{"total":282,"rows":[{"id":"2104.08894","title":"The Intrinsic Dimension of Images and Its Impact on Learning","created":"2021-04-18","cited_by_count":315,"area":null},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2205.13218","title":"A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning","created":"2022-05-26","cited_by_count":154,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2302.00294","title":"The geometry of hidden representations of large transformer models","created":"2023-02-01","cited_by_count":112,"area":null},{"id":"2306.04723","title":"Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts","created":"2023-06-07","cited_by_count":112,"area":null},{"id":"2302.14367","title":"BrainBERT: Self-supervised representation learning for intracranial recordings","created":"2023-02-28","cited_by_count":72,"area":null},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71,"area":null},{"id":"2111.13171","title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","created":"2021-11-25","cited_by_count":70,"area":null},{"id":"2207.02862","title":"Verifying the Union of Manifolds Hypothesis for Image Data","created":"2022-07-06","cited_by_count":64,"area":null},{"id":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"area":null},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56,"area":null},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52,"area":"mechinterp"},{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51,"area":"mechinterp"},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50,"area":null},{"id":"2402.18048","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","created":"2024-02-28","cited_by_count":45,"area":null},{"id":"2307.02347","title":"Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality","created":"2023-07-05","cited_by_count":44,"area":"diffusion"},{"id":"2406.03537","title":"A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models","created":"2024-06-05","cited_by_count":42,"area":"diffusion"},{"id":"2205.02956","title":"Low Dimensional Invariant Embeddings for Universal Geometric Learning","created":"2022-05-05","cited_by_count":38,"area":null},{"id":"2107.08562","title":"Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering","created":"2021-07-19","cited_by_count":37,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2507.11783","title":"EEG Foundation Models: A Critical Review of Current Progress and Future Directions","created":"2025-07-15","cited_by_count":32,"area":null},{"id":"2206.14882","title":"LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood","created":"2022-06-29","cited_by_count":30,"area":null},{"id":"2310.04400","title":"On the Embedding Collapse when Scaling up Recommendation Models","created":"2023-10-06","cited_by_count":29,"area":null},{"id":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2206.12314","title":"Learning sparse features can lead to overfitting in neural networks","created":"2022-06-24","cited_by_count":23,"area":null},{"id":"2405.12250","title":"Your Transformer is Secretly Linear","created":"2024-05-19","cited_by_count":23,"area":null},{"id":"2205.03373","title":"DADApy: Distance-based Analysis of DAta-manifolds in Python","created":"2022-05-04","cited_by_count":22,"area":null},{"id":"2307.08283","title":"Complexity Matters: Rethinking the Latent Space for Generative Modeling","created":"2023-07-17","cited_by_count":19,"area":"diffusion"},{"id":"2408.10548","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","created":"2024-08-20","cited_by_count":19,"area":null},{"id":"2509.26314","title":"Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts","created":"2025-09-30","cited_by_count":19,"area":"lr"},{"id":"2308.02346","title":"Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning","created":"2023-08-04","cited_by_count":18,"area":null},{"id":"2502.08009","title":"The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2205.06926","title":"Toward a Geometrical Understanding of Self-supervised Contrastive Learning","created":"2022-05-13","cited_by_count":17,"area":null},{"id":"2501.10573","title":"The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models","created":"2025-01-17","cited_by_count":17,"area":"mechinterp"},{"id":"2507.09709","title":"Large Language Models Encode Semantics and Alignment in Linearly Separable Representations","created":"2025-07-13","cited_by_count":17,"area":"safety"},{"id":"2410.01444","title":"Geometric Signatures of Compositionality Across a Language Model's Lifetime","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2310.17715","title":"Outlier Dimensions Encode Task-Specific Knowledge","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2409.03662","title":"The representation landscape of few-shot learning and fine-tuning in large language models","created":"2024-09-05","cited_by_count":15,"area":null},{"id":"2309.12821","title":"A Spectral Theory of Neural Prediction and Alignment","created":"2023-09-22","cited_by_count":14,"area":null},{"id":"2504.05461","title":"Intermediate Layer Classifiers for OOD generalization","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14,"area":null},{"id":"2103.05524","title":"On the interplay between data structure and loss function in classification problems","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2401.08865","title":"The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images","created":"2024-01-16","cited_by_count":13,"area":null},{"id":"2406.01909","title":"A Global Geometric Analysis of Maximal Coding Rate Reduction","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2105.02468","title":"Relative stability toward diffeomorphisms indicates performance in deep nets","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2111.06979","title":"Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception","created":"2021-11-12","cited_by_count":12,"area":null},{"id":"2204.08624","title":"Topology and geometry of data manifold in deep learning","created":"2022-04-19","cited_by_count":12,"area":null},{"id":"2305.19358","title":"Stable Anisotropic Regularization","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2410.11042","title":"Persistent Topological Features in Large Language Models","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2107.12972","title":"Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation","created":"2021-07-27","cited_by_count":11,"area":null},{"id":"2209.10438","title":"A Measure of the Complexity of Neural Representations based on Partial Information Decomposition","created":"2022-09-21","cited_by_count":11,"area":null},{"id":"2305.18353","title":"Emergent representations in networks trained with the Forward-Forward algorithm","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2305.19730","title":"Data Representations' Study of Latent Image Manifolds","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2401.10474","title":"LDReg: Local Dimensionality Regularized Self-Supervised Learning","created":"2024-01-19","cited_by_count":11,"area":null},{"id":"2506.01435","title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2207.02797","title":"The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning","created":"2022-07-06","cited_by_count":10,"area":null},{"id":"2302.02060","title":"Representation Deficiency in Masked Language Modeling","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2505.15239","title":"Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers","created":"2025-05-21","cited_by_count":10,"area":null},{"id":"2511.02101","title":"Measuring the Intrinsic Dimension of Earth Representations","created":"2025-11-03","cited_by_count":10,"area":null},{"id":"2104.13289","title":"Model-centric Data Manifold: the Data Through the Eyes of the Model","created":"2021-04-26","cited_by_count":9,"area":null},{"id":"2106.03485","title":"Redundant representations help generalization in wide neural networks","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2211.13239","title":"Relating Regularization and Generalization through the Intrinsic Dimension of Activations","created":"2022-11-23","cited_by_count":9,"area":null},{"id":"2211.14961","title":"Linear Classification of Neural Manifolds with Correlated Variability","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2303.09767","title":"It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness","created":"2023-03-17","cited_by_count":9,"area":null},{"id":"2304.02834","title":"Probing the Purview of Neural Networks via Gradient Analysis","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2408.04965","title":"Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2503.18114","title":"Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry","created":"2025-03-23","cited_by_count":9,"area":null},{"id":"2505.05892","title":"Register and [CLS] tokens yield a decoupling of local and global features in large ViTs","created":"2025-05-09","cited_by_count":9,"area":null},{"id":"2511.20315","title":"Geometry of Decision Making in Language Models","created":"2025-11-25","cited_by_count":9,"area":null},{"id":"2101.06898","title":"What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space","created":"2021-01-18","cited_by_count":8,"area":"safety"},{"id":"2107.11774","title":"SGD with a Constant Large Learning Rate Can Converge to Local Maxima","created":"2021-07-25","cited_by_count":8,"area":null},{"id":"2412.09250","title":"GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning","created":"2024-12-12","cited_by_count":8,"area":null},{"id":"2505.09022","title":"Block-Biased Mamba for Long-Range Sequence Processing","created":"2025-05-13","cited_by_count":8,"area":"ssm"},{"id":"2509.17738","title":"Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking","created":"2025-09-22","cited_by_count":8,"area":null},{"id":"2106.11486","title":"Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification","created":"2021-06-22","cited_by_count":7,"area":null},{"id":"2302.09301","title":"Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension","created":"2023-02-16","cited_by_count":7,"area":"diffusion"},{"id":"2410.07687","title":"Learning to Compress: Local Rank and Information Compression in Deep Neural Networks","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2512.13568","title":"Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability","created":"2025-12-15","cited_by_count":7,"area":"mechinterp"},{"id":"2105.01867","title":"A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2303.05161","title":"Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2404.13859","title":"Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2411.00246","title":"ResiDual Transformer Alignment with Spectral Decomposition","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2601.13308","title":"Scaling laws for amplitude surrogates","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2605.08142","title":"Reasoning emerges from constrained inference manifolds in large language models","created":"2026-05-02","cited_by_count":6,"area":"lr"},{"id":"2202.00339","title":"Quantifying Relevance in Learning and Inference","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2209.12806","title":"FONDUE: an algorithm to find the optimal dimensionality of the latent representations of variational autoencoders","created":"2022-09-26","cited_by_count":5,"area":null},{"id":"2210.01506","title":"How deep convolutional neural networks lose spatial information with training","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2211.12759","title":"NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2304.11925","title":"Data-driven modelling of brain activity using neural networks, Diffusion Maps, and the Koopman operator","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2306.03406","title":"Deep neural networks architectures from the perspective of manifold learning","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2410.13792","title":"Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2501.19067","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2502.15051","title":"Approximating Latent Manifolds in Neural Networks via Vanishing Ideals","created":"2025-02-20","cited_by_count":5,"area":null},{"id":"2503.02142","title":"Measuring Intrinsic Dimension of Token Embeddings","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2603.22301","title":"Latent Semantic Manifolds in Large Language Models","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2111.11514","title":"On Data-centric Myths","created":"2021-11-22","cited_by_count":4,"area":null}],"next_cursor":"100"}