Logit Knowledge Distillation has gained substantial research interest in recent years due to its simplicity and lack of requirement for intermediate feature alignment; however, it suffers from limited interpretability in its decision-making process. To address this, we propose implicit Clustering Distillation (iCD): a simple and effective method that mines and transfers interpretable structural knowledge from logits, without requiring ground-truth labels or feature-space alignment. iCD leverages Gram matrices over decoupled local logit representations to enable student models to learn latent semantic structural patterns. Extensive experiments on benchmark datasets demonstrate the effectiveness of iCD across diverse teacher-student architectures, with particularly strong performance in fine-grained classification tasks---achieving a peak improvement of +5.08% over the baseline.

Multi-Agent Reinforcement Learning (MARL) has shown significant promise in tackling complex cooperative tasks, largely due to parameter sharing among agents. However, while this sharing facilitates teamwork, it can also result in agent homogenization, which limits individualized behaviors. To address this issue, we introduce a novel method called Diverse Collaboration in Multi-Agent Reinforcement Learning via Self-Adaptive Method (DC-SA). DC-SA advances individualized behaviors by maximizing the mutual information between agents’ representations and their trajectories to enhance diversity collaboration. The method employs adaptive weights to balance collaboration and individualization, particularly in scenarios where collaboration is challenging. Our empirical results demonstrate that DC-SA outperforms five baselines on the StarCraft II micromanagement tasks.

The development of powerful software tools that apply and facilitate the use of formal notations and methodologies effectively has been crucial. This paper introduces a new software tool that fully supports the construction of SOFL specifications in a user-friendly manner. With this tool it would be helpful to construct a SOFL specification that consists of condition data flow diagrams and specification modules, as well as take advantage of build in features that improve the correctness and integrity of specifications.