This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Computer Vision and Machine Learning at MPI Informatics
cvml.mpi-inf.mpg.de
did:plc:lv4cgkwqc6dwkupbw4fnuric
7/ 🧵 Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
Authors: S. Rao, S. Mahajan, M. Böhle, B. Schiele
🔍 Explore sparse autoencoders to automatically extract and name concepts, enabling performance improvements on downstream tasks.
📚 arxiv.org/abs/2407.14499
2025-06-11T20:44:59.071Z