{"total":169,"rows":[{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2201.00058","title":"Representation Topology Divergence: A Method for Comparing Neural Network Representations","created":"2021-12-31","cited_by_count":66,"area":null},{"id":"2206.08720","title":"Fast Finite Width Neural Tangent Kernel","created":"2022-06-17","cited_by_count":62,"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":"2201.10355","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":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"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":"2204.11582","title":"Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection","created":"2022-04-25","cited_by_count":35,"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":"2110.08611","title":"Deep Active Learning by Leveraging Training Dynamics","created":"2021-10-16","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":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30,"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":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2208.13614","title":"Neural Tangent Kernel: A Survey","created":"2022-08-29","cited_by_count":23,"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":"2211.16126","title":"Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting","created":"2022-11-29","cited_by_count":22,"area":null},{"id":"2210.05577","title":"What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?","created":"2022-10-11","cited_by_count":21,"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":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2202.02842","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","created":"2022-02-06","cited_by_count":19,"area":null},{"id":"2203.08887","title":"On Redundancy and Diversity in Cell-based Neural Architecture Search","created":"2022-03-16","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":"2209.04121","title":"Fast Neural Kernel Embeddings for General Activations","created":"2022-09-09","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":"2207.11727","title":"Can we achieve robustness from data alone?","created":"2022-07-24","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":"2203.08734","title":"Learning Where To Look -- Generative NAS is Surprisingly Efficient","created":"2022-03-16","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":"2209.07238","title":"Generalization Properties of NAS under Activation and Skip Connection Search","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2303.01980","title":"Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2303.02165","title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","created":"2023-03-05","cited_by_count":14,"area":null},{"id":"2403.06020","title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","created":"2024-03-09","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":"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":"2206.13329","title":"Prior-Guided One-shot Neural Architecture Search","created":"2022-06-27","cited_by_count":12,"area":null},{"id":"2211.14810","title":"A Kernel Perspective of Skip Connections in Convolutional Networks","created":"2022-11-27","cited_by_count":12,"area":null},{"id":"2108.00568","title":"FLASH: Fast Neural Architecture Search with Hardware Optimization","created":"2021-08-01","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":"2207.05135","title":"FreeREA: Training-Free Evolution-based Architecture Search","created":"2022-06-17","cited_by_count":10,"area":null},{"id":"2306.03968","title":"Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels","created":"2023-06-06","cited_by_count":10,"area":null},{"id":"2506.06280","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","created":"2025-06-06","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":"2206.00228","title":"Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networks","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2406.11129","title":"Neural Lineage","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2111.01203","title":"One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search","created":"2021-11-01","cited_by_count":8,"area":null},{"id":"2209.14778","title":"Batch Normalization Explained","created":"2022-09-29","cited_by_count":8,"area":null},{"id":"2103.12827","title":"Fisher Task Distance and Its Application in Neural Architecture Search","created":"2021-03-23","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":"2110.06018","title":"On the Security Risks of AutoML","created":"2021-10-12","cited_by_count":7,"area":null},{"id":"2301.06393","title":"$\\beta$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search","created":"2023-01-16","cited_by_count":7,"area":null},{"id":"2311.00447","title":"On the Opportunities of Green Computing: A Survey","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2509.05657","title":"LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding","created":"2025-09-06","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":"2302.14772","title":"PA&DA: Jointly Sampling PAth and DAta for Consistent NAS","created":"2023-02-28","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":"2103.11833","title":"AutoSpace: Neural Architecture Search with Less Human Interference","created":"2021-03-22","cited_by_count":5,"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":"2209.01688","title":"On the Privacy Risks of Cell-Based NAS Architectures","created":"2022-09-04","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":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2305.14065","title":"Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2401.08996","title":"MicroNAS: Zero-Shot Neural Architecture Search for MCUs","created":"2024-01-17","cited_by_count":5,"area":null},{"id":"2401.11188","title":"Fast and Exact Enumeration of Deep Networks Partitions Regions","created":"2024-01-20","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":"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":"2410.00350","title":"Efficient Training of Large Vision Models via Advanced Automated Progressive Learning","created":"2024-09-06","cited_by_count":5,"area":"diffusion"},{"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":"2109.04983","title":"A Neural Tangent Kernel Perspective of Infinite Tree Ensembles","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2203.05508","title":"Towards Less Constrained Macro-Neural Architecture Search","created":"2022-03-10","cited_by_count":4,"area":null},{"id":"2205.05662","title":"Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2208.08835","title":"Differentiable Architecture Search with Random Features","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2210.07634","title":"Pareto-aware Neural Architecture Generation for Diverse Computational Budgets","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2308.15609","title":"InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2402.17440","title":"Principled Architecture-aware Scaling of Hyperparameters","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2403.07591","title":"Robustifying and Boosting Training-Free Neural Architecture Search","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2408.15034","title":"MONAS: Efficient Zero-Shot Neural Architecture Search for MCUs","created":"2024-08-26","cited_by_count":4,"area":null},{"id":"2503.22733","title":"RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2204.04918","title":"When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search","created":"2022-04-11","cited_by_count":3,"area":null}],"next_cursor":"100"}