[2606.02841] Learning Coherent Representations: A Topological Approach to Interpretability
Abstract page for arXiv paper 2606.02841: Learning Coherent Representations: A Topological Approach to Interpretability
America Forever Bytes
Other
Abstract page for arXiv paper 2606.02841: Learning Coherent Representations: A Topological Approach to Interpretability
Abstract page for arXiv paper 2606.02633: Generalized polygonal number representations
Abstract page for arXiv paper 2606.01868: Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
Abstract page for arXiv paper 2605.28870: Representation Alignment Rests on Linear Structure
Abstract page for arXiv paper 2605.27970: Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations