{"total":44,"rows":[{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2312.03526","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","created":"2023-12-06","cited_by_count":109,"area":null},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"area":null},{"id":"2210.07277","title":"The Hidden Uniform Cluster Prior in Self-Supervised Learning","created":"2022-10-13","cited_by_count":58,"area":null},{"id":"2210.00965","title":"Green Learning: Introduction, Examples and Outlook","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2306.13924","title":"Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning","created":"2023-06-24","cited_by_count":25,"area":null},{"id":"2308.16271","title":"Emergence of Segmentation with Minimalistic White-Box Transformers","created":"2023-08-30","cited_by_count":24,"area":null},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","cited_by_count":20,"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":"2305.01777","title":"Representation Learning via Manifold Flattening and Reconstruction","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2404.02446","title":"Masked Completion via Structured Diffusion with White-Box Transformers","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2405.14736","title":"GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost","created":"2024-05-23","cited_by_count":9,"area":null},{"id":"2405.20024","title":"Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Survey","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2309.12078","title":"Clustering-based Domain-Incremental Learning","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2311.12894","title":"Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval","created":"2023-11-21","cited_by_count":8,"area":null},{"id":"2209.15261","title":"Minimalistic Unsupervised Learning with the Sparse Manifold Transform","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2306.11232","title":"Eight challenges in developing theory of intelligence","created":"2023-06-20","cited_by_count":6,"area":null},{"id":"2401.13558","title":"Task structure and nonlinearity jointly determine learned representational geometry","created":"2024-01-24","cited_by_count":6,"area":null},{"id":"2506.03790","title":"Attention-Only Transformers via Unrolled Subspace Denoising","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2301.04027","title":"Differentiable modeling to unify machine learning and physical models and advance Geosciences","created":"2023-01-10","cited_by_count":4,"area":null},{"id":"2302.09347","title":"Closed-Loop Transcription via Convolutional Sparse Coding","created":"2023-02-18","cited_by_count":4,"area":null},{"id":"2311.07618","title":"Large Language Models' Understanding of Math: Source Criticism and Extrapolation","created":"2023-11-12","cited_by_count":4,"area":null},{"id":"2412.16884","title":"Out-of-Distribution Detection with Prototypical Outlier Proxy","created":"2024-12-22","cited_by_count":4,"area":null},{"id":"2605.03517","title":"Understanding Self-Supervised Learning via Latent Distribution Matching","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2307.06950","title":"Pathway toward prior knowledge-integrated machine learning in engineering","created":"2023-07-10","cited_by_count":2,"area":null},{"id":"2505.20964","title":"Semantic Communication meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2310.03186","title":"Inferring Inference","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2407.11024","title":"A mathematical framework of intelligence and consciousness based on Riemannian Geometry","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2412.14668","title":"LoLaFL: Low-Latency Federated Learning via Forward-only Propagation","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2502.19816","title":"Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2503.07600","title":"A Representationalist, Functionalist and Naturalistic Conception of Intelligence as a Foundation for AGI","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2504.12675","title":"Physics Informed Constrained Learning of Dynamics from Static Data","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2605.05436","title":"Estimating Implicit Regularization in Deep Learning","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2209.02388","title":"Pathway to Future Symbiotic Creativity","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2209.02691","title":"Statistical Foundation Behind Machine Learning and Its Impact on Computer Vision","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2303.09075","title":"Enhancing Text Generation with Cooperative Training","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2407.14430","title":"The Extrapolation Power of Implicit Models","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2510.22196","title":"Scaling Non-Parametric Sampling with Representation","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2601.10282","title":"SPIKE: Sparse Koopman Regularization for Physics-Informed Neural Networks","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.25033","title":"Epistemic Compression: The Case for Deliberate Ignorance in High-Stakes AI","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.18237","title":"Semantic-based Distributed Learning for Diverse and Discriminative Representations","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2609.21001","title":"On the Limits of Maximal Coding Rate Reduction for Out-of-Distribution Generalisation","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}