I’m curious, how does it fit your daily workflow as an engineer? Is it somewhere where you get the “news” for the day? Or do you use it for getting information relevant to your current work projects?
I never tracked is like news. I used it for two main things:
- Checking the state of the art (SotA) for a given problem. For some problems 2 year old solutions are still close to SotA; in others - there is a huge difference. And if there is a huge difference - is it because of architecture and parameter tuning, or using totally different architectures and training modes.
- Running code - to be used somewhere, or as a reference. Papers never have all details, and do not compile.
Context: I used to work in the field, as a consultant. Though, I cite Papers with Code in one overview paper.
You use it to find the code and data of a paper - since it also lists other implementations - to run additional baselines on Imagenet in order to appease reviewer #3( who has no idea why your paper on convex optimization has nothing to do with this but it's easier to run them than argue with them).
Pre-parenthesis part is dead serious, parenthesis part is slightly hyperbolic due to accumulated trauma with bad reviewers
It also gives an overview of the current state of the art for thousands of tasks and indexes current research by methods used, so you can quickly bootstrap research on a topic.
Another great resource is the HuggingFace model zoo. So many trained models easy to deploy.
- Checking the state of the art (SotA) for a given problem. For some problems 2 year old solutions are still close to SotA; in others - there is a huge difference. And if there is a huge difference - is it because of architecture and parameter tuning, or using totally different architectures and training modes.
- Running code - to be used somewhere, or as a reference. Papers never have all details, and do not compile.
Context: I used to work in the field, as a consultant. Though, I cite Papers with Code in one overview paper.