--- tags: PSE --- # ZKML @ Team Novi Click here to know more about [Team Novi](https://0xparc.notion.site/Team-Novi-2d81bc06b0aa4c99b61a9ee06166b3b6) ## Proposed work schedule: 1. [Research and proposal](#1-Research-and-proposal) (2 weeks) 2. [Implementation and benchmark](#2-Implementation-and-benchmark) (5 weeks) 3. [Recommendation and feature requests for Nova](#3-Recommendation-and-feature-requests-for-Nova) (1 week) ## 1. Research and proposal Previously, Nova has been used to fold [models](https://github.com/lyronctk/zator) and [batch inference](https://hackmd.io/@cathie/zkml-folding). What else can we fold? Starting points: * convolutional layer operations? * dense layer operations? * activation layer operations? * ... ## 2. Implementation and benchmark ... ## 3. Recommendation and feature requests for Nova During the process of implementing [Zator](https://github.com/lyronctk/zator), we realized the need to parallelize some operations in [Nova-Scotia](https://github.com/nalinbhardwaj/Nova-Scotia/). After 5 weeks of implementation, we should gain a lot of insights as to what needs to be done to make tools surrounding Nova more user-friendly and effective.