{"total":348,"rows":[{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163,"area":null},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135,"area":null},{"id":"2302.14838","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","created":"2023-02-28","cited_by_count":131,"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":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2304.10970","title":"Can GPT-4 Perform Neural Architecture Search?","created":"2023-04-21","cited_by_count":74,"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":"2102.03983","title":"Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning","created":"2021-02-08","cited_by_count":72,"area":null},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71,"area":null},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66,"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":"2101.03958","title":"Evolving Reinforcement Learning Algorithms","created":"2021-01-08","cited_by_count":49,"area":null},{"id":"2002.04013","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","created":"2020-02-10","cited_by_count":43,"area":"moe"},{"id":"2201.12738","title":"AutoSNN: Towards Energy-Efficient Spiking Neural Networks","created":"2022-01-30","cited_by_count":40,"area":null},{"id":"2103.00742","title":"Automated Machine Learning on Graphs: A Survey","created":"2021-03-01","cited_by_count":39,"area":null},{"id":"2105.03354","title":"The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems","created":"2021-05-07","cited_by_count":39,"area":null},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37,"area":null},{"id":"2108.10587","title":"Pooling Architecture Search for Graph Classification","created":"2021-08-24","cited_by_count":36,"area":null},{"id":"2101.01761","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","created":"2021-01-05","cited_by_count":35,"area":null},{"id":"2108.01289","title":"AdvRush: Searching for Adversarially Robust Neural Architectures","created":"2021-08-03","cited_by_count":28,"area":null},{"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":"2103.14282","title":"Rethinking Graph Neural Architecture Search from Message-passing","created":"2021-03-26","cited_by_count":26,"area":null},{"id":"2206.09166","title":"NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search","created":"2022-06-18","cited_by_count":25,"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":"2102.07108","title":"CATE: Computation-aware Neural Architecture Encoding with Transformers","created":"2021-02-14","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":"2108.12821","title":"Analyzing and Mitigating Interference in Neural Architecture Search","created":"2021-08-29","cited_by_count":20,"area":null},{"id":"2110.08557","title":"DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy","created":"2021-10-16","cited_by_count":20,"area":null},{"id":"2101.08809","title":"PyGlove: Symbolic Programming for Automated Machine Learning","created":"2021-01-21","cited_by_count":19,"area":null},{"id":"2105.01015","title":"Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization","created":"2021-05-03","cited_by_count":19,"area":null},{"id":"2112.14531","title":"Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective","created":"2021-12-29","cited_by_count":19,"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":"2208.04321","title":"Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment","created":"2022-08-08","cited_by_count":17,"area":null},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"area":null},{"id":"2201.03801","title":"Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019","created":"2022-01-11","cited_by_count":16,"area":null},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16,"area":null},{"id":"2411.02433","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","created":"2024-11-01","cited_by_count":16,"area":"moe"},{"id":"2101.06658","title":"Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution","created":"2021-01-17","cited_by_count":15,"area":null},{"id":"2102.05710","title":"Derivative-Free Reinforcement Learning: A Review","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2111.10007","title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","created":"2021-11-19","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":"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":"2301.10281","title":"Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge","created":"2023-01-24","cited_by_count":15,"area":null},{"id":"2306.06712","title":"Neural Architecture Design and Robustness: A Dataset","created":"2023-06-11","cited_by_count":15,"area":null},{"id":"2107.13153","title":"Homogeneous Architecture Augmentation for Neural Predictor","created":"2021-07-28","cited_by_count":14,"area":null},{"id":"2108.01899","title":"Generic Neural Architecture Search via Regression","created":"2021-08-04","cited_by_count":14,"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":"2204.04705","title":"SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems","created":"2022-04-10","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":"2410.23691","title":"Automatically Learning Hybrid Digital Twins of Dynamical Systems","created":"2024-10-31","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":"2106.14033","title":"BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation","created":"2021-06-26","cited_by_count":13,"area":null},{"id":"2107.05033","title":"Blending Pruning Criteria for Convolutional Neural Networks","created":"2021-07-11","cited_by_count":13,"area":null},{"id":"2108.06885","title":"Neural Architecture Dilation for Adversarial Robustness","created":"2021-08-16","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":"2409.12255","title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2108.01265","title":"Memorize, Factorize, or be Na\\\"ive: Learning Optimal Feature Interaction Methods for CTR Prediction","created":"2021-08-03","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":"2206.01520","title":"A Survey on Computationally Efficient Neural Architecture Search","created":"2022-06-03","cited_by_count":12,"area":null},{"id":"2107.10624","title":"LANA: Latency Aware Network Acceleration","created":"2021-07-12","cited_by_count":11,"area":"distill"},{"id":"2108.00568","title":"FLASH: Fast Neural Architecture Search with Hardware Optimization","created":"2021-08-01","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":"2102.05348","title":"Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition","created":"2021-02-10","cited_by_count":10,"area":null},{"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":"2204.13160","title":"AutoLossGen: Automatic Loss Function Generation for Recommender Systems","created":"2022-04-27","cited_by_count":10,"area":null},{"id":"2207.05135","title":"FreeREA: Training-Free Evolution-based Architecture Search","created":"2022-06-17","cited_by_count":10,"area":null},{"id":"2303.09730","title":"ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices","created":"2023-03-17","cited_by_count":10,"area":null},{"id":"2108.06156","title":"EEEA-Net: An Early Exit Evolutionary Neural Architecture Search","created":"2021-08-13","cited_by_count":9,"area":null},{"id":"2109.00642","title":"Searching for Efficient Multi-Stage Vision Transformers","created":"2021-09-01","cited_by_count":9,"area":null},{"id":"2110.10165","title":"NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters","created":"2021-10-19","cited_by_count":9,"area":null},{"id":"2111.04459","title":"Triple-level Model Inferred Collaborative Network Architecture for Video Deraining","created":"2021-11-08","cited_by_count":9,"area":null},{"id":"2112.08273","title":"Programming Knowledge Tracing: A Comprehensive Dataset and A New Model","created":"2021-12-11","cited_by_count":9,"area":null},{"id":"2201.01288","title":"Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions","created":"2022-01-04","cited_by_count":9,"area":null},{"id":"2204.05941","title":"Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search","created":"2022-04-12","cited_by_count":9,"area":null},{"id":"2206.08852","title":"Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes","created":"2022-06-17","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":"2303.06856","title":"Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies","created":"2023-03-13","cited_by_count":9,"area":null},{"id":"2104.05309","title":"Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search","created":"2021-04-12","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":"2204.12726","title":"PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search","created":"2022-04-27","cited_by_count":8,"area":null},{"id":"2210.05484","title":"Equivariance-aware Architectural Optimization of Neural Networks","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2303.07669","title":"AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks","created":"2023-03-14","cited_by_count":8,"area":null},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2105.10626","title":"Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound","created":"2021-05-22","cited_by_count":7,"area":null},{"id":"2110.05621","title":"Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo","created":"2021-10-11","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":"2301.09231","title":"GP-NAS-ensemble: a model for NAS Performance Prediction","created":"2023-01-23","cited_by_count":7,"area":null},{"id":"2310.07217","title":"Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2407.00584","title":"Hyperparameter Optimization for Randomized Algorithms: A Case Study on Random Features","created":"2024-06-30","cited_by_count":7,"area":null},{"id":"2103.02904","title":"Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2105.06369","title":"Neighborhood-Aware Neural Architecture Search","created":"2021-05-13","cited_by_count":6,"area":null}],"next_cursor":"100"}