{"total":88,"rows":[{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199,"area":null},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"area":null},{"id":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90,"area":null},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2305.16742","title":"Parameter-Efficient Fine-Tuning without Introducing New Latency","created":"2023-05-26","cited_by_count":59,"area":null},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54,"area":null},{"id":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47,"area":null},{"id":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"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":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2110.11395","title":"SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning","created":"2021-10-19","cited_by_count":30,"area":null},{"id":"2106.06091","title":"DECORE: Deep Compression with Reinforcement Learning","created":"2021-06-11","cited_by_count":29,"area":null},{"id":"2105.08667","title":"Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency","created":"2021-05-18","cited_by_count":22,"area":null},{"id":"2110.10423","title":"ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22,"area":null},{"id":"2307.01998","title":"Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities","created":"2023-07-05","cited_by_count":21,"area":null},{"id":"2311.03748","title":"Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning","created":"2023-11-07","cited_by_count":21,"area":null},{"id":"2110.08616","title":"GradSign: Model Performance Inference with Theoretical Insights","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2211.01642","title":"Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2307.09988","title":"TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge","created":"2023-07-19","cited_by_count":18,"area":null},{"id":"2110.08350","title":"Differentiable Network Pruning for Microcontrollers","created":"2021-10-15","cited_by_count":16,"area":null},{"id":"2301.05219","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","created":"2023-01-12","cited_by_count":16,"area":null},{"id":"2202.02664","title":"No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models","created":"2022-02-06","cited_by_count":15,"area":null},{"id":"2305.06559","title":"Patch-wise Mixed-Precision Quantization of Vision Transformer","created":"2023-05-11","cited_by_count":15,"area":null},{"id":"2203.02094","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","created":"2022-03-04","cited_by_count":14,"area":null},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14,"area":null},{"id":"2312.09059","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","created":"2023-12-14","cited_by_count":13,"area":null},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2106.06799","title":"Zero-Cost Operation Scoring in Differentiable Architecture Search","created":"2021-06-12","cited_by_count":9,"area":null},{"id":"2102.06599","title":"Neural Architecture Search as Program Transformation Exploration","created":"2021-02-12","cited_by_count":8,"area":null},{"id":"2403.10650","title":"PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation","created":"2024-03-15","cited_by_count":8,"area":null},{"id":"2205.10121","title":"Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2412.00143","title":"Is Oracle Pruning the True Oracle?","created":"2024-11-28","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":"2406.01414","title":"CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2505.07300","title":"L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2104.05421","title":"NullaNet Tiny: Ultra-low-latency DNN Inference Through Fixed-function Combinational Logic","created":"2021-04-07","cited_by_count":4,"area":null},{"id":"2201.05020","title":"Automatic Sparse Connectivity Learning for Neural Networks","created":"2022-01-13","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":"2304.13718","title":"Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2306.17504","title":"Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2404.10824","title":"Decoupled Weight Decay for Any $p$ Norm","created":"2024-04-16","cited_by_count":4,"area":null},{"id":"2412.02328","title":"Efficient Model Compression Techniques with FishLeg","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2201.10520","title":"Adaptive Activation-based Structured Pruning","created":"2022-01-21","cited_by_count":3,"area":null},{"id":"2302.00932","title":"Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS \"Cold-Start\"","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2407.16269","title":"HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis","created":"2024-07-23","cited_by_count":3,"area":null},{"id":"2508.05521","title":"Optimal Brain Connection: Towards Efficient Structural Pruning","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2508.13836","title":"One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2105.05916","title":"Dynamical Isometry: The Missing Ingredient for Neural Network Pruning","created":"2021-05-12","cited_by_count":2,"area":null},{"id":"2110.08764","title":"S-Cyc: A Learning Rate Schedule for Iterative Pruning of ReLU-based Networks","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2201.09881","title":"Iterative Activation-based Structured Pruning","created":"2022-01-22","cited_by_count":2,"area":null},{"id":"2303.15479","title":"Exploring the Performance of Pruning Methods in Neural Networks: An Empirical Study of the Lottery Ticket Hypothesis","created":"2023-03-26","cited_by_count":2,"area":null},{"id":"2310.04649","title":"Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2312.02820","title":"Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2403.10318","title":"pTNAS: Progressive Neural Architecture Search for Tabular Data","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2407.15875","title":"Shapley Pruning for Neural Network Compression","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2409.10673","title":"A Bayesian Interpretation of Adaptive Low-Rank Adaptation","created":"2024-09-16","cited_by_count":2,"area":null},{"id":"2411.06236","title":"Zero-Shot NAS via the Suppression of Local Entropy Decrease","created":"2024-11-09","cited_by_count":2,"area":null},{"id":"2503.11164","title":"Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2607.17568","title":"CoCurve: Cross-Module Co-Pruning Curvature for Structured LLM Pruning","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2106.11655","title":"DARTS-PRIME: Regularization and Scheduling Improve Constrained Optimization in Differentiable NAS","created":"2021-06-22","cited_by_count":1,"area":null},{"id":"2210.09459","title":"Extensible Proxy for Efficient NAS","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2311.03609","title":"Testing RadiX-Nets: Advances in Viable Sparse Topologies","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2405.01306","title":"Graph is all you need? Lightweight data-agnostic neural architecture search without training","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2502.11450","title":"What Scalable Second-Order Information Knows for Pruning at Initialization","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2507.08841","title":"Zero-Shot Neural Architecture Search with Weighted Response Correlation","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2510.01472","title":"LLM-NAS: LLM-driven Hardware-Aware Neural Architecture Search","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2511.11641","title":"EcoSpa: Efficient Transformer Training with Coupled Sparsity","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2602.03918","title":"Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2212.06144","title":"Optimizing Learning Rate Schedules for Iterative Pruning of Deep Neural Networks","created":"2022-12-09","cited_by_count":0,"area":null},{"id":"2212.06145","title":"AP: Selective Activation for De-sparsifying Pruned Neural Networks","created":"2022-12-09","cited_by_count":0,"area":null},{"id":"2404.02947","title":"DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2405.17506","title":"Subspace Node Pruning","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2411.19819","title":"GradAlign for Training-free Model Performance Inference","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2508.04100","title":"SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2512.06440","title":"Neural expressiveness for beyond importance model compression","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2512.11089","title":"TPV: Parameter Perturbations Through the Lens of Test Prediction Variance","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2604.05856","title":"Neural Network Pruning via QUBO Optimization","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2606.00442","title":"Exploiting weight-space symmetries for approximating curvature","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2608.00481","title":"F-WANDA: Fisher-Reweighted Post-Training Pruning for Sustainable Deployment of Large Language Models","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.16129","title":"Optimal Pruning for Neural Architectures using Fisher Information Distances","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}