{"total":25,"rows":[{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2201.04828","title":"Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2310.19224","title":"CHAMMI: A benchmark for channel-adaptive models in microscopy imaging","created":"2023-10-30","cited_by_count":18,"area":null},{"id":"2205.09459","title":"Neural Network Architecture Beyond Width and Depth","created":"2022-05-19","cited_by_count":17,"area":null},{"id":"2311.05241","title":"When Meta-Learning Meets Online and Continual Learning: A Survey","created":"2023-11-09","cited_by_count":12,"area":null},{"id":"2405.16419","title":"Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers","created":"2024-05-26","cited_by_count":10,"area":null},{"id":"2103.16584","title":"Parameterized Hypercomplex Graph Neural Networks for Graph Classification","created":"2021-03-30","cited_by_count":7,"area":null},{"id":"2311.04251","title":"MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters","created":"2023-11-07","cited_by_count":7,"area":null},{"id":"2201.05739","title":"Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillance","created":"2022-01-15","cited_by_count":6,"area":null},{"id":"2301.12353","title":"On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network","created":"2023-01-29","cited_by_count":6,"area":null},{"id":"2503.19331","title":"ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2503.09826","title":"Isolated Channel Vision Transformers: From Single-Channel Pretraining to Multi-Channel Finetuning","created":"2025-03-12","cited_by_count":5,"area":null},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2506.07549","title":"Improving Memory Efficiency for Training KANs via Meta Learning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2411.16870","title":"RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks","created":"2024-11-25","cited_by_count":2,"area":null},{"id":"2505.18745","title":"C3R: Channel Conditioned Cell Representations for unified evaluation in microscopy imaging","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2510.19105","title":"MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2304.07613","title":"STen: Productive and Efficient Sparsity in PyTorch","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2312.01274","title":"Learning to Compose SuperWeights for Neural Parameter Allocation Search","created":"2023-12-03","cited_by_count":1,"area":null},{"id":"2403.19163","title":"D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2510.18431","title":"ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.27383","title":"Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2609.01550","title":"Linear Reusable Neural Bases Architecture for Network Compression","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}