{"total":188,"rows":[{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"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":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2109.05211","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","created":"2021-09-11","cited_by_count":79,"area":null},{"id":"2304.10970","title":"Can GPT-4 Perform Neural Architecture Search?","created":"2023-04-21","cited_by_count":74,"area":null},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66,"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":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41,"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":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37,"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":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36,"area":null},{"id":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32,"area":"distill"},{"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":"2312.09299","title":"Weight subcloning: direct initialization of transformers using larger pretrained ones","created":"2023-12-14","cited_by_count":30,"area":null},{"id":"2310.16712","title":"LLM Performance Predictors are good initializers for Architecture Search","created":"2023-10-25","cited_by_count":29,"area":null},{"id":"2102.10490","title":"Stronger NAS with Weaker Predictors","created":"2021-02-21","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":"2106.11346","title":"GAIA: A Transfer Learning System of Object Detection that Fits Your Needs","created":"2021-06-21","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":"2105.10154","title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","created":"2021-05-21","cited_by_count":26,"area":null},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2203.15207","title":"Generalizing Few-Shot NAS with Gradient Matching","created":"2022-03-29","cited_by_count":25,"area":null},{"id":"2208.11547","title":"ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild","created":"2022-08-23","cited_by_count":23,"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":"2105.08952","title":"BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer","created":"2021-05-19","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":"2106.08630","title":"HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2106.08895","title":"Masked Training of Neural Networks with Partial Gradients","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2203.15380","title":"SepViT: Separable Vision Transformer","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2106.11890","title":"Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization","created":"2021-06-22","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":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15,"area":null},{"id":"2106.02435","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","created":"2021-06-04","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":"2204.04705","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":"2104.00031","title":"NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization","created":"2021-03-31","cited_by_count":13,"area":null},{"id":"2105.07085","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","created":"2021-05-14","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":"2401.01543","title":"Retraining-free Model Quantization via One-Shot Weight-Coupling Learning","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2104.00597","title":"One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking","created":"2021-04-01","cited_by_count":12,"area":null},{"id":"2106.06575","title":"Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators","created":"2021-06-11","cited_by_count":12,"area":null},{"id":"2110.08352","title":"Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet","created":"2021-10-15","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":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2312.16733","title":"SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads","created":"2023-12-27","cited_by_count":12,"area":null},{"id":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","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":"2109.03508","title":"RepNAS: Searching for Efficient Re-parameterizing Blocks","created":"2021-09-08","cited_by_count":11,"area":null},{"id":"2111.07535","title":"T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging","created":"2021-11-15","cited_by_count":11,"area":null},{"id":"2112.10878","title":"Enabling NAS with Automated Super-Network Generation","created":"2021-12-20","cited_by_count":11,"area":null},{"id":"2312.15408","title":"Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective","created":"2023-12-24","cited_by_count":11,"area":null},{"id":"2210.04153","title":"Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing","created":"2022-10-09","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":"2307.02092","title":"Make A Long Image Short: Adaptive Token Length for Vision Transformers","created":"2023-07-05","cited_by_count":10,"area":null},{"id":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2404.09532","title":"TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models","created":"2024-04-15","cited_by_count":10,"area":"diffusion"},{"id":"2407.05010","title":"PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2103.13253","title":"Learning Versatile Neural Architectures by Propagating Network Codes","created":"2021-03-24","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":"2109.00642","title":"Searching for Efficient Multi-Stage Vision Transformers","created":"2021-09-01","cited_by_count":9,"area":null},{"id":"2208.05271","title":"Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation","created":"2022-08-10","cited_by_count":9,"area":null},{"id":"2307.08065","title":"MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment","created":"2023-07-16","cited_by_count":9,"area":null},{"id":"2401.06426","title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer","created":"2024-01-12","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":"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":"2205.08119","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","created":"2022-05-17","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":"2205.00841","title":"GPUNet: Searching the Deployable Convolution Neural Networks for GPUs","created":"2022-04-26","cited_by_count":7,"area":null},{"id":"2207.07187","title":"NASRec: Weight Sharing Neural Architecture Search for Recommender Systems","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2306.04845","title":"Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts","created":"2023-06-08","cited_by_count":7,"area":"moe"},{"id":"2308.11744","title":"Efficient Controllable Multi-Task Architectures","created":"2023-08-22","cited_by_count":7,"area":null},{"id":"2403.02446","title":"On Latency Predictors for Neural Architecture Search","created":"2024-03-04","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":"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":"2305.02507","title":"Stimulative Training++: Go Beyond The Performance Limits of Residual Networks","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2305.08117","title":"MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2412.04786","title":"Slicing Vision Transformer for Flexible Inference","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2201.12725","title":"Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search","created":"2022-01-30","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":"2208.10861","title":"FocusFormer: Focusing on What We Need via Architecture Sampler","created":"2022-08-23","cited_by_count":5,"area":null},{"id":"2210.13361","title":"NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2211.12759","title":"NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2303.13121","title":"DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter","created":"2023-03-23","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":"2304.11835","title":"Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2404.01353","title":"Efficiently Distilling LLMs for Edge Applications","created":"2024-04-01","cited_by_count":5,"area":"distill"},{"id":"2405.02267","title":"Structural Pruning of Pre-trained Language Models via Neural Architecture Search","created":"2024-05-03","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"}],"next_cursor":"100"}