{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/model-compression/papers/12","list_of":"/task/model-compression","task":"Model Compression","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":12,"pages_in_order":14,"rows_per_page":100,"rows":[1101,1200],"of":1356,"counts":{"archive_papers_tagged":1356,"with_a_code_link":440,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":1356,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":97,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":97,"listed_every_run_a_failure_of_syntologys_instrument":22,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/model-compression","prev":"/task/model-compression/papers/11","next":"/task/model-compression/papers/13","papers":[{"url":"/paper/context-aware-deep-model-compression-for-edge","slug":"context-aware-deep-model-compression-for-edge","title":"Context-aware deep model compression for edge cloud computing","date":"2020-11-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-graph-encoder-decoder-for-model","title":"Auto Graph Encoder-Decoder for Neural Network Pruning","date":"2020-11-25","arxiv_id":"2011.12641","repositories_listed":0,"syntology":null},{"url":null,"slug":"bringing-ai-to-edge-from-deep-learning-s","title":"Bringing AI To Edge: From Deep Learning's Perspective","date":"2020-11-25","arxiv_id":"2011.14808","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-in-school-multi-teacher-knowledge","title":"MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing","date":"2020-11-19","arxiv_id":"2011.09899","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-model-compression-by-jointly","title":"Automated Model Compression by Jointly Applied Pruning and Quantization","date":"2020-11-12","arxiv_id":"2011.06231","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-via-sparse","title":"Neural Network Compression Via Sparse Optimization","date":"2020-11-10","arxiv_id":"2011.04868","repositories_listed":0,"syntology":null},{"url":null,"slug":"stage-wise-channel-pruning-for-model","title":"Effective Model Compression via Stage-wise Pruning","date":"2020-11-10","arxiv_id":"2011.04908","repositories_listed":0,"syntology":null},{"url":null,"slug":"know-what-you-don-t-need-single-shot-meta","title":"Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads","date":"2020-11-07","arxiv_id":"2011.03770","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-boundaries-of-low-resource-bert","title":"Exploring the Boundaries of Low-Resource BERT Distillation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"watermarking-graph-neural-networks-by-random","title":"Watermarking Graph Neural Networks by Random Graphs","date":"2020-11-01","arxiv_id":"2011.00512","repositories_listed":0,"syntology":null},{"url":null,"slug":"activation-map-adaptation-for-effective","title":"Activation Map Adaptation for Effective Knowledge Distillation","date":"2020-10-26","arxiv_id":"2010.13500","repositories_listed":0,"syntology":null},{"url":null,"slug":"mars-multi-macro-architecture-sram-cim-based","title":"MARS: Multi-macro Architecture SRAM CIM-Based Accelerator with Co-designed Compressed Neural Networks","date":"2020-10-24","arxiv_id":"2010.12861","repositories_listed":0,"syntology":null},{"url":null,"slug":"autobss-an-efficient-algorithm-for-block","title":"AutoBSS: An Efficient Algorithm for Block Stacking Style Search","date":"2020-10-20","arxiv_id":"2010.10261","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-in-wide-neural","title":"Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher","date":"2020-10-20","arxiv_id":"2010.10090","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisy-neural-network-compression-for-analog","title":"Noisy Neural Network Compression for Analog Storage Devices","date":"2020-10-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"closed-loop-neural-interfaces-with-embedded","title":"Closed-Loop Neural Interfaces with Embedded Machine Learning","date":"2020-10-15","arxiv_id":"2010.09457","repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-squeezing-reparameterization-for","title":"Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression","date":"2020-10-14","arxiv_id":"2010.06993","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-compression-method-with-matrix","title":"A Model Compression Method with Matrix Product Operators for Speech Enhancement","date":"2020-10-10","arxiv_id":"2010.04950","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-deep-convolutional-neural","title":"Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters","date":"2020-10-06","arxiv_id":"2010.02778","repositories_listed":0,"syntology":null},{"url":null,"slug":"gecko-reconciling-privacy-accuracy-and","title":"GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning","date":"2020-10-02","arxiv_id":"2010.00912","repositories_listed":0,"syntology":null},{"url":null,"slug":"pea-kd-parameter-efficient-and-accurate","title":"Pea-KD: Parameter-efficient and Accurate Knowledge Distillation on BERT","date":"2020-09-30","arxiv_id":"2009.14822","repositories_listed":0,"syntology":null},{"url":null,"slug":"pea-kd-parameter-efficient-and-accurate-1","title":"Pea-KD: Parameter-efficient and accurate Knowledge Distillation","date":"2020-09-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-automated-channel-pruning-for","title":"Conditional Automated Channel Pruning for Deep Neural Networks","date":"2020-09-21","arxiv_id":"2009.09724","repositories_listed":0,"syntology":null},{"url":null,"slug":"msp-an-fpga-specific-mixed-scheme-multi","title":"MSP: An FPGA-Specific Mixed-Scheme, Multi-Precision Deep Neural Network Quantization Framework","date":"2020-09-16","arxiv_id":"2009.07460","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-progressive-sub-network-searching-framework","title":"A Progressive Sub-Network Searching Framework for Dynamic Inference","date":"2020-09-11","arxiv_id":"2009.05681","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-partial-regularization-method-for-network","title":"A Partial Regularization Method for Network Compression","date":"2020-09-03","arxiv_id":"2009.01395","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-specific-optimization-for-mixed-data","title":"Layer-specific Optimization for Mixed Data Flow with Mixed Precision in FPGA Design for CNN-based Object Detectors","date":"2020-09-03","arxiv_id":"2009.01588","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcmia-model-compression-against-membership","title":"Against Membership Inference Attack: Pruning is All You Need","date":"2020-08-28","arxiv_id":"2008.13578","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-weight-bitwidth-to-rule-them-all","title":"One Weight Bitwidth to Rule Them All","date":"2020-08-22","arxiv_id":"2008.09916","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-independent-structured-pruning-of-neural","title":"Data-Independent Structured Pruning of Neural Networks via Coresets","date":"2020-08-19","arxiv_id":"2008.08316","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-channel-pruning-using-hierarchical","title":"Cascaded channel pruning using hierarchical self-distillation","date":"2020-08-16","arxiv_id":"2008.06814","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-modality-transferable-visual","title":"Towards Modality Transferable Visual Information Representation with Optimal Model Compression","date":"2020-08-13","arxiv_id":"2008.05642","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-tensor-learning-with-tensor-networks","title":"Adaptive Learning of Tensor Network Structures","date":"2020-08-12","arxiv_id":"2008.05437","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-compression-of-end-to-end-asr-model","title":"Iterative Compression of End-to-End ASR Model using AutoML","date":"2020-08-06","arxiv_id":"2008.02897","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-convolutions-for-efficient-neural","title":"Structured Convolutions for Efficient Neural Network Design","date":"2020-08-06","arxiv_id":"2008.02454","repositories_listed":0,"syntology":null},{"url":null,"slug":"tutornet-towards-flexible-knowledge","title":"TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition","date":"2020-08-03","arxiv_id":"2008.00671","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-feature-aggregation-search-for","title":"Differentiable Feature Aggregation Search for Knowledge Distillation","date":"2020-08-02","arxiv_id":"2008.00506","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-deep-neural-networks-via-layer","title":"Compressing Deep Neural Networks via Layer Fusion","date":"2020-07-29","arxiv_id":"2007.14917","repositories_listed":0,"syntology":null},{"url":null,"slug":"alf-autoencoder-based-low-rank-filter-sharing","title":"ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks","date":"2020-07-27","arxiv_id":"2007.13384","repositories_listed":0,"syntology":null},{"url":null,"slug":"achieving-real-time-execution-of-3d","title":"RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices","date":"2020-07-20","arxiv_id":"2007.09835","repositories_listed":0,"syntology":null},{"url":null,"slug":"ftrans-energy-efficient-acceleration-of","title":"FTRANS: Energy-Efficient Acceleration of Transformers using FPGA","date":"2020-07-16","arxiv_id":"2007.08563","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-transfer-by-optimal-transport","title":"Representation Transfer by Optimal Transport","date":"2020-07-13","arxiv_id":"2007.06737","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-prune-deep-neural-networks-via-2","title":"Learning to Prune Deep Neural Networks via Reinforcement Learning","date":"2020-07-09","arxiv_id":"2007.04756","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-labeling-affects-out-of-distribution","title":"Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks","date":"2020-07-07","arxiv_id":"2007.03212","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-beyond-model","title":"Knowledge Distillation Beyond Model Compression","date":"2020-07-03","arxiv_id":"2007.01922","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-compression-rethinking-information","title":"Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture","date":"2020-07-02","arxiv_id":"2007.01696","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-limits-of-simple-learners-in","title":"Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"go-wide-then-narrow-efficient-training-of","title":"Go Wide, Then Narrow: Efficient Training of Deep Thin Networks","date":"2020-07-01","arxiv_id":"2007.00811","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-demystification-of-knowledge","title":"On the Demystification of Knowledge Distillation: A Residual Network Perspective","date":"2020-06-30","arxiv_id":"2006.16589","repositories_listed":0,"syntology":null},{"url":null,"slug":"pfgdf-pruning-filter-via-gaussian","title":"PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration","date":"2020-06-23","arxiv_id":"2006.12963","repositories_listed":0,"syntology":null},{"url":null,"slug":"additive-tree-structured-covariance-function","title":"Additive Tree-Structured Covariance Function for Conditional Parameter Spaces in Bayesian Optimization","date":"2020-06-21","arxiv_id":"2006.11771","repositories_listed":0,"syntology":null},{"url":null,"slug":"resot-resource-efficient-oblique-trees-for","title":"ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification","date":"2020-06-14","arxiv_id":"2006.07900","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-model-pruning-with-feedback-1","title":"Dynamic Model Pruning with Feedback","date":"2020-06-12","arxiv_id":"2006.07253","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-embedded-deep-learning-object-detection","title":"An Embedded Deep Learning Object Detection Model For Traffic In Asian Countries","date":"2020-06-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-a-survey","title":"Knowledge Distillation: A Survey","date":"2020-06-09","arxiv_id":"2006.05525","repositories_listed":0,"syntology":null},{"url":null,"slug":"adadeep-a-usage-driven-automated-deep-model","title":"AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles","date":"2020-06-08","arxiv_id":"2006.04432","repositories_listed":0,"syntology":null},{"url":null,"slug":"edcompress-energy-aware-model-compression","title":"EDCompress: Energy-Aware Model Compression for Dataflows","date":"2020-06-08","arxiv_id":"2006.04588","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-neural-network-compression","title":"An Overview of Neural Network Compression","date":"2020-06-05","arxiv_id":"2006.03669","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-model-compression-with-resource","title":"Discrete Model Compression With Resource Constraint for Deep Neural Networks","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-dimensional-pruning-a-unified-framework","title":"Multi-Dimensional Pruning: A Unified Framework for Model Compression","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-squeezing-reparameterization-for-1","title":"Weight Squeezing: Reparameterization for Compression and Fast Inference","date":"2020-05-30","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-non-linear-redundancy-for-neural","title":"Exploiting Non-Linear Redundancy for Neural Model Compression","date":"2020-05-28","arxiv_id":"2005.14070","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-recurrent-neural-networks-using","title":"Compressing Recurrent Neural Networks Using Hierarchical Tucker Tensor Decomposition","date":"2020-05-09","arxiv_id":"2005.04366","repositories_listed":0,"syntology":null},{"url":null,"slug":"pruning-algorithms-to-accelerate","title":"Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey","date":"2020-05-08","arxiv_id":"2005.04275","repositories_listed":0,"syntology":null},{"url":null,"slug":"smartexchange-trading-higher-cost-memory","title":"SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation","date":"2020-05-07","arxiv_id":"2005.03403","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-spikes-knowledge-distillation-in","title":"Distilling Spikes: Knowledge Distillation in Spiking Neural Networks","date":"2020-05-01","arxiv_id":"2005.00288","repositories_listed":0,"syntology":null},{"url":null,"slug":"streamlining-tensor-and-network-pruning-in","title":"Streamlining Tensor and Network Pruning in PyTorch","date":"2020-04-28","arxiv_id":"2004.13770","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-testing-of-low-dimensional-functions","title":"Robust testing of low-dimensional functions","date":"2020-04-24","arxiv_id":"2004.11642","repositories_listed":0,"syntology":null},{"url":null,"slug":"permdnn-efficient-compressed-dnn-architecture","title":"PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices","date":"2020-04-23","arxiv_id":"2004.10936","repositories_listed":0,"syntology":null},{"url":null,"slug":"lottery-hypothesis-based-unsupervised-pre","title":"Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning","date":"2020-04-21","arxiv_id":"2004.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepsdf-x-sim-3-extending-deepsdf-for","title":"Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation","date":"2020-04-20","arxiv_id":"2004.09048","repositories_listed":0,"syntology":null},{"url":null,"slug":"genecai-genetic-evolution-for-acquiring","title":"GeneCAI: Genetic Evolution for Acquiring Compact AI","date":"2020-04-08","arxiv_id":"2004.04249","repositories_listed":0,"syntology":null},{"url":null,"slug":"ladabert-lightweight-adaptation-of-bert","title":"LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression","date":"2020-04-08","arxiv_id":"2004.04124","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-two-challenges-of-6d-object-pose","title":"Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images","date":"2020-03-27","arxiv_id":"2003.12344","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-contextual-embeddings","title":"A Survey on Contextual Embeddings","date":"2020-03-16","arxiv_id":"2003.07278","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-privacy-preserving-dnn-pruning-and-mobile","title":"A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework","date":"2020-03-13","arxiv_id":"2003.06513","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-graph-embedding-with-limited-labeled","title":"Learning by Sampling and Compressing: Efficient Graph Representation Learning with Extremely Limited Annotations","date":"2020-03-13","arxiv_id":"2003.06100","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-via-adaptive-instance","title":"Knowledge distillation via adaptive instance normalization","date":"2020-03-09","arxiv_id":"2003.04289","repositories_listed":0,"syntology":null},{"url":null,"slug":"pacemaker-intermediate-teacher-knowledge","title":"Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network","date":"2020-03-09","arxiv_id":"2003.03944","repositories_listed":0,"syntology":null},{"url":"/paper/adaptive-neural-connections-for-sparsity","slug":"adaptive-neural-connections-for-sparsity","title":"Adaptive Neural Connections for Sparsity Learning","date":"2020-03-05","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-method-of-training-small-models","title":"An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation","date":"2020-02-28","arxiv_id":"2002.12597","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-large-scale-transformer-based","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","date":"2020-02-27","arxiv_id":"2002.11985","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-knowledge-distillation","title":"Residual Knowledge Distillation","date":"2020-02-21","arxiv_id":"2002.09168","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-cost-and-benefit-with-tied-multi-1","title":"Balancing Cost and Benefit with Tied-Multi Transformers","date":"2020-02-20","arxiv_id":"2002.08614","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-aware-convolutional-neural","title":"Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs","date":"2020-02-20","arxiv_id":"2002.08697","repositories_listed":0,"syntology":null},{"url":null,"slug":"pcnn-pattern-based-fine-grained-regular","title":"PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators","date":"2020-02-11","arxiv_id":"2002.04997","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-improving-knowledge","title":"Understanding and Improving Knowledge Distillation","date":"2020-02-10","arxiv_id":"2002.03532","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-convolutional-representations-for","title":"Lightweight Convolutional Representations for On-Device Natural Language Processing","date":"2020-02-04","arxiv_id":"2002.01535","repositories_listed":0,"syntology":null},{"url":null,"slug":"search-for-better-students-to-learn-distilled","title":"Search for Better Students to Learn Distilled Knowledge","date":"2020-01-30","arxiv_id":"2001.11612","repositories_listed":0,"syntology":null},{"url":null,"slug":"mt-bioner-multi-task-learning-for-biomedical","title":"MT-BioNER: Multi-task Learning for Biomedical Named Entity Recognition using Deep Bidirectional Transformers","date":"2020-01-24","arxiv_id":"2001.08904","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-accurate-and-fast-vehicle-re-id-on-the","title":"Small, Accurate, and Fast Vehicle Re-ID on the Edge: the SAFR Approach","date":"2020-01-24","arxiv_id":"2001.08895","repositories_listed":0,"syntology":null},{"url":null,"slug":"ss-auto-a-single-shot-automatic-structured","title":"SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency","date":"2020-01-23","arxiv_id":"2001.08839","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-network-pruning-network-approach-to-deep","title":"A \"Network Pruning Network\" Approach to Deep Model Compression","date":"2020-01-15","arxiv_id":"2001.05545","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-architecture-compression","title":"Differentiable Architecture Compression","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fedboost-a-communication-efficient-algorithm","title":"FedBoost: A Communication-Efficient Algorithm for Federated Learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"patdnn-achieving-real-time-dnn-execution-on","title":"PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning","date":"2020-01-01","arxiv_id":"2001.00138","repositories_listed":0,"syntology":null},{"url":null,"slug":"degan-data-enriching-gan-for-retrieving","title":"DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier","date":"2019-12-27","arxiv_id":"1912.11960","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-regularization-for-spectral","title":"Domain Adaptation Regularization for Spectral Pruning","date":"2019-12-26","arxiv_id":"1912.11853","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-building-a-real-time-mobile-device","title":"Towards Building a Real Time Mobile Device Bird Counting System Through Synthetic Data Training and Model Compression","date":"2019-12-15","arxiv_id":"1912.07106","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improving-framework-of-regularization-for","title":"An Improving Framework of regularization for Network Compression","date":"2019-12-11","arxiv_id":"1912.05078","repositories_listed":0,"syntology":null}],"record_sha256":"be85174a2b5ad75438741444ea5e64748a896ea712e717f8a5bf91ad63e1d2e6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}