{"total":19,"rows":[{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2110.08271","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2303.13635","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","created":"2023-03-22","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":"2310.09382","title":"LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representations","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2305.07135","title":"Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systems","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2201.00063","title":"Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems","created":"2021-12-31","cited_by_count":1,"area":null},{"id":"2204.00783","title":"Supervised Robustness-preserving Data-free Neural Network Pruning","created":"2022-04-02","cited_by_count":1,"area":null},{"id":"2501.09849","title":"Coded Deep Learning: Framework and Algorithm","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2108.12704","title":"Compact representations of convolutional neural networks via weight pruning and quantization","created":"2021-08-28","cited_by_count":0,"area":null},{"id":"2210.05111","title":"Deep learning model compression using network sensitivity and gradients","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2401.00014","title":"Resource-Limited Automated Ki67 Index Estimation in Breast Cancer","created":"2023-12-22","cited_by_count":0,"area":null},{"id":"2501.03095","title":"A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2505.18758","title":"Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2605.24754","title":"Motion-Compensated Weight Compression","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2610.16020","title":"When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}