{"total":96,"rows":[{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522,"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":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79,"area":null},{"id":"2105.01883","title":"RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition","created":"2021-05-05","cited_by_count":40,"area":null},{"id":"2107.08147","title":"AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning","created":"2021-07-16","cited_by_count":39,"area":null},{"id":"2304.04237","title":"Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention","created":"2023-04-09","cited_by_count":38,"area":null},{"id":"2205.15242","title":"Re-parameterizing Your Optimizers rather than Architectures","created":"2022-05-30","cited_by_count":35,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2112.11081","title":"RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality","created":"2021-12-21","cited_by_count":32,"area":null},{"id":"2205.13603","title":"Tensor Program Optimization with Probabilistic Programs","created":"2022-05-26","cited_by_count":30,"area":null},{"id":"2105.09564","title":"Dual-side Sparse Tensor Core","created":"2021-05-20","cited_by_count":29,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2204.08397","title":"Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2305.12393","title":"Layer Collaboration in the Forward-Forward Algorithm","created":"2023-05-21","cited_by_count":21,"area":null},{"id":"2105.12842","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","created":"2021-05-26","cited_by_count":19,"area":null},{"id":"2310.14848","title":"Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2311.16833","title":"1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness","created":"2023-11-28","cited_by_count":16,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"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":"2201.10369","title":"Winograd Convolution for Deep Neural Networks: Efficient Point Selection","created":"2022-01-25","cited_by_count":8,"area":null},{"id":"2203.13556","title":"Deformable Butterfly: A Highly Structured and Sparse Linear Transform","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2104.09252","title":"Learning on Hardware: A Tutorial on Neural Network Accelerators and Co-Processors","created":"2021-04-19","cited_by_count":6,"area":null},{"id":"2202.08675","title":"Winograd Convolution: A Perspective from Fault Tolerance","created":"2022-02-17","cited_by_count":6,"area":null},{"id":"2206.07446","title":"Boosting DNN Cold Inference on Edge Devices","created":"2022-06-15","cited_by_count":6,"area":null},{"id":"2305.18334","title":"PQA: Exploring the Potential of Product Quantization in DNN Hardware Acceleration","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2107.04244","title":"WinoCNN: Kernel Sharing Winograd Systolic Array for Efficient Convolutional Neural Network Acceleration on FPGAs","created":"2021-07-09","cited_by_count":5,"area":null},{"id":"2206.05700","title":"A Functional Information Perspective on Model Interpretation","created":"2022-06-12","cited_by_count":5,"area":null},{"id":"2105.05530","title":"Winograd Algorithm for AdderNet","created":"2021-05-12","cited_by_count":4,"area":null},{"id":"2108.05580","title":"perf4sight: A toolflow to model CNN training performance on Edge GPUs","created":"2021-08-12","cited_by_count":4,"area":null},{"id":"2205.09120","title":"Fast matrix multiplication for binary and ternary CNNs on ARM CPU","created":"2022-05-18","cited_by_count":4,"area":null},{"id":"2507.04792","title":"Model Compression using Progressive Channel Pruning","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2112.15445","title":"Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction","created":"2021-12-28","cited_by_count":3,"area":null},{"id":"2304.03388","title":"InferNet: Exploiting Aggregate GPU Profiles as Side-Channel for DNN Architecture Inference","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2306.14316","title":"Im2win: An Efficient Convolution Paradigm on GPU","created":"2023-06-25","cited_by_count":3,"area":null},{"id":"2308.07641","title":"Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping","created":"2023-08-15","cited_by_count":3,"area":null},{"id":"2409.17016","title":"CNN Mixture-of-Depths","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2209.00411","title":"Efficient ML Models for Practical Secure Inference","created":"2022-08-26","cited_by_count":2,"area":null},{"id":"2311.00586","title":"PAUMER: Patch Pausing Transformer for Semantic Segmentation","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2311.12224","title":"Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators","created":"2023-11-20","cited_by_count":2,"area":null},{"id":"2402.02361","title":"Pruner: A Draft-then-Verify Exploration Mechanism to Accelerate Tensor Program Tuning","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2510.23389","title":"Floating-Point Neural Network Verification at the Software Level","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2102.13272","title":"Accelerating Large Kernel Convolutions with Nested Winograd Transformation.pdf","created":"2021-02-26","cited_by_count":1,"area":null},{"id":"2103.16234","title":"cuConv: A CUDA Implementation of Convolution for CNN Inference","created":"2021-03-30","cited_by_count":1,"area":null},{"id":"2104.08002","title":"Efficient and Generic 1D Dilated Convolution Layer for Deep Learning","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2108.11441","title":"Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edge","created":"2021-08-25","cited_by_count":1,"area":null},{"id":"2203.06589","title":"AugShuffleNet: Communicate More, Compute Less","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2204.06718","title":"Learning Convolutional Neural Networks in the Frequency Domain","created":"2022-04-14","cited_by_count":1,"area":null},{"id":"2208.02025","title":"OLLIE: Derivation-based Tensor Program Optimizer","created":"2022-08-02","cited_by_count":1,"area":null},{"id":"2209.03704","title":"Kernel-Segregated Transpose Convolution Operation","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2209.12982","title":"Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2210.02620","title":"Inference Latency Prediction at the Edge","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2301.11180","title":"Low-Rank Winograd Transformation for 3D Convolutional Neural Networks","created":"2023-01-26","cited_by_count":1,"area":null},{"id":"2308.08230","title":"Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2404.05872","title":"TabConv: Low-Computation CNN Inference via Table Lookups","created":"2024-04-08","cited_by_count":1,"area":null},{"id":"2407.00449","title":"Fully tensorial approach to hypercomplex-valued neural networks","created":"2024-06-29","cited_by_count":1,"area":null},{"id":"2407.02913","title":"SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2505.13461","title":"FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2505.24527","title":"Optimal Density Functions for Weighted Convolution in Learning Models","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2609.10632","title":"Numbat: Building and Verifying a Self-Contained Machine-Learning Stack","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2106.06778","title":"Dynamic Clone Transformer for Efficient Convolutional Neural Netwoks","created":"2021-06-12","cited_by_count":0,"area":null},{"id":"2106.12810","title":"A Construction Kit for Efficient Low Power Neural Network Accelerator Designs","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2111.00977","title":"Fast Convolution based on Winograd Minimum Filtering: Introduction and Development","created":"2021-11-01","cited_by_count":0,"area":null},{"id":"2202.02783","title":"Energy awareness in low precision neural networks","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2206.10620","title":"CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2211.08339","title":"Pruning Very Deep Neural Network Channels for Efficient Inference","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2212.06361","title":"Numerical Stability of DeepGOPlus Inference","created":"2022-12-13","cited_by_count":0,"area":null},{"id":"2301.03047","title":"Large-scale Global Low-rank Optimization for Computational Compressed Imaging","created":"2023-01-08","cited_by_count":0,"area":null},{"id":"2302.09564","title":"Fixflow: A Framework to Evaluate Fixed-point Arithmetic in Light-Weight CNN Inference","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2311.08909","title":"DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2312.14441","title":"DMC4ML: Data Movement Complexity for Machine Learning","created":"2023-12-22","cited_by_count":0,"area":null},{"id":"2401.15949","title":"TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2402.08645","title":"Peeking Behind the Curtains of Residual Learning","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2403.11251","title":"NeoNeXt: Novel neural network operator and architecture based on the patch-wise matrix multiplications","created":"2024-03-17","cited_by_count":0,"area":null},{"id":"2405.06345","title":"Evaluating Adversarial Robustness in the Spatial Frequency Domain","created":"2024-05-10","cited_by_count":0,"area":null},{"id":"2406.00290","title":"Phasor-Driven Acceleration for FFT-based CNNs","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2407.10730","title":"ConvBench: A Comprehensive Benchmark for 2D Convolution Primitive Evaluation","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2410.08300","title":"A Framework to Enable Algorithmic Design Choice Exploration in DNNs","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2411.01579","title":"Flexible Coded Distributed Convolution Computing for Enhanced Straggler Resilience and Numerical Stability in Distributed CNNs","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2411.15659","title":"SMM-Conv: Scalar Matrix Multiplication with Zero Packing for Accelerated Convolution","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2501.08889","title":"Karatsuba Matrix Multiplication and its Efficient Custom Hardware Implementations","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2502.10063","title":"Strassen Multisystolic Array Hardware Architectures","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2506.10407","title":"Semi-Tensor-Product Based Convolutional Neural Networks","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2508.07011","title":"HiMat: DiT-based Ultra-High Resolution SVBRDF Generation","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2509.26217","title":"Benchmarking Deep Learning Convolutions on Energy-constrained CPUs","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.18222","title":"Using MLIR Transform to Design Sliced Convolution Algorithm","created":"2025-11-22","cited_by_count":0,"area":null},{"id":"2512.08888","title":"Accelerated Rotation-Invariant Convolution for UAV Image Segmentation","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.18453","title":"NOVA: Discovering Well-Conditioned Winograd Transforms through Numerical Optimization of Vandermonde Arithmetic","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2602.18758","title":"UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2602.21965","title":"Compact Circulant Layers with Spectral Priors","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.09054","title":"Spectral-Structured Diffusion for Single-Image Rain Removal","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.12067","title":"Beyond Convolution: A Taxonomy of Structured Operators for Learning-Based Image Processing","created":"2026-03-12","cited_by_count":0,"area":null}],"next_cursor":null}