{"total":244,"rows":[{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199,"area":null},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"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":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2102.01063","title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","created":"2021-02-01","cited_by_count":73,"area":null},{"id":"2310.15080","title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","created":"2023-10-23","cited_by_count":65,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2301.11300","title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2201.03299","title":"Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks","created":"2022-01-10","cited_by_count":55,"area":null},{"id":"2201.10355","title":"Neural Architecture Search for Spiking Neural Networks","created":"2022-01-23","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2210.03230","title":"NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies","created":"2022-10-06","cited_by_count":36,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34,"area":null},{"id":"2101.11834","title":"Neural Architecture Search with Random Labels","created":"2021-01-28","cited_by_count":33,"area":null},{"id":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33,"area":null},{"id":"2110.05668","title":"NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks","created":"2021-10-12","cited_by_count":32,"area":null},{"id":"2302.12828","title":"SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries","created":"2023-02-24","cited_by_count":31,"area":null},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2109.00817","title":"NASI: Label- and Data-agnostic Neural Architecture Search at Initialization","created":"2021-09-02","cited_by_count":28,"area":null},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2403.19232","title":"AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search","created":"2024-03-28","cited_by_count":28,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2111.05850","title":"Towards Green Automated Machine Learning: Status Quo and Future Directions","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2410.14720","title":"SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2102.08099","title":"EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search","created":"2021-02-16","cited_by_count":24,"area":null},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"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":"2203.09137","title":"Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning","created":"2022-03-17","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":"2405.03547","title":"Position: Leverage Foundational Models for Black-Box Optimization","created":"2024-05-06","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":"2201.05120","title":"SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps","created":"2022-01-13","cited_by_count":19,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2202.08539","title":"When, where, and how to add new neurons to ANNs","created":"2022-02-17","cited_by_count":18,"area":null},{"id":"2203.14577","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","created":"2022-03-28","cited_by_count":18,"area":null},{"id":"2201.09785","title":"Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2402.15490","title":"A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends","created":"2024-02-23","cited_by_count":16,"area":null},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2209.07413","title":"EZNAS: Evolving Zero Cost Proxies For Neural Architecture Scoring","created":"2022-09-15","cited_by_count":15,"area":null},{"id":"2108.01899","title":"Generic Neural Architecture Search via Regression","created":"2021-08-04","cited_by_count":14,"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":"2209.07238","title":"Generalization Properties of NAS under Activation and Skip Connection Search","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"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":"2406.16635","title":"ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models","created":"2024-06-24","cited_by_count":13,"area":null},{"id":"2111.15362","title":"ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior","created":"2021-11-27","cited_by_count":12,"area":null},{"id":"2202.07242","title":"Neural Architecture Search for Dense Prediction Tasks in Computer Vision","created":"2022-02-15","cited_by_count":12,"area":null},{"id":"2206.13329","title":"Prior-Guided One-shot Neural Architecture Search","created":"2022-06-27","cited_by_count":12,"area":null},{"id":"2402.11322","title":"SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems","created":"2024-02-17","cited_by_count":12,"area":null},{"id":"2112.03159","title":"UniLog: Deploy One Model and Specialize it for All Log Analysis Tasks","created":"2021-12-06","cited_by_count":11,"area":null},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2403.04161","title":"SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2404.16551","title":"Surprisingly Strong Performance Prediction with Neural Graph Features","created":"2024-04-25","cited_by_count":11,"area":null},{"id":"2509.26476","title":"Regression Language Models for Code","created":"2025-09-30","cited_by_count":11,"area":null},{"id":"2207.05135","title":"FreeREA: Training-Free Evolution-based Architecture Search","created":"2022-06-17","cited_by_count":10,"area":null},{"id":"2512.24120","title":"Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design","created":"2025-12-30","cited_by_count":10,"area":null},{"id":"2601.02997","title":"From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures","created":"2026-01-06","cited_by_count":10,"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":"2108.08019","title":"RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving","created":"2021-08-18","cited_by_count":9,"area":null},{"id":"2211.01842","title":"Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2306.00288","title":"Training-free Neural Architecture Search for RNNs and Transformers","created":"2023-06-01","cited_by_count":9,"area":null},{"id":"2403.02484","title":"Encodings for Prediction-based Neural Architecture Search","created":"2024-03-04","cited_by_count":9,"area":null},{"id":"2405.03727","title":"Large Language Models Synergize with Automated Machine Learning","created":"2024-05-06","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":"2409.18893","title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2102.11382","title":"Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity","created":"2021-02-22","cited_by_count":7,"area":null},{"id":"2108.11105","title":"Lightweight Monocular Depth with a Novel Neural Architecture Search Method","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2108.11939","title":"Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2108.12502","title":"StressNAS: Affect State and Stress Detection Using Neural Architecture Search","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2301.09850","title":"RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies","created":"2023-01-24","cited_by_count":7,"area":null},{"id":"2410.04808","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2603.12091","title":"Resource-Efficient Iterative LLM-Based NAS with Feedback Memory","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2211.01454","title":"Speeding up NAS with Adaptive Subset Selection","created":"2022-11-02","cited_by_count":6,"area":null},{"id":"2303.17646","title":"XPert: Peripheral Circuit & Neural Architecture Co-search for Area and Energy-efficient Xbar-based Computing","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2306.02459","title":"Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search","created":"2023-06-04","cited_by_count":6,"area":null},{"id":"2306.05031","title":"Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations","created":"2023-06-08","cited_by_count":6,"area":null},{"id":"2307.00293","title":"AutoST: Training-free Neural Architecture Search for Spiking Transformers","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2312.09411","title":"OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2403.13134","title":"Robust NAS under adversarial training: benchmark, theory, and beyond","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2410.00131","title":"Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2111.13204","title":"BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule","created":"2021-11-25","cited_by_count":5,"area":null},{"id":"2301.05785","title":"Efficient Activation Function Optimization through Surrogate Modeling","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2303.02693","title":"Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition","created":"2023-03-05","cited_by_count":5,"area":null},{"id":"2304.05405","title":"Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search","created":"2023-04-11","cited_by_count":5,"area":null},{"id":"2306.04454","title":"Training-Free Neural Active Learning with Initialization-Robustness Guarantees","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2307.13901","title":"YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems","created":"2023-07-26","cited_by_count":5,"area":null},{"id":"2402.02105","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","created":"2024-02-03","cited_by_count":5,"area":null},{"id":"2403.05064","title":"Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision","created":"2024-03-08","cited_by_count":5,"area":null},{"id":"2404.02189","title":"Insights from the Use of Previously Unseen Neural Architecture Search Datasets","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2405.03924","title":"NeurDB: An AI-powered Autonomous Data System","created":"2024-05-07","cited_by_count":5,"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}],"next_cursor":"100"}