The evolving worldly dynamics necessitate continuous revision and updating of knowledge within Large Language Models (LLMs), driving the development of Knowledge Editing (KE) techniques. Recently, a novel paradigm of Temporal Knowledge Editing (TKE) has been proposed, emphasizing that models deployed in dynamic environments should integrate new information while retaining historical knowledge. However, we observe that current definitions and methods for TKE are insufficient, as they do not effectively capture or adapt to the fine-grained temporal dynamics inherent in real-world knowledge evolution. In this paper, we introduce the notion of multi-granularity TKE, encompassing temporal knowledge across yearly, monthly, and daily granularities, and propose a corresponding dataset, named MTKE. We argue that comprehending and retaining knowledge across different temporal granularities is crucial for LLMs to accurately reflect real-world changes. The key challenge lies in integrating new temporal knowledge at various granularities while also preserving relevant historical knowledge, thus ensuring LLMs maintain a consistent and accurate understanding over time. To achieve this, we propose a Sparse Parameter-Injected Knowledge Editing method, dubbed SPIKE, which anchors both temporal knowledge and subject positions within the model. Experiments demonstrate that our method effectively preserves historical knowledge performance while accurately incorporating dynamic temporal knowledge across multi-granularity temporal scenarios.

Continual Few-shot Relation Extraction (CFRE) aims to continually learn new relations from limited labeled data while preserving knowledge about previously learned relations. Facing the inherent issue of catastrophic forgetting, previous approaches predominantly rely on memory replay strategies. However, they often overlook task interference in continual learning and the varying memory requirements for different relations. To address these shortcomings, we propose a novel framework, DPC-FT, which features: 1) a lightweight relation encoder for each task to mitigate negative knowledge transfer across tasks; 2) a dynamic prototype module to allocate less memory for easier relations and more memory for harder relations. Additionally, we introduce the None-Of-The-Above (NOTA) detection in CFRE and propose a threshold criterion to identify relations that have never been learned. Extensive experiments demonstrate the effectiveness and efficiency of our method in CFRE, making our approach more practical and comprehensive for real-world scenarios.

The enzyme turnover rate, ${k}_{cat}$, quantifies enzyme kinetics by indicating the maximum efficiency of enzyme catalysis. Despite its importance, ${k}_{cat}$ values remain scarce in databases for most organisms, primarily because of the cost of experimental measurements. To predict ${k}_{cat}$ and account for its strong temperature dependence, DLTKcat was developed in this study and demonstrated superior performance (log10-scale root mean squared error = 0.88, R-squared = 0.66) than previously published models. Through two case studies, DLTKcat showed its ability to predict the effects of protein sequence mutations and temperature changes on ${k}_{cat}$ values. Although its quantitative accuracy is not high enough yet to model the responses of cellular metabolism to temperature changes, DLTKcat has the potential to eventually become a computational tool to describe the temperature dependence of biological systems.