The exponential growth of the Internet of Things (IoT) necessitates the deployment of large-scale models capable of processing the complex and diverse data generated by IoT devices. However, the substantial memory requirements of these models pose significant challenges, especially in scenarios where rapid decision-making and low-latency responses are critical. To address these challenges, we propose three innovative strategies for optimizing large model usage in IoT environments. The first strategy is an adaptive loading scheme, which enables dynamic loading of individual model experts. The second strategy involves an expert-by-expert loading approach, further enhancing the ability to load experts as needed, which optimizes memory usage and accelerates computations. The third strategy employs an interlayer expert reuse mechanism, facilitating the efficient reuse of experts across different layers, thus enhancing response rates without compromising model accuracy. Importantly, these strategies can be directly applied to Mixture of Experts (MoE) large language models without requiring additional training, thereby providing a seamless and efficient solution for leveraging these models in memory-constrained, high-performance IoT environments.

In software development, the raw requirements proposed by users are frequently incomplete, which impedes the complete implementation of software functionalities. With the emergence of large language models, the exploration of generating software through user requirements has attracted attention. Recent methods with the top-down waterfall model employ a questioning approach for requirement completion, attempting to explore further user requirements. However, users, constrained by their domain knowledge, result in a lack of effective acceptance criteria during the requirement completion, failing to fully capture the implicit needs of the user. Moreover, the cumulative errors of the waterfall model can lead to discrepancies between the generated code and user requirements. The Agile methodologies reduce cumulative errors of the waterfall model through lightweight iteration and collaboration with users, but the challenge lies in ensuring semantic consistency between user requirements and the code generated by the agent. To address these challenges, we propose AgileGen, an agile-based generative software development through human-AI teamwork. Unlike existing questioning agents, AgileGen adopts a novel collaborative approach that breaks free from the constraints of domain knowledge by initiating the end-user perspective to complete the acceptance criteria. By introducing the Gherkin language, AgileGen attempts for the first time to use testable requirement descriptions as a bridge for semantic consistency between requirements and code, aiming to ensure that software products meet actual user requirements by defining user scenarios that include acceptance criteria. Additionally, we innovate in the human-AI teamwork model, allowing users to participate in decision-making processes they do well and significantly enhancing the completeness of software functionality. To ensure semantic consistency between requirements and generated code, we derive consistency factors from Gherkin to drive the subsequent software code generation. Finally, to improve the reliability of user scenarios, we also introduce a memory pool mechanism, collecting user decision-making scenarios and recommending them to new users with similar requirements. AgileGen, as a user-friendly interactive system, significantly outperformed existing best methods by 16.4% and garnered higher user satisfaction.

In partial label learning, each training sample corresponds to a set of candidate labels. The ground-truth label, hidden within this set, cannot be directly obtained during the training phase. The key to solving the partial label learning problem is to obtain ground-truth labels through label disambiguation. Existing works often rely on the label averaging assumption and do not fully investigate the class imbalance. Tail ground-truth labels are often overwhelmed by head pseudo-labels. The incorrectly identified labels could have contagiously negative impacts on the final predictions. In this paper, we propose a cost-guided retraining strategy, which achieves guidance and correction of disambiguation results, and provides instance-based class imbalance concerns for candidate labels. This approach significantly enhances the algorithm’s ability to handle class imbalance problems. The superiority of our method is demonstrated using 8 real-world datasets and 5 evaluation metrics. Code is available at https://github.com/DerrickZzyR/PL-CGR