularly challenging due to their variable shape and low contrast with surrounding structures. Recently deep learning has developed rapidly, which can handle complex problems. However, most of the current deep learning methods for processing medical images are still based on supervised learning. Compared with natural images, medical images are difficult to acquire and costly to label. Contrastive learning, as an unsupervised learning method, can more effectively utilize unlabeled medical images. In this paper, we used a Transformer-based contrastive learning method and innovatively trained the contrastive learning network with transfer learning. Then, the output model was transferred to the downstream parotid segmentation task, which improved the performance of the parotid segmentation model on the test set. The improved DSC was 89.60%, MPA was 99.36%, MIoU was 85.11%, and HD was 2.98. All four metrics showed significant improvement compared to the results of using a supervised learning model as a pre-trained model for the parotid segmentation network. In addition, we found that the improvement of the segmentation network by the contrastive learning model was mainly in the encoder part, so this paper also tried to build a contrastive learning network for the decoder part and discussed the problems encountered in the process of building.

Boyuan Wu

Cooperative Multi-Agent Reinforcement Learning (MARL) faces two major design bottlenecks: crafting dense reward functions and constructing curricula that avoid local optima in high-dimensional, non-stationary environments. Existing approaches rely on fixed heuristics or use Large Language Models (LLMs) directly in the control loop, which is costly and unsuitable for real-time systems. We propose MAESTRO (Multi-Agent Environment Shaping through Task and Reward Optimization), a framework that moves the LLM outside the execution loop and uses it as an offline training architect. MAESTRO introduces two generative components: (i) a semantic curriculum generator that creates diverse, performance-driven traffic scenarios, and (ii) an automated reward synthesizer that produces executable Python reward functions adapted to evolving curriculum difficulty. These components guide a standard MARL backbone (MADDPG) without increasing inference cost at deployment. We evaluate MAESTRO on large-scale traffic signal control (Hangzhou, 16 intersections) and conduct controlled ablations. Results show that combining LLM-generated curricula with LLM-generated reward shaping yields improved performance and stability. Across four seeds, the full system achieves +4.0% higher mean return (163.26 vs. 156.93) and 2.2% better risk-adjusted performance (Sharpe 1.53 vs. 0.70) over a strong curriculum baseline. These findings highlight LLMs as effective high-level designers for cooperative MARL training.