{"total":59,"rows":[{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110,"area":null},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85,"area":null},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79,"area":null},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2411.12469","title":"AI Flow at the Network Edge","created":"2024-11-19","cited_by_count":46,"area":null},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30,"area":null},{"id":"2109.14509","title":"PAC-Bayes Information Bottleneck","created":"2021-09-29","cited_by_count":28,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2208.04425","title":"Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints","created":"2022-08-08","cited_by_count":25,"area":null},{"id":"2310.02998","title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","created":"2023-10-04","cited_by_count":19,"area":"mllm"},{"id":"2108.08532","title":"An Information Theory-inspired Strategy for Automatic Network Pruning","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2103.13283","title":"Information-based Disentangled Representation Learning for Unsupervised MR Harmonization","created":"2021-03-24","cited_by_count":16,"area":null},{"id":"2103.12300","title":"Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2209.11204","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","created":"2022-09-22","cited_by_count":11,"area":null},{"id":"2405.19816","title":"Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2508.03058","title":"VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training","created":"2025-08-05","cited_by_count":9,"area":"lr"},{"id":"2302.14670","title":"Balanced Training for Sparse GANs","created":"2023-02-28","cited_by_count":8,"area":null},{"id":"2202.10716","title":"HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2202.01290","title":"Cyclical Pruning for Sparse Neural Networks","created":"2022-02-02","cited_by_count":6,"area":null},{"id":"2308.15368","title":"RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics","created":"2023-08-29","cited_by_count":6,"area":null},{"id":"2110.14283","title":"How Important is Importance Sampling for Deep Budgeted Training?","created":"2021-10-27","cited_by_count":5,"area":null},{"id":"2203.05724","title":"Information-Theoretic Odometry Learning","created":"2022-03-11","cited_by_count":5,"area":null},{"id":"2407.09072","title":"New Desiderata for Direct Preference Optimization","created":"2024-07-12","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2111.09635","title":"Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2201.03624","title":"Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations","created":"2022-01-10","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2308.09104","title":"Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks","created":"2023-08-17","cited_by_count":4,"area":null},{"id":"2110.06057","title":"Gated Information Bottleneck for Generalization in Sequential Environments","created":"2021-10-12","cited_by_count":3,"area":null},{"id":"2207.11048","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2307.11962","title":"MIMONet: Multi-Input Multi-Output On-Device Deep Learning","created":"2023-07-22","cited_by_count":3,"area":null},{"id":"2312.00840","title":"Towards Redundancy-Free Sub-networks in Continual Learning","created":"2023-12-01","cited_by_count":3,"area":null},{"id":"2405.07748","title":"Neural Network Compression for Reinforcement Learning Tasks","created":"2024-05-13","cited_by_count":3,"area":"deeprl"},{"id":"2406.05276","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2506.15617","title":"The Compositional Architecture of Regret in Large Language Models","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2207.01394","title":"BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2305.12458","title":"Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2311.13349","title":"REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints","created":"2023-11-22","cited_by_count":2,"area":null},{"id":"2411.13548","title":"MGHF: Multi-Granular High-Frequency Perceptual Loss for Image Super-Resolution","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2208.00651","title":"De-biased Representation Learning for Fairness with Unreliable Labels","created":"2022-08-01","cited_by_count":1,"area":null},{"id":"2303.02846","title":"Contrastive variational information bottleneck for aspect-based sentiment analysis","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2402.10473","title":"Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacy","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2502.09125","title":"Enhanced Structured Lasso Pruning with Class-wise Information","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2507.12110","title":"Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVs","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2602.14481","title":"On the Rate-Distortion-Complexity Tradeoff for Semantic Communication","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2101.05650","title":"Rescaling CNN through Learnable Repetition of Network Parameters","created":"2021-01-14","cited_by_count":0,"area":null},{"id":"2103.10629","title":"Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2104.14379","title":"Learning Robust Variational Information Bottleneck with Reference","created":"2021-04-29","cited_by_count":0,"area":null},{"id":"2112.15111","title":"Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers","created":"2021-12-30","cited_by_count":0,"area":null},{"id":"2212.09415","title":"Training Lightweight Graph Convolutional Networks with Phase-field Models","created":"2022-12-19","cited_by_count":0,"area":null},{"id":"2307.07389","title":"Learning Sparse Neural Networks with Identity Layers","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2505.08961","title":"Learning Informative Attention Weights for Person Re-Identification","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2508.13875","title":"A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2603.23390","title":"Harnessing Lightweight Transformer with Contextual Synergic Enhancement for Efficient 3D Medical Image Segmentation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2607.23181","title":"Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation","created":"2026-07-25","cited_by_count":0,"area":"wm"}],"next_cursor":null}