HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant improvement in offline video understanding. However, extending these capabilities to streaming video inputs, remains challenging, as existing models struggle to simultaneously maintain stable understanding performance, real-time responses, and low GPU memory overhead. To address this challenge, we propose HERMES, a novel training-free architecture for real-time and accurate understanding of video streams. Based on a mechanistic attention investigation, we conceptualize KV cache as a hierarchical memory framework that encapsulates video information across multiple granularities. During inference, HERMES reuses a compact KV cache, enabling efficient streaming understanding under resource constraints. Notably, HERMES requires no auxiliary computations upon the arrival of user queries, thereby guaranteeing real-time responses for continuous video stream interactions, which achieves 10$\times$ faster TTFT compared to prior SOTA. Even when reducing video tokens by up to 68% compared with uniform sampling, HERMES achieves superior or comparable accuracy across all benchmarks, with up to 11.4% gains on streaming datasets.

Who will dropout from university? Academic risk prediction based on interpretable machine learning

In the institutional research mode, in order to explore which characteristics are the best indicators for predicting academic risk from the student behavior data sets that have high-dimensional, unbalanced classified small sample, it transforms the academic risk prediction of college students into a binary classification task. It predicts academic risk based on the LightGBM model and the interpretable machine learning method of Shapley value. The simulation results show that from the global perspective of the prediction model, characteristics such as the quality of academic partners, the seating position in classroom, the dormitory study atmosphere, the English scores of the college entrance examination, the quantity of academic partners, the addiction level of video games, the mobility of academic partners, and the degree of truancy are the best 8 predictors for academic risk. It is contrary to intuition that characteristics such as living in campus or not, work-study, lipstick addiction, student leader or not, lover amount, and smoking have little correlation with university academic risk in this experiment. From the local perspective of the sample, the factors affecting academic risk vary from person to person. It can perform personalized interpretable analysis through Shapley values, which cannot be done by traditional mathematical statistical prediction models. The academic contributions of this research are mainly in two aspects: First, the learning interaction networks is proposed for the first time, so that social behavior can be used to compensate for the one-sided individual behavior and improve the performance of academic risk prediction. Second, the introduction of Shapley value calculation makes machine learning that lacks a clear reasoning process visualized, and provides intuitive decision support for education managers.

Mining Meta-indicators of University Ranking: A Machine Learning Approach Based on SHAP

University evaluation and ranking is an extremely complex activity. Major universities are struggling because of increasingly complex indicator systems of world university rankings. So can we find the meta-indicators of the index system by simplifying the complexity? This research discovered three meta-indicators based on interpretable machine learning. The first one is time, to be friends with time, and believe in the power of time, and accumulate historical deposits; the second one is space, to be friends with city, and grow together by co-develop; the third one is relationships, to be friends with alumni, and strive for more alumni donations without ceiling.