{"total":84,"rows":[{"id":"2201.12872","title":"Discovering Invariant Rationales for Graph Neural Networks","created":"2022-01-30","cited_by_count":188,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93,"area":null},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"area":null},{"id":"2310.07931","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","created":"2023-10-11","cited_by_count":69,"area":null},{"id":"2108.07567","title":"How Powerful is Graph Convolution for Recommendation?","created":"2021-08-17","cited_by_count":50,"area":null},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50,"area":"lr"},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50,"area":null},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48,"area":"mllm"},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2210.00965","title":"Green Learning: Introduction, Examples and Outlook","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24,"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":"2111.06636","title":"Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction","created":"2021-11-12","cited_by_count":17,"area":null},{"id":"2202.05411","title":"Incremental Learning of Structured Memory via Closed-Loop Transcription","created":"2022-02-11","cited_by_count":17,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2112.07096","title":"Learning High-Dimensional Parametric Maps via Reduced Basis Adaptive Residual Networks","created":"2021-12-14","cited_by_count":16,"area":null},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15,"area":null},{"id":"2408.13442","title":"A Law of Next-Token Prediction in Large Language Models","created":"2024-08-24","cited_by_count":15,"area":null},{"id":"2506.01701","title":"Data Pruning by Information Maximization","created":"2025-06-02","cited_by_count":15,"area":null},{"id":"2303.02165","title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","created":"2023-03-05","cited_by_count":14,"area":null},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2305.01777","title":"Representation Learning via Manifold Flattening and Reconstruction","created":"2023-05-02","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":"2307.08924","title":"Towards Task Sampler Learning for Meta-Learning","created":"2023-07-18","cited_by_count":11,"area":null},{"id":"2410.01296","title":"Speculative Coreset Selection for Task-Specific Fine-tuning","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2402.05970","title":"Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts","created":"2024-02-06","cited_by_count":9,"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":"2210.16782","title":"Unsupervised Learning of Structured Representations via Closed-Loop Transcription","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2307.04047","title":"Threshold-Consistent Margin Loss for Open-World Deep Metric Learning","created":"2023-07-08","cited_by_count":7,"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":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2205.05787","title":"Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models","created":"2022-05-11","cited_by_count":5,"area":null},{"id":"2208.12212","title":"Sustaining Fairness via Incremental Learning","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2209.07496","title":"Unsupervised Opinion Summarization Using Approximate Geodesics","created":"2022-09-15","cited_by_count":5,"area":null},{"id":"2211.16710","title":"Extracting Semantic Knowledge from GANs with Unsupervised Learning","created":"2022-11-30","cited_by_count":5,"area":null},{"id":"2303.02693","title":"Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition","created":"2023-03-05","cited_by_count":5,"area":null},{"id":"2302.02302","title":"Achieving Robust Generalization for Wireless Channel Estimation Neural Networks by Designed Training Data","created":"2023-02-05","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":"2112.09741","title":"Envisioning Future Deep Learning Theories: Some Basic Concepts and Characteristics","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2210.05151","title":"UGformer for Robust Left Atrium and Scar Segmentation Across Scanners","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2403.07921","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2404.05241","title":"LightFF: Lightweight Inference for Forward-Forward Algorithm","created":"2024-04-08","cited_by_count":3,"area":null},{"id":"2408.11372","title":"Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2411.03033","title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2507.20853","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","created":"2025-07-28","cited_by_count":3,"area":"deeprl"},{"id":"2511.00907","title":"Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2211.00460","title":"Augmentation Invariant Manifold Learning","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2407.09524","title":"Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2407.19353","title":"Spring-block theory of feature learning in deep neural networks","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2502.05242","title":"Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2509.16875","title":"Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2407.00362","title":"JSCDS: A Core Data Selection Method with Jason-Shannon Divergence for Caries RGB Images-Efficient Learning","created":"2024-06-29","cited_by_count":1,"area":null},{"id":"2410.09749","title":"EMWaveNet: Physically Explainable Neural Network Based on Electromagnetic Propagation for SAR Target Recognition","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2410.16443","title":"Improving Neuron-level Interpretability with White-box Language Models","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2411.06785","title":"White-Box Diffusion Transformer for single-cell RNA-seq generation","created":"2024-11-11","cited_by_count":1,"area":"diffusion"},{"id":"2411.17961","title":"ESS-ReduNet: Enhancing Subspace Separability of ReduNet via Dynamic Expansion with Bayesian Inference","created":"2024-11-27","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":"2503.13935","title":"SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2507.21799","title":"Towards White-Box Deep Wireless Sensing","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2605.24113","title":"Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2105.13905","title":"Learning Structures for Deep Neural Networks","created":"2021-05-27","cited_by_count":0,"area":null},{"id":"2112.10390","title":"Evaluation and Comparison of Deep Learning Methods for Pavement Crack Identification with Visual Images","created":"2021-12-20","cited_by_count":0,"area":null},{"id":"2211.10418","title":"Sample-efficient Quantum Born Machine through Coding Rate Reduction","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2302.10383","title":"On Interpretable Approaches to Cluster, Classify and Represent Multi-Subspace Data via Minimum Lossy Coding Length based on Rate-Distortion Theory","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2305.11387","title":"Justices for Information Bottleneck Theory","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2410.00132","title":"CVVLSNet: Vehicle Location and Speed Estimation Using Partial Connected Vehicle Trajectory Data","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2410.00772","title":"On the Generalization and Causal Explanation in Self-Supervised Learning","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2410.07499","title":"Dense Optimizer : An Information Entropy-Guided Structural Search Method for Dense-like Neural Network Design","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2508.20427","title":"Rethinking Purity and Diversity in Multi-Behavior Sequential Recommendation from the Frequency Perspective","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.20284","title":"Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2510.20428","title":"An Empirical Study of Sample Selection Strategies for Large Language Model Repair","created":"2025-10-23","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":"2511.06443","title":"How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2601.15540","title":"PRISM: Deriving a White-Box Transformer as a Signal-Noise Decomposition Operator via Maximum Coding Rate Reduction","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2601.17042","title":"Interpretable and Sparse Linear Attention with Decoupled Membership-Subspace Modeling via MCR2 Objective","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.04062","title":"FedCova: Robust Federated Covariance Learning Against Noisy Labels","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.25132","title":"Robust Principal Component Completion","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.22676","title":"Operational Feature Fingerprints of Graph Datasets via a White-Box Signal-Subspace Probe","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.01897","title":"How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse","created":"2026-05-03","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},{"id":"2609.29913","title":"MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression","created":"2026-09-24","cited_by_count":0,"area":"inference"}],"next_cursor":null}