{"total":128,"rows":[{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"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":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2205.07424","title":"Trustworthy Graph Neural Networks: Aspects, Methods and Trends","created":"2022-05-16","cited_by_count":89,"area":null},{"id":"2301.11047","title":"A Systematic Review of Green AI","created":"2023-01-26","cited_by_count":77,"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":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2101.05108","title":"Fast convolutional neural networks on FPGAs with hls4ml","created":"2021-01-13","cited_by_count":42,"area":null},{"id":"2302.03773","title":"What Matters In The Structured Pruning of Generative Language Models?","created":"2023-02-07","cited_by_count":30,"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":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2110.08232","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2112.09852","title":"LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision","created":"2021-12-18","cited_by_count":20,"area":null},{"id":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2203.02202","title":"Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis","created":"2022-03-04","cited_by_count":18,"area":null},{"id":"2312.09610","title":"A Synthesis of Green Architectural Tactics for ML-Enabled Systems","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2303.13972","title":"Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI","created":"2023-03-24","cited_by_count":16,"area":null},{"id":"2204.13784","title":"AGIC: Approximate Gradient Inversion Attack on Federated Learning","created":"2022-04-28","cited_by_count":15,"area":null},{"id":"2308.10438","title":"Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks","created":"2023-08-21","cited_by_count":15,"area":null},{"id":"2110.05607","title":"Partial Variable Training for Efficient On-Device Federated Learning","created":"2021-10-11","cited_by_count":14,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2106.12718","title":"Sparse Flows: Pruning Continuous-depth Models","created":"2021-06-24","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":"2309.02065","title":"Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2403.07094","title":"FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2201.05842","title":"UDC: Unified DNAS for Compressible TinyML Models","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2411.01800","title":"Expanding Sparse Tuning for Low Memory Usage","created":"2024-11-04","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":"2306.05857","title":"How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective","created":"2023-06-09","cited_by_count":9,"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":"2308.04637","title":"Sparse Binary Transformers for Multivariate Time Series Modeling","created":"2023-08-09","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":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2205.03494","title":"Online Model Compression for Federated Learning with Large Models","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","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":"2103.03483","title":"Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2104.07521","title":"QuickLoc: Adaptive Deep-Learning for Fast Indoor Localization with Mobile Devices","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2202.01341","title":"Robust Binary Models by Pruning Randomly-initialized Networks","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2308.12264","title":"Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement","created":"2023-08-23","cited_by_count":5,"area":null},{"id":"2412.14714","title":"Holistic Adversarially Robust Pruning","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2203.03794","title":"YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2406.14328","title":"Computing Within Limits: An Empirical Study of Energy Consumption in ML Training and Inference","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2509.17968","title":"Visual Detector Compression via Location-Aware Discriminant Analysis","created":"2025-09-22","cited_by_count":4,"area":null},{"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":"2110.14871","title":"Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks","created":"2021-10-28","cited_by_count":3,"area":null},{"id":"2204.05566","title":"Compact Model Training by Low-Rank Projection with Energy Transfer","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2212.12770","title":"COLT: Cyclic Overlapping Lottery Tickets for Faster Pruning of Convolutional Neural Networks","created":"2022-12-24","cited_by_count":3,"area":null},{"id":"2303.15953","title":"Randomly Initialized Subnetworks with Iterative Weight Recycling","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2305.17305","title":"DynaShare: Task and Instance Conditioned Parameter Sharing for Multi-Task Learning","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2101.09225","title":"Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence","created":"2021-01-22","cited_by_count":2,"area":null},{"id":"2102.02804","title":"A Deeper Look into Convolutions via Eigenvalue-based Pruning","created":"2021-02-04","cited_by_count":2,"area":null},{"id":"2204.05274","title":"MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning","created":"2022-04-11","cited_by_count":2,"area":null},{"id":"2205.15062","title":"A Transistor Operations Model for Deep Learning Energy Consumption Scaling Law","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2207.01260","title":"CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2211.03741","title":"AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2302.10483","title":"Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2306.16869","title":"NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2310.11131","title":"FROST: Towards Energy-efficient AI-on-5G Platforms -- A GPU Power Capping Evaluation","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2311.07427","title":"Boolean Variation and Boolean Logic BackPropagation","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2401.16694","title":"EdgeOL: Efficient in-situ Online Learning on Edge Devices","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2402.03142","title":"Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2405.09600","title":"Aggregate Representation Measure for Predictive Model Reusability","created":"2024-05-15","cited_by_count":2,"area":null},{"id":"2503.23934","title":"Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2101.09693","title":"A2P-MANN: Adaptive Attention Inference Hops Pruned Memory-Augmented Neural Networks","created":"2021-01-24","cited_by_count":1,"area":null},{"id":"2101.11800","title":"AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications","created":"2021-01-28","cited_by_count":1,"area":null},{"id":"2103.12896","title":"SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2108.12914","title":"Leveraging Transprecision Computing for Machine Vision Applications at the Edge","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2109.12584","title":"Curb Your Carbon Emissions: Benchmarking Carbon Emissions in Machine Translation","created":"2021-09-26","cited_by_count":1,"area":null},{"id":"2111.02399","title":"Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2112.00324","title":"Optimizing for In-memory Deep Learning with Emerging Memory Technology","created":"2021-12-01","cited_by_count":1,"area":null},{"id":"2206.12191","title":"Computational Complexity Evaluation of Neural Network Applications in Signal Processing","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2210.13554","title":"Weight Fixing Networks","created":"2022-10-24","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":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2505.07317","title":"How Do Companies Manage the Environmental Sustainability of AI? An Interview Study About Green AI Efforts and Regulations","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2505.14234","title":"Fast, close, non-singular and property-preserving approximations of entropic measures","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.15090","title":"DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2510.24037","title":"Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2601.22141","title":"Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2101.00717","title":"Algorithmic Complexities in Backpropagation and Tropical Neural Networks","created":"2021-01-03","cited_by_count":0,"area":null},{"id":"2101.01163","title":"SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2103.08031","title":"BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks","created":"2021-03-14","cited_by_count":0,"area":null},{"id":"2105.02954","title":"Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classification","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2105.11848","title":"DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications","created":"2021-05-25","cited_by_count":0,"area":null},{"id":"2106.08301","title":"Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2106.10617","title":"Cogradient Descent for Dependable Learning","created":"2021-06-20","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":"2107.07706","title":"DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference","created":"2021-07-16","cited_by_count":0,"area":null},{"id":"2108.01192","title":"MOHAQ: Multi-Objective Hardware-Aware Quantization of Recurrent Neural Networks","created":"2021-08-02","cited_by_count":0,"area":null},{"id":"2109.00170","title":"Architecture Aware Latency Constrained Sparse Neural Networks","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2201.08830","title":"APack: Off-Chip, Lossless Data Compression for Efficient Deep Learning Inference","created":"2022-01-21","cited_by_count":0,"area":null},{"id":"2204.09797","title":"Multiply-and-Fire (MNF): An Event-driven Sparse Neural Network Accelerator","created":"2022-04-20","cited_by_count":0,"area":null},{"id":"2206.07649","title":"Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks","created":"2022-06-14","cited_by_count":0,"area":null}],"next_cursor":"100"}