{"total":135,"rows":[{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2102.07952","title":"A Survey of Machine Learning for Computer Architecture and Systems","created":"2021-02-16","cited_by_count":53,"area":null},{"id":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","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":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","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":"2106.10860","title":"Multiplying Matrices Without Multiplying","created":"2021-06-21","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":"2203.08147","title":"Energy-Latency Attacks via Sponge Poisoning","created":"2022-03-14","cited_by_count":29,"area":null},{"id":"2208.06118","title":"An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers","created":"2022-08-12","cited_by_count":29,"area":null},{"id":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2110.09310","title":"Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention","created":"2021-10-18","cited_by_count":26,"area":null},{"id":"2207.01382","title":"Exploring Lottery Ticket Hypothesis in Spiking Neural Networks","created":"2022-07-04","cited_by_count":26,"area":null},{"id":"2208.11434","title":"YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception","created":"2022-08-24","cited_by_count":26,"area":null},{"id":"2103.01489","title":"Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search","created":"2021-03-02","cited_by_count":24,"area":null},{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23,"area":null},{"id":"2105.01898","title":"CoSA: Scheduling by Constrained Optimization for Spatial Accelerators","created":"2021-05-05","cited_by_count":22,"area":null},{"id":"2306.15552","title":"A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms","created":"2023-06-27","cited_by_count":21,"area":null},{"id":"2107.07983","title":"S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration","created":"2021-07-16","cited_by_count":19,"area":null},{"id":"2103.01548","title":"PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization","created":"2021-03-02","cited_by_count":18,"area":null},{"id":"2402.04744","title":"Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers","created":"2024-02-07","cited_by_count":18,"area":null},{"id":"2501.11211","title":"Ditto: Accelerating Diffusion Model via Temporal Value Similarity","created":"2025-01-20","cited_by_count":18,"area":"diffusion"},{"id":"2205.05826","title":"Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling","created":"2022-05-12","cited_by_count":15,"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":"2307.10705","title":"TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars","created":"2023-07-20","cited_by_count":13,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"id":"2209.00606","title":"Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation","created":"2022-09-01","cited_by_count":12,"area":null},{"id":"2305.12718","title":"HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2205.04702","title":"Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards","created":"2022-05-10","cited_by_count":11,"area":null},{"id":"2102.07511","title":"GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent","created":"2021-02-15","cited_by_count":10,"area":null},{"id":"2108.11033","title":"GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity","created":"2021-08-25","cited_by_count":10,"area":"inference"},{"id":"2305.03888","title":"Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning","created":"2023-05-06","cited_by_count":10,"area":null},{"id":"2105.14070","title":"Accelerating Neural ODEs Using Model Order Reduction","created":"2021-05-28","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":"2302.08687","title":"VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs","created":"2023-02-17","cited_by_count":9,"area":null},{"id":"2501.10658","title":"LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator","created":"2025-01-18","cited_by_count":9,"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":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2304.10618","title":"ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2407.14073","title":"LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks","created":"2024-07-19","cited_by_count":8,"area":null},{"id":"2103.00768","title":"Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2403.18587","title":"The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2407.20421","title":"Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2205.00778","title":"Sparse Compressed Spiking Neural Network Accelerator for Object Detection","created":"2022-05-02","cited_by_count":6,"area":null},{"id":"2203.00158","title":"GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks","created":"2022-03-01","cited_by_count":5,"area":null},{"id":"2207.06613","title":"T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXit","created":"2022-07-14","cited_by_count":5,"area":"inference"},{"id":"2209.08938","title":"Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloud","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2301.10388","title":"SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators","created":"2023-01-25","cited_by_count":5,"area":null},{"id":"2403.16958","title":"TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2103.05600","title":"unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation","created":"2021-03-09","cited_by_count":4,"area":null},{"id":"2110.06155","title":"Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression","created":"2021-10-12","cited_by_count":4,"area":null},{"id":"2110.08828","title":"Compression-aware Projection with Greedy Dimension Reduction for Convolutional Neural Network Activations","created":"2021-10-17","cited_by_count":4,"area":null},{"id":"2204.01460","title":"Optimizing the Consumption of Spiking Neural Networks with Activity Regularization","created":"2022-04-04","cited_by_count":4,"area":null},{"id":"2208.12392","title":"DiVa: An Accelerator for Differentially Private Machine Learning","created":"2022-08-26","cited_by_count":4,"area":null},{"id":"2210.10246","title":"Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction","created":"2022-10-19","cited_by_count":4,"area":null},{"id":"2305.07522","title":"SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2509.10372","title":"MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness","created":"2025-09-12","cited_by_count":4,"area":"inference"},{"id":"2101.04354","title":"Activation Density based Mixed-Precision Quantization for Energy Efficient Neural Networks","created":"2021-01-12","cited_by_count":3,"area":null},{"id":"2103.01705","title":"SME: ReRAM-based Sparse-Multiplication-Engine to Squeeze-Out Bit Sparsity of Neural Network","created":"2021-03-02","cited_by_count":3,"area":null},{"id":"2103.07674","title":"Efficient Sparse Artificial Neural Networks","created":"2021-03-13","cited_by_count":3,"area":null},{"id":"2104.08314","title":"High Performance Convolution Using Sparsity and Patterns for Inference in Deep Convolutional Neural Networks","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2104.08335","title":"Demystifying BERT: Implications for Accelerator Design","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2104.09056","title":"RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imaging","created":"2021-04-19","cited_by_count":3,"area":null},{"id":"2105.01280","title":"VersaGNN: a Versatile accelerator for Graph neural networks","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2105.10554","title":"GNNIE: GNN Inference Engine with Load-balancing and Graph-Specific Caching","created":"2021-05-21","cited_by_count":3,"area":null},{"id":"2105.10832","title":"Spectral Pruning for Recurrent Neural Networks","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2105.14156","title":"SMASH: Sparse Matrix Atomic Scratchpad Hashing","created":"2021-05-29","cited_by_count":3,"area":null},{"id":"2110.14904","title":"MERCURY: Accelerating DNN Training By Exploiting Input Similarity","created":"2021-10-28","cited_by_count":3,"area":null},{"id":"2205.13045","title":"QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2210.11237","title":"Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2307.00368","title":"Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training","created":"2023-07-01","cited_by_count":3,"area":null},{"id":"2307.11128","title":"Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2402.06357","title":"The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks","created":"2024-02-09","cited_by_count":3,"area":null},{"id":"2405.07748","title":"Neural Network Compression for Reinforcement Learning Tasks","created":"2024-05-13","cited_by_count":3,"area":"deeprl"},{"id":"2408.02412","title":"PENDRAM: Enabling High-Performance and Energy-Efficient Processing of Deep Neural Networks through a Generalized DRAM Data Mapping Policy","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2504.14365","title":"Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator","created":"2025-04-19","cited_by_count":3,"area":null},{"id":"2512.00055","title":"KAN-SAs: Efficient Acceleration of Kolmogorov-Arnold Networks on Systolic Arrays","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2106.07894","title":"S2Engine: A Novel Systolic Architecture for Sparse Convolutional Neural Networks","created":"2021-06-15","cited_by_count":2,"area":null},{"id":"2107.07305","title":"Training for temporal sparsity in deep neural networks, application in video processing","created":"2021-07-15","cited_by_count":2,"area":null},{"id":"2109.04925","title":"Rapid Model Architecture Adaption for Meta-Learning","created":"2021-09-10","cited_by_count":2,"area":null},{"id":"2201.07634","title":"FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks","created":"2022-01-19","cited_by_count":2,"area":null},{"id":"2206.15463","title":"QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration","created":"2022-06-30","cited_by_count":2,"area":null},{"id":"2210.03731","title":"Demystifying Map Space Exploration for NPUs","created":"2022-10-07","cited_by_count":2,"area":null},{"id":"2210.15170","title":"Improved Projection Learning for Lower Dimensional Feature Maps","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2306.09552","title":"Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2311.02003","title":"Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2311.07625","title":"Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2404.07821","title":"Sparse Laneformer","created":"2024-04-11","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":"2503.14799","title":"Pruning-Based TinyML Optimization of Machine Learning Models for Anomaly Detection in Electric Vehicle Charging Infrastructure","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2503.21928","title":"An Efficient Training Algorithm for Models with Block-wise Sparsity","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2505.19349","title":"DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2604.18137","title":"AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2107.09408","title":"CREW: Computation Reuse and Efficient Weight Storage for Hardware-accelerated MLPs and RNNs","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2109.07710","title":"Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2202.02310","title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2210.14151","title":"Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing","created":"2022-10-23","cited_by_count":1,"area":null},{"id":"2210.16624","title":"LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning","created":"2022-10-29","cited_by_count":1,"area":null},{"id":"2212.02046","title":"Algorithm and Hardware Co-Design of Energy-Efficient LSTM Networks for Video Recognition with Hierarchical Tucker Tensor Decomposition","created":"2022-12-05","cited_by_count":1,"area":null}],"next_cursor":"100"}