{"total":55,"rows":[{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120,"area":null},{"id":"2105.03361","title":"What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory","created":"2021-05-07","cited_by_count":60,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2205.01510","title":"ExSpliNet: An interpretable and expressive spline-based neural network","created":"2022-05-03","cited_by_count":33,"area":null},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33,"area":"mechinterp"},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2110.08009","title":"MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining","created":"2021-10-15","cited_by_count":23,"area":null},{"id":"2203.01993","title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2206.08615","title":"On the Number of Regions of Piecewise Linear Neural Networks","created":"2022-06-17","cited_by_count":21,"area":null},{"id":"2301.09554","title":"Deep Learning Meets Sparse Regularization: A Signal Processing Perspective","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2210.05189","title":"Neural Networks are Decision Trees","created":"2022-10-11","cited_by_count":17,"area":null},{"id":"2306.07212","title":"Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision","created":"2023-06-12","cited_by_count":14,"area":null},{"id":"2312.01648","title":"Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2203.03099","title":"Singular Value Perturbation and Deep Network Optimization","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2203.11355","title":"Origami in N dimensions: How feed-forward networks manufacture linear separability","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2411.00392","title":"Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization","created":"2024-11-01","cited_by_count":9,"area":null},{"id":"2209.14778","title":"Batch Normalization Explained","created":"2022-09-29","cited_by_count":8,"area":null},{"id":"2501.09283","title":"Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2202.04052","title":"Decision boundaries and convex hulls in the feature space that deep learning functions learn from images","created":"2022-02-05","cited_by_count":5,"area":null},{"id":"2210.05546","title":"What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2311.00858","title":"SmoothHess: ReLU Network Feature Interactions via Stein's Lemma","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2104.00219","title":"Fast Jacobian-Vector Product for Deep Networks","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2203.04886","title":"Reverse Engineering $\\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees","created":"2022-03-09","cited_by_count":4,"area":null},{"id":"2110.09374","title":"Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2406.01755","title":"Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2604.11962","title":"The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2103.07020","title":"Max-Linear Regression by Convex Programming","created":"2021-03-12","cited_by_count":2,"area":null},{"id":"2111.12963","title":"Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2112.13542","title":"Sparsest Univariate Learning Models Under Lipschitz Constraint","created":"2021-12-27","cited_by_count":2,"area":null},{"id":"2201.05279","title":"Manifoldron: Direct Space Partition via Manifold Discovery","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2412.07980","title":"TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2203.10447","title":"Over-parameterization: A Necessary Condition for Models that Extrapolate","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2307.00721","title":"Neural Polytopes","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2406.09657","title":"Mitigating over-exploration in latent space optimization using LES","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2509.15441","title":"Computing Linear Regions in Neural Networks with Skip Connections","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2511.12757","title":"Which Way from B to A: The role of embedding geometry in image interpolation for Stable Diffusion","created":"2025-11-16","cited_by_count":1,"area":"diffusion"},{"id":"2601.11575","title":"Concept Attractors in LLMs and their Applications","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2606.07728","title":"Characterizing the Discrete Geometry of ReLU Networks","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2101.06940","title":"Learning DNN networks using un-rectifying ReLU with compressed sensing application","created":"2021-01-18","cited_by_count":0,"area":null},{"id":"2110.14055","title":"Polynomial-Spline Neural Networks with Exact Integrals","created":"2021-10-26","cited_by_count":0,"area":null},{"id":"2210.12054","title":"Towards Global Neural Network Abstractions with Locally-Exact Reconstruction","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2302.09949","title":"SpecXAI -- Spectral interpretability of Deep Learning Models","created":"2023-02-20","cited_by_count":0,"area":null},{"id":"2304.12586","title":"Unsupervised Discovery of Extreme Weather Events Using Universal Representations of Emergent Organization","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2307.09602","title":"A max-affine spline approximation of neural networks using the Legendre transform of a convex-concave representation","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2407.08214","title":"Towards stable training of parallel continual learning","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2408.04809","title":"On the Geometry of Deep Learning","created":"2024-08-09","cited_by_count":0,"area":null},{"id":"2501.01564","title":"Semialgebraic Neural Networks: From roots to representations","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2502.17622","title":"A Priori Generalizability Estimate for a CNN","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2510.24466","title":"Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2601.05586","title":"Poisson Hyperplane Processes with Rectified Linear Units","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2602.05635","title":"Structural Disentanglement in Bilinear MLPs via Architectural Inductive Bias","created":"2026-02-05","cited_by_count":0,"area":"safety"},{"id":"2602.14495","title":"Divine Benevolence is an $x^2$: GLUs scale asymptotically faster than MLPs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.08464","title":"The Geometric Structure of Models Learning Sparse Data","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2609.34166","title":"Hidden Activations are not Enough I: Knowledge Matrices as Higher Representations","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}