{"total":59,"rows":[{"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":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2105.05720","title":"Breaking the Computation and Communication Abstraction Barrier in Distributed Machine Learning Workloads","created":"2021-05-12","cited_by_count":40,"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":"2110.10486","title":"A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays","created":"2021-10-20","cited_by_count":37,"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":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2205.13603","title":"Tensor Program Optimization with Probabilistic Programs","created":"2022-05-26","cited_by_count":30,"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":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20,"area":null},{"id":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","cited_by_count":19,"area":null},{"id":"2104.01481","title":"Do We Need Anisotropic Graph Neural Networks?","created":"2021-04-03","cited_by_count":18,"area":null},{"id":"2103.10255","title":"Equivariant Filters for Efficient Tracking in 3D Imaging","created":"2021-03-18","cited_by_count":17,"area":null},{"id":"2110.10221","title":"The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding","created":"2021-10-19","cited_by_count":17,"area":null},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2211.03578","title":"TLP: A Deep Learning-based Cost Model for Tensor Program Tuning","created":"2022-11-07","cited_by_count":14,"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":"2203.01877","title":"Query Processing on Tensor Computation Runtimes","created":"2022-03-03","cited_by_count":12,"area":null},{"id":"2205.10364","title":"Learning to Reverse DNNs from AI Programs Automatically","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2112.01955","title":"Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion","created":"2021-12-03","cited_by_count":11,"area":null},{"id":"2101.08458","title":"UNIT: Unifying Tensorized Instruction Compilation","created":"2021-01-21","cited_by_count":10,"area":null},{"id":"2202.09947","title":"Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation","created":"2022-02-21","cited_by_count":10,"area":null},{"id":"2102.04199","title":"MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks","created":"2021-02-08","cited_by_count":9,"area":null},{"id":"2104.09455","title":"Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs","created":"2021-04-19","cited_by_count":9,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2301.13062","title":"Operator Fusion in XLA: Analysis and Evaluation","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2111.11581","title":"Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2203.05759","title":"Federated Remote Physiological Measurement with Imperfect Data","created":"2022-03-11","cited_by_count":7,"area":null},{"id":"2206.02845","title":"On Efficient Approximate Queries over Machine Learning Models","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2202.05048","title":"Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment","created":"2022-02-10","cited_by_count":6,"area":null},{"id":"2204.09514","title":"Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2104.13732","title":"A Reinforcement Learning Environment for Polyhedral Optimizations","created":"2021-04-28","cited_by_count":5,"area":null},{"id":"2111.14247","title":"A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities","created":"2021-11-28","cited_by_count":5,"area":null},{"id":"2202.09113","title":"How to Manage Tiny Machine Learning at Scale: An Industrial Perspective","created":"2022-02-18","cited_by_count":5,"area":null},{"id":"2201.05752","title":"Moses: Efficient Exploitation of Cross-device Transferable Features for Tensor Program Optimization","created":"2022-01-15","cited_by_count":3,"area":null},{"id":"2211.00471","title":"Exploring Effects of Computational Parameter Changes to Image Recognition Systems","created":"2022-11-01","cited_by_count":3,"area":null},{"id":"2302.04430","title":"A Comparison of Decision Forest Inference Platforms from A Database Perspective","created":"2023-02-09","cited_by_count":3,"area":null},{"id":"2101.06371","title":"NNStreamer: Efficient and Agile Development of On-Device AI Systems","created":"2021-01-16","cited_by_count":2,"area":null},{"id":"2103.14949","title":"Automated Backend-Aware Post-Training Quantization","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2106.09180","title":"RHNAS: Realizable Hardware and Neural Architecture Search","created":"2021-06-17","cited_by_count":2,"area":null},{"id":"2108.12489","title":"Using Graph Neural Networks to model the performance of Deep Neural Networks","created":"2021-08-27","cited_by_count":2,"area":null},{"id":"2110.06037","title":"SoftNeuro: Fast Deep Inference using Multi-platform Optimization","created":"2021-10-12","cited_by_count":2,"area":null},{"id":"2210.04323","title":"Deep Learning Inference Frameworks Benchmark","created":"2022-10-09","cited_by_count":2,"area":null},{"id":"2303.17878","title":"Fused Depthwise Tiling for Memory Optimization in TinyML Deep Neural Network Inference","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2106.08846","title":"Algorithm to Compilation Co-design: An Integrated View of Neural Network Sparsity","created":"2021-06-16","cited_by_count":1,"area":null},{"id":"2201.09210","title":"Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs","created":"2022-01-23","cited_by_count":1,"area":null},{"id":"2204.10183","title":"Multi-Component Optimization and Efficient Deployment of Neural-Networks on Resource-Constrained IoT Hardware","created":"2022-04-20","cited_by_count":1,"area":null},{"id":"2205.10940","title":"Toward smart composites: small-scale, untethered prediction and control for soft sensor/actuator systems","created":"2022-05-22","cited_by_count":1,"area":null},{"id":"2205.14465","title":"ByteComp: Revisiting Gradient Compression in Distributed Training","created":"2022-05-28","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":"2212.07936","title":"A Study on the Intersection of GPU Utilization and CNN Inference","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2304.05430","title":"Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2110.14819","title":"Characterizing and Taming Resolution in Convolutional Neural Networks","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2206.00402","title":"NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural Networks","created":"2022-06-01","cited_by_count":0,"area":null},{"id":"2208.08711","title":"L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2305.08872","title":"AMULET: Adaptive Matrix-Multiplication-Like Tasks","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2306.13474","title":"Efficient Online Processing with Deep Neural Networks","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2306.15656","title":"SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design","created":"2023-06-27","cited_by_count":0,"area":null}],"next_cursor":null}