{"total":221,"rows":[{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"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":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75,"area":"inference"},{"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":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50,"area":null},{"id":"2302.05071","title":"EVC: Towards Real-Time Neural Image Compression with Mask Decay","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2406.10260","title":"Flextron: Many-in-One Flexible Large Language Model","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"id":"2103.15726","title":"Slimmable Compressive Autoencoders for Practical Neural Image Compression","created":"2021-03-29","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":"2204.03880","title":"CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning","created":"2022-04-08","cited_by_count":34,"area":null},{"id":"2105.09103","title":"Recursive-NeRF: An Efficient and Dynamically Growing NeRF","created":"2021-05-19","cited_by_count":32,"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":"2111.14655","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2105.13878","title":"Accelerating BERT Inference for Sequence Labeling via Early-Exit","created":"2021-05-28","cited_by_count":29,"area":"inference"},{"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":"2112.06334","title":"DPICT: Deep Progressive Image Compression Using Trit-Planes","created":"2021-12-12","cited_by_count":25,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2406.09135","title":"AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring","created":"2024-06-13","cited_by_count":25,"area":null},{"id":"2105.11683","title":"Towards Compact Single Image Super-Resolution via Contrastive Self-distillation","created":"2021-05-25","cited_by_count":24,"area":"distill"},{"id":"2310.03337","title":"Denoising Diffusion Step-aware Models","created":"2023-10-05","cited_by_count":24,"area":"diffusion"},{"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":"2103.17267","title":"Bit-Mixer: Mixed-precision networks with runtime bit-width selection","created":"2021-03-31","cited_by_count":22,"area":null},{"id":"2304.14593","title":"Deep Graph Reprogramming","created":"2023-04-28","cited_by_count":22,"area":null},{"id":"2404.00742","title":"Adapting to Length Shift: FlexiLength Network for Trajectory Prediction","created":"2024-03-31","cited_by_count":22,"area":null},{"id":"2207.05306","title":"Contrastive Deep Supervision","created":"2022-07-12","cited_by_count":20,"area":null},{"id":"2112.00459","title":"Information Theoretic Representation Distillation","created":"2021-12-01","cited_by_count":19,"area":"distill"},{"id":"2203.10812","title":"ARM: Any-Time Super-Resolution Method","created":"2022-03-21","cited_by_count":19,"area":null},{"id":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2105.03596","title":"Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms","created":"2021-05-08","cited_by_count":18,"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":"2203.11589","title":"Adaptive Patch Exiting for Scalable Single Image Super-Resolution","created":"2022-03-22","cited_by_count":16,"area":null},{"id":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2103.07289","title":"Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator","created":"2021-03-12","cited_by_count":15,"area":null},{"id":"2312.10034","title":"SlimmeRF: Slimmable Radiance Fields","created":"2023-12-15","cited_by_count":15,"area":null},{"id":"2107.01269","title":"Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition","created":"2021-07-02","cited_by_count":14,"area":null},{"id":"2112.02543","title":"Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networks","created":"2021-12-05","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":"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":"2106.09216","title":"Layer Pruning on Demand with Intermediate CTC","created":"2021-06-17","cited_by_count":13,"area":null},{"id":"2206.00395","title":"Optimization with Access to Auxiliary Information","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2207.09663","title":"Streamable Neural Fields","created":"2022-07-20","cited_by_count":13,"area":null},{"id":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13,"area":null},{"id":"2302.02184","title":"Real-Time Image Demoireing on Mobile Devices","created":"2023-02-04","cited_by_count":13,"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":"2302.05666","title":"Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels","created":"2023-02-11","cited_by_count":12,"area":"distill"},{"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":"2106.07734","title":"CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition","created":"2021-06-14","cited_by_count":11,"area":"distill"},{"id":"2112.10878","title":"Enabling NAS with Automated Super-Network Generation","created":"2021-12-20","cited_by_count":11,"area":null},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"area":null},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2507.06671","title":"FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting","created":"2025-07-09","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":"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":"2110.08940","title":"Dynamic Slimmable Denoising Network","created":"2021-10-17","cited_by_count":9,"area":null},{"id":"2206.06620","title":"Slimmable Domain Adaptation","created":"2022-06-14","cited_by_count":9,"area":null},{"id":"2211.16749","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","created":"2022-11-30","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":"2110.09195","title":"Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks","created":"2021-10-18","cited_by_count":8,"area":null},{"id":"2203.03324","title":"Dynamic ConvNets on Tiny Devices via Nested Sparsity","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2309.06612","title":"Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2410.17752","title":"AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution","created":"2024-10-23","cited_by_count":8,"area":"diffusion"},{"id":"2106.08960","title":"Collaborative Training of Acoustic Encoders for Speech Recognition","created":"2021-06-16","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":"2308.11744","title":"Efficient Controllable Multi-Task Architectures","created":"2023-08-22","cited_by_count":7,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2507.10800","title":"ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2103.01847","title":"Network Pruning via Resource Reallocation","created":"2021-03-02","cited_by_count":6,"area":null},{"id":"2105.00591","title":"Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2105.12386","title":"CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network","created":"2021-05-26","cited_by_count":6,"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":"2203.14094","title":"SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networks","created":"2022-03-26","cited_by_count":6,"area":null},{"id":"2207.05252","title":"Dynamic Proposals for Efficient Object Detection","created":"2022-07-12","cited_by_count":6,"area":null},{"id":"2303.04887","title":"Memory-adaptive Depth-wise Heterogeneous Federated Learning","created":"2023-03-08","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":"2309.00255","title":"SortedNet: A Scalable and Generalized Framework for Training Modular Deep Neural Networks","created":"2023-09-01","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":"2502.04850","title":"Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks","created":"2025-02-07","cited_by_count":6,"area":null},{"id":"2203.02651","title":"Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning","created":"2022-03-05","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":"2205.14570","title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2210.00588","title":"DFA: Dynamic Feature Aggregation for Efficient Video Object Detection","created":"2022-10-02","cited_by_count":5,"area":null},{"id":"2212.05122","title":"All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2303.06870","title":"Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning","created":"2023-03-13","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":"2306.00183","title":"Diffused Redundancy in Pre-trained Representations","created":"2023-05-31","cited_by_count":5,"area":"mechinterp"},{"id":"2308.11464","title":"Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning","created":"2023-08-22","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"}