2. AsapASAP: Prioritizing Attention via Time Series Smoothing
3. ColbertColBERT: Contextualized Late Interaction over BERT (SIGIR'20 paper)
5. FastEnd-to-end earthquake detection pipeline via efficient time series similarity search
6. Equivariant Transformers Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.org/abs/1901.11399
7. Acidrain2AD analysis prototype and logs from sample applications
9. SparserSparser: Raw Filtering for Faster Analytics over Raw Data
11. wmsketchSketching linear classifiers over data streams with the Weight-Median Sketch (SIGMOD 2018).
14. gavelCode for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020
15. POPCode for "Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP", which appeared at SOSP 2021
18. sinkhorn-label-allocationSinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in full in this ICML 2021 paper: https://arxiv.org/abs/2102.08622.
19. WillumpWillump Is a Low-Latency Useful Machine learning Platform.