{"total":32,"rows":[{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2602.02315","title":"The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors","created":"2026-02-02","cited_by_count":15,"area":null},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2602.02385","title":"Transformers learn factored representations","created":"2026-02-02","cited_by_count":7,"area":null},{"id":"2602.06065","title":"Deep networks learn to parse uniform-depth context-free languages from local statistics","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2602.02224","title":"Spectral Superposition: A Theory of Feature Geometry","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.04752","title":"Decomposing Query-Key Feature Interactions Using Contrastive Covariances","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2605.09011","title":"A Geometric Perspective on Next-Token Prediction in Large Language Models: Three Emerging Phases","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2605.02715","title":"Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2605.03780","title":"Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.23821","title":"Hierarchical Concept Geometry in Language Models Emerges from Word Co-occurrence","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.27970","title":"Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2603.19849","title":"Semantic Delta: An Interpretable Signal Differentiating Human and LLMs Dialogue","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.05469","title":"Task Ecologies and the Evolution of World-Tracking Representations in Large Language Models","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.07095","title":"Multilingual Embedding Probes Fail to Generalize Across Learner Corpora","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.07127","title":"The Position Curse: LLMs Struggle to Locate the Last Few Items in a List","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.12207","title":"Not How Many, But Which: Parameter Placement in Low-Rank Adaptation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.01302","title":"Structure and Scale in Simplicial Sequence Modelling","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.13934","title":"Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.04167","title":"Geometry of Ordinal Representations in Language Models","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.10578","title":"Laguerre Geometry for Interpreting Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.12279","title":"A Shared Subcircuit Lets LLMs Count Down Across Tasks","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.27092","title":"Sky sphere representation in language models","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.01551","title":"What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13072","title":"MAxBench: A Multinomial Concept Recovery Benchmark","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.28086","title":"LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.35663","title":"Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35970","title":"Causal and Interpretable Structures in LLM Compositional Tasks","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}