{"total":202,"rows":[{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"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":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146,"area":"offlinerl"},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2306.06955","title":"A Brief Review of Hypernetworks in Deep Learning","created":"2023-06-12","cited_by_count":102,"area":null},{"id":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2101.01035","title":"HyperMorph: Amortized Hyperparameter Learning for Image Registration","created":"2021-01-04","cited_by_count":85,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74,"area":null},{"id":"2103.12424","title":"BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search","created":"2021-03-23","cited_by_count":63,"area":null},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58,"area":null},{"id":"2103.11832","title":"Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion","created":"2021-03-22","cited_by_count":56,"area":null},{"id":"2201.10355","title":"Neural Architecture Search for Spiking Neural Networks","created":"2022-01-23","cited_by_count":53,"area":null},{"id":"2402.13144","title":"Neural Network Diffusion","created":"2024-02-20","cited_by_count":42,"area":"diffusion"},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2203.16680","title":"Learning the Effect of Registration Hyperparameters with HyperMorph","created":"2022-03-30","cited_by_count":35,"area":null},{"id":"2209.05227","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","created":"2022-09-12","cited_by_count":35,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2101.11834","title":"Neural Architecture Search with Random Labels","created":"2021-01-28","cited_by_count":33,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2107.13686","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","created":"2021-07-29","cited_by_count":31,"area":null},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2312.12487","title":"Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models","created":"2023-12-19","cited_by_count":31,"area":"diffusion"},{"id":"2303.04143","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2402.12550","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","created":"2024-02-19","cited_by_count":28,"area":"moe"},{"id":"2101.11342","title":"Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search","created":"2021-01-27","cited_by_count":27,"area":null},{"id":"2104.12642","title":"CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment","created":"2021-04-26","cited_by_count":26,"area":null},{"id":"2111.00902","title":"PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices","created":"2021-11-01","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":"2208.05836","title":"HyperTime: Implicit Neural Representation for Time Series","created":"2022-08-11","cited_by_count":24,"area":null},{"id":"2107.06869","title":"Core-set Sampling for Efficient Neural Architecture Search","created":"2021-07-08","cited_by_count":23,"area":null},{"id":"2203.14949","title":"Controllable Dynamic Multi-Task Architectures","created":"2022-03-28","cited_by_count":21,"area":null},{"id":"2102.11646","title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","created":"2021-02-23","cited_by_count":20,"area":null},{"id":"2108.12821","title":"Analyzing and Mitigating Interference in Neural Architecture Search","created":"2021-08-29","cited_by_count":20,"area":null},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20,"area":null},{"id":"2403.13447","title":"HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models","created":"2024-03-20","cited_by_count":20,"area":"mllm"},{"id":"2403.20233","title":"Functional Bilevel Optimization for Machine Learning","created":"2024-03-29","cited_by_count":20,"area":null},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2103.04507","title":"OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection","created":"2021-03-08","cited_by_count":19,"area":null},{"id":"2201.08459","title":"Federated Learning with Heterogeneous Architectures using Graph HyperNetworks","created":"2022-01-20","cited_by_count":19,"area":null},{"id":"2312.08399","title":"Principled Weight Initialization for Hypernetworks","created":"2023-12-13","cited_by_count":19,"area":null},{"id":"2103.09439","title":"HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2203.02202","title":"Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis","created":"2022-03-04","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":"2102.10301","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","created":"2021-02-20","cited_by_count":17,"area":null},{"id":"2404.01143","title":"Condition-Aware Neural Network for Controlled Image Generation","created":"2024-04-01","cited_by_count":16,"area":null},{"id":"2210.07998","title":"$\\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells","created":"2022-10-14","cited_by_count":15,"area":null},{"id":"2501.11587","title":"Recurrent Diffusion for Large-Scale Parameter Generation","created":"2025-01-20","cited_by_count":15,"area":null},{"id":"2108.09671","title":"Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift","created":"2021-08-22","cited_by_count":14,"area":null},{"id":"2112.10652","title":"HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet","created":"2021-12-20","cited_by_count":14,"area":null},{"id":"2204.05599","title":"HyperDet3D: Learning a Scene-conditioned 3D Object Detector","created":"2022-04-12","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","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":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14,"area":null},{"id":"2105.14669","title":"Memory-Efficient Differentiable Transformer Architecture Search","created":"2021-05-31","cited_by_count":13,"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":"2201.09874","title":"CVAE-H: Conditionalizing Variational Autoencoders via Hypernetworks and Trajectory Forecasting for Autonomous Driving","created":"2022-01-24","cited_by_count":13,"area":null},{"id":"2304.05352","title":"SPOT: Sequential Predictive Modeling of Clinical Trial Outcome with Meta-Learning","created":"2023-04-07","cited_by_count":13,"area":null},{"id":"2102.08619","title":"Rethinking Co-design of Neural Architectures and Hardware Accelerators","created":"2021-02-17","cited_by_count":12,"area":null},{"id":"1812.05285","title":"IRLAS: Inverse Reinforcement Learning for Architecture Search","created":"2018-12-13","cited_by_count":10,"area":"offlinerl"},{"id":"2108.04541","title":"Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluation","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2108.11014","title":"iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization","created":"2021-08-25","cited_by_count":10,"area":null},{"id":"2307.08279","title":"Combiner and HyperCombiner Networks: Rules to Combine Multimodality MR Images for Prostate Cancer Localisation","created":"2023-07-17","cited_by_count":10,"area":null},{"id":"2101.02194","title":"Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworks","created":"2021-01-06","cited_by_count":9,"area":null},{"id":"2104.08702","title":"Reconsidering CO2 emissions from Computer Vision","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2206.06620","title":"Slimmable Domain Adaptation","created":"2022-06-14","cited_by_count":9,"area":null},{"id":"2210.00471","title":"OCD: Learning to Overfit with Conditional Diffusion Models","created":"2022-10-02","cited_by_count":9,"area":"diffusion"},{"id":"2103.01495","title":"Task-Adaptive Neural Network Search with Meta-Contrastive Learning","created":"2021-03-02","cited_by_count":8,"area":null},{"id":"2112.02086","title":"Data-Free Neural Architecture Search via Recursive Label Calibration","created":"2021-12-03","cited_by_count":8,"area":null},{"id":"2202.11009","title":"Computing Multiple Image Reconstructions with a Single Hypernetwork","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2310.18384","title":"MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollers","created":"2023-10-27","cited_by_count":8,"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":"2109.07582","title":"Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural Architecture Search","created":"2021-09-14","cited_by_count":7,"area":null},{"id":"2110.02900","title":"Meta Internal Learning","created":"2021-10-06","cited_by_count":7,"area":null},{"id":"2208.00791","title":"Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search","created":"2022-08-01","cited_by_count":7,"area":null},{"id":"2306.10724","title":"Partial Hypernetworks for Continual Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2308.07760","title":"Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2502.20422","title":"SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models","created":"2025-02-27","cited_by_count":7,"area":"distill"},{"id":"2503.00838","title":"Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2110.04711","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2303.12797","title":"An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters","created":"2023-02-27","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":"2307.10529","title":"Fast Unsupervised Deep Outlier Model Selection with Hypernetworks","created":"2023-07-20","cited_by_count":6,"area":null},{"id":"2308.09915","title":"EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning","created":"2023-08-19","cited_by_count":6,"area":null},{"id":"2412.04095","title":"HyperFLINT: Hypernetwork-based Flow Estimation and Temporal Interpolation for Scientific Ensemble Visualization","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2503.24354","title":"ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion","created":"2025-03-31","cited_by_count":6,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2102.10557","title":"Contrastive Self-supervised Neural Architecture Search","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2203.09041","title":"DATA: Domain-Aware and Task-Aware Self-supervised Learning","created":"2022-03-17","cited_by_count":5,"area":null},{"id":"2207.07868","title":"CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS","created":"2022-07-16","cited_by_count":5,"area":null},{"id":"2208.06820","title":"Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation","created":"2022-08-14","cited_by_count":5,"area":null},{"id":"2210.02959","title":"POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique","created":"2022-10-06","cited_by_count":5,"area":null},{"id":"2211.15155","title":"GraphPNAS: Learning Distribution of Good Neural Architectures via Deep Graph Generative Models","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2405.20882","title":"Sheaf HyperNetworks for Personalized Federated Learning","created":"2024-05-31","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"}],"next_cursor":"100"}