Jiawei Han

TL;DR: Experimental results show that MICoL significantly outperforms strong zero-shot text classification and contrastive learning baselines and is on par with the state-of-the-art supervised metadata-aware LMTC method trained on 10K–200K labeled documents, and tends to predict more infrequent labels than supervised methods, thus alleviates the deteriorated performance on long-tailed labels.

TL;DR: KnowEnG, a free-to-use computational system for analysis of genomics data sets, designed to accelerate biomedical discovery, is presented and its potential value in democratization of advanced tools for the modern genomics era is demonstrated.

TL;DR: Zhang et al. as discussed by the authors take the anonymous place graph from Facebook as an example to systematically study the problem of place deduplication: they carefully formulate the problem, study its connections to various related tasks, and arrive at a systematic two-step data-driven pipeline based on place embedding with multiple novel techniques.

TL;DR: It is found that cell mass homeostasis is robustly maintained, despite disruptions of the normal G1/S transition or cell growth rate, and together they form a compensatory network that strictly controls the coefficient of variation of cell mass in a population.