{"total":271,"rows":[{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"area":null},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"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":"2102.04170","title":"Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach","created":"2021-02-08","cited_by_count":110,"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":"2104.03438","title":"Convolutional Neural Network Pruning with Structural Redundancy Reduction","created":"2021-04-08","cited_by_count":73,"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":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"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":"2106.02990","title":"Self-Damaging Contrastive Learning","created":"2021-06-06","cited_by_count":48,"area":null},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46,"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":"2103.15726","title":"Slimmable Compressive Autoencoders for Practical Neural Image Compression","created":"2021-03-29","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":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","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":"2206.14383","title":"Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems","created":"2022-06-29","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":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2103.08756","title":"Revisiting Dynamic Convolution via Matrix Decomposition","created":"2021-03-15","cited_by_count":35,"area":null},{"id":"2203.09747","title":"Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization","created":"2022-03-18","cited_by_count":35,"area":null},{"id":"2106.02022","title":"Single Image Depth Prediction with Wavelet Decomposition","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2203.15243","title":"Fine-tuning Image Transformers using Learnable Memory","created":"2022-03-29","cited_by_count":34,"area":null},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33,"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":"2110.05323","title":"ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training","created":"2021-10-11","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":"2108.05894","title":"MicroNet: Improving Image Recognition with Extremely Low FLOPs","created":"2021-08-12","cited_by_count":26,"area":null},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2108.05009","title":"Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion","created":"2021-08-11","cited_by_count":25,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"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":"2108.06908","title":"Online Multi-Granularity Distillation for GAN Compression","created":"2021-08-16","cited_by_count":24,"area":null},{"id":"2207.01580","title":"Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks","created":"2022-07-04","cited_by_count":24,"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":"2210.07913","title":"Efficiently Controlling Multiple Risks with Pareto Testing","created":"2022-10-14","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":"2303.05715","title":"Context-Based Trit-Plane Coding for Progressive Image Compression","created":"2023-03-10","cited_by_count":21,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"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":"2203.11442","title":"Scalable Video Object Segmentation with Identification Mechanism","created":"2022-03-22","cited_by_count":18,"area":null},{"id":"2306.14306","title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","created":"2023-06-25","cited_by_count":17,"area":null},{"id":"2101.07985","title":"Network Pruning using Adaptive Exemplar Filters","created":"2021-01-20","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":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","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":"2404.01143","title":"Condition-Aware Neural Network for Controlled Image Generation","created":"2024-04-01","cited_by_count":16,"area":null},{"id":"2102.07887","title":"VA-RED$^2$: Video Adaptive Redundancy Reduction","created":"2021-02-15","cited_by_count":15,"area":null},{"id":"2103.02644","title":"Compute and memory efficient universal sound source separation","created":"2021-03-03","cited_by_count":15,"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":"2201.03297","title":"GhostNets on Heterogeneous Devices via Cheap Operations","created":"2022-01-10","cited_by_count":15,"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":"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":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2103.15750","title":"Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design","created":"2021-03-25","cited_by_count":13,"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":"2205.11397","title":"Super Vision Transformer","created":"2022-05-23","cited_by_count":13,"area":null},{"id":"2207.09663","title":"Streamable Neural Fields","created":"2022-07-20","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":"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":"2109.03508","title":"RepNAS: Searching for Efficient Re-parameterizing Blocks","created":"2021-09-08","cited_by_count":11,"area":null},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11,"area":null},{"id":"2409.17978","title":"HydraViT: Stacking Heads for a Scalable ViT","created":"2024-09-26","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":"2112.08761","title":"DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systems","created":"2021-12-16","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":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","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":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","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":"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":"2209.06359","title":"Federated Pruning: Improving Neural Network Efficiency with Federated Learning","created":"2022-09-14","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":"2102.11382","title":"Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity","created":"2021-02-22","cited_by_count":7,"area":null},{"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":"2407.18930","title":"Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2407.21139","title":"Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning","created":"2024-07-30","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":"2507.19360","title":"EA-ViT: Efficient Adaptation for Elastic Vision Transformer","created":"2025-07-25","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}],"next_cursor":"100"}