{"total":13,"rows":[{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25,"area":null},{"id":"2110.08190","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2404.08564","title":"Federated Distillation: A Survey","created":"2024-04-02","cited_by_count":15,"area":null},{"id":"2212.04129","title":"Deep Incubation: Training Large Models by Divide-and-Conquering","created":"2022-12-08","cited_by_count":13,"area":null},{"id":"2201.02620","title":"Compressing Models with Few Samples: Mimicking then Replacing","created":"2022-01-07","cited_by_count":8,"area":null},{"id":"2103.00430","title":"Training Generative Adversarial Networks in One Stage","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2210.09922","title":"Few-Shot Learning of Compact Models via Task-Specific Meta Distillation","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2506.08591","title":"Diversity-Guided MLP Reduction for Efficient Large Vision Transformers","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2303.00972","title":"Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2401.16760","title":"One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2510.05064","title":"Boomerang Distillation Enables Zero-Shot Model Size Interpolation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2303.01913","title":"Bespoke: A Block-Level Neural Network Optimization Framework for Low-Cost Deployment","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2406.09481","title":"ELF-UA: Efficient Label-Free User Adaptation in Gaze Estimation","created":"2024-06-13","cited_by_count":0,"area":null}],"next_cursor":null}