• Yong Zhuang: Data science will only become more critical to efforts in science in engineering, such as understanding the neural basis of cognition, extracting and predicting coherent changes in the climate, stabilizing financial markets, managing the spread of disease, and controlling turbulence, where data are abundant, but physical laws remain elusive.source
• Tianyu Kang: Besides the theoretical guarantees, we empirically validate the proposed algorithm on benchmark datasets across both classical algorithms as well as modern DNN architectures.source
• Hefei Qiu: Sentence embeddings are an important component of many natural language processing(NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such as clustering and retrieval. Unlike word embeddings, the highest performing solutions for learning sentence embeddings require labelled data, limiting their usefulness to languages and domains where labelled data is abundant.source
• Zihan Li: We argue that such benchmarks do little to move the field forward, and in fact may hold it back as they reward techniques that are effective at rapidly solving trivial problems rather than performing as well as possible on hard ones.source
• Chengjie Zheng: We present a conceptually simple, flexible, and general framework for object instance segmentation.source
• Wei Ding: Writing with the Reader in Mind: Expectation and Context Readers do not simply read; they interpret. Any piece of prose, no matter how short, may “mean” in 10 (or more) different ways to 10 different readers. This methodology of reader expectations is founded on the recognition that readers make many of their most important interpretive decisions about the substance of prose based on clues they receive from its structure.source