arXiv:2606. 07007v1 Announce Type: cross Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs).
By Chenhao Zhang, Chris Lin, Su-In Lee
The paper reviews Cobweb, a computational model of categorization and concept formation, and extends it to include chunks and their acquisition. It introduces rellis/, an implementation that applies this unified theory to learning context-free grammars, demonstrating the system’s ability to represent syntactic knowledge, parse and generate sentences, and learn compositional structures from sample parses. The authors discuss related work on concepts and chunks and suggest directions for future research.
By Karthik Singaravadivelan, Pat Langley
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
By Alexandre Rocchi, Thomas Fel, Gianni Franchi
The paper introduces Mapping the Concept Landscape (MCL), a framework that replaces high‑dimensional feature embeddings with explicit sample‑level graphs of entities, events, and attributes for image‑caption pairs. By aggregating these graphs into a dataset‑level graph, MCL captures the global distribution of semantic concepts and identifies rare concepts. A greedy algorithm then selects samples to maximize coverage of under‑represented concepts, achieving better pruning efficiency and providing a transparent audit trail.
By Dongyue Wu, Tao Ma
arXiv:2603. 01227v3 Announce Type: replace Abstract: We propose the Lattice Representation Hypothesis of large language models: a symbolic backbone that grounds conceptual hierarchies and logical operations in embedding geometry.
By Bo Xiong
arXiv:2607. 04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaque latent feature spaces.
By Ifrat Ikhtear Uddin, Yang Zhou, KC Santosh, Longwei Wang