{"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/13","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":13,"pages_in_order":14,"rows_per_page":100,"rows":[1201,1300],"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/12","next":"/task/model-compression/papers/14","papers":[{"url":null,"slug":"explaining-sequence-level-knowledge","title":"Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation","date":"2019-12-06","arxiv_id":"1912.03334","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-model-compression-via-deep-reinforcement","title":"Deep Model Compression Via Two-Stage Deep Reinforcement Learning","date":"2019-12-04","arxiv_id":"1912.02254","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-knowledge-within-methods-for-data-free","title":"The Knowledge Within: Methods for Data-Free Model Compression","date":"2019-12-03","arxiv_id":"1912.01274","repositories_listed":0,"syntology":null},{"url":null,"slug":"pruning-at-a-glance-global-neural-pruning-for","title":"Pruning at a Glance: Global Neural Pruning for Model Compression","date":"2019-11-30","arxiv_id":"1912.00200","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-distributed-online","title":"Communication-Efficient Distributed Online Learning with Kernels","date":"2019-11-28","arxiv_id":"1911.12899","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-compression-of-convolutional","title":"Data-Driven Compression of Convolutional Neural Networks","date":"2019-11-28","arxiv_id":"1911.12740","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-multi-hashing-for-model","title":"Structured Multi-Hashing for Model Compression","date":"2019-11-25","arxiv_id":"1911.11177","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sot-mram-based-processing-in-memory-engine","title":"A SOT-MRAM-based Processing-In-Memory Engine for Highly Compressed DNN Implementation","date":"2019-11-24","arxiv_id":"1912.05416","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-pruning-for-model-compression","title":"Graph Pruning for Model Compression","date":"2019-11-22","arxiv_id":"1911.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"darb-a-density-aware-regular-block-pruning","title":"DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks","date":"2019-11-19","arxiv_id":"1911.08020","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-low-precision-training-without","title":"Distributed Low Precision Training Without Mixed Precision","date":"2019-11-18","arxiv_id":"1911.07384","repositories_listed":0,"syntology":null},{"url":null,"slug":"ascai-adaptive-sampling-for-acquiring-compact","title":"ASCAI: Adaptive Sampling for acquiring Compact AI","date":"2019-11-15","arxiv_id":"1911.06471","repositories_listed":0,"syntology":null},{"url":null,"slug":"subcharacter-chinese-english-neural-machine","title":"SubCharacter Chinese-English Neural Machine Translation with Wubi encoding","date":"2019-11-07","arxiv_id":"1911.02737","repositories_listed":0,"syntology":null},{"url":null,"slug":"localization-aware-channel-pruning-for-object","title":"Localization-aware Channel Pruning for Object Detection","date":"2019-11-06","arxiv_id":"1911.02237","repositories_listed":0,"syntology":null},{"url":null,"slug":"locality-sensitive-hashing-for-f-divergences","title":"Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond","date":"2019-10-28","arxiv_id":"1910.12414","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-channel-intragroup-sparsity-neural","title":"Cross-Channel Intragroup Sparsity Neural Network","date":"2019-10-26","arxiv_id":"1910.11971","repositories_listed":0,"syntology":null},{"url":null,"slug":"lprnet-lightweight-deep-network-by-low-rank","title":"LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution","date":"2019-10-25","arxiv_id":"1910.11853","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-with-two-stage-multi","title":"Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System","date":"2019-10-18","arxiv_id":"1910.08381","repositories_listed":0,"syntology":null},{"url":null,"slug":"pruning-a-bert-based-question-answering-model","title":"Structured Pruning of a BERT-based Question Answering Model","date":"2019-10-14","arxiv_id":"1910.06360","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-sparsification-for-deep-neural","title":"Differentiable Sparsification for Deep Neural Networks","date":"2019-10-08","arxiv_id":"1910.03201","repositories_listed":0,"syntology":null},{"url":null,"slug":"req-yolo-a-resource-aware-efficient","title":"REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs","date":"2019-09-29","arxiv_id":"1909.13396","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-encoding-for-deep-learning","title":"Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning","date":"2019-09-27","arxiv_id":"1909.12982","repositories_listed":0,"syntology":null},{"url":null,"slug":"atomic-compression-networks","title":"Atomic Compression Networks","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-specialization-generalization-and","title":"Balancing Specialization, Generalization, and Compression for Detection and Tracking","date":"2019-09-25","arxiv_id":"1909.11348","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupling-weight-regularization-from-batch","title":"Decoupling Weight Regularization from Batch Size for Model Compression","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","repositories_listed":0,"syntology":null},{"url":null,"slug":"gq-net-training-quantization-friendly-deep","title":"GQ-Net: Training Quantization-Friendly Deep Networks","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"network-pruning-for-low-rank-binary-index","title":"Network Pruning for Low-Rank Binary Index","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-mask-pruning-for-neural","title":"Differentiable Mask for Pruning Convolutional and Recurrent Networks","date":"2019-09-10","arxiv_id":"1909.04567","repositories_listed":0,"syntology":null},{"url":null,"slug":"pconv-the-missing-but-desirable-sparsity-in","title":"PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices","date":"2019-09-06","arxiv_id":"1909.05073","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effectiveness-of-low-rank-matrix","title":"On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression","date":"2019-08-27","arxiv_id":"1908.09982","repositories_listed":0,"syntology":null},{"url":null,"slug":"tiny-but-accurate-a-pruned-quantized-and","title":"Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation","date":"2019-08-27","arxiv_id":"1908.10017","repositories_listed":0,"syntology":null},{"url":null,"slug":"190807985","title":"MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors","date":"2019-08-21","arxiv_id":"1908.07985","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-algorithms-and-generators-for","title":"Tuning Algorithms and Generators for Efficient Edge Inference","date":"2019-07-31","arxiv_id":"1908.02239","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-and-communication-aware-model","title":"Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT","date":"2019-07-26","arxiv_id":"1907.11804","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-model-compression-via-filter-auto","title":"Neural Epitome Search for Architecture-Agnostic Network Compression","date":"2019-07-12","arxiv_id":"1907.05642","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-activation-function-coresets-for-network","title":"Data-Independent Neural Pruning via Coresets","date":"2019-07-09","arxiv_id":"1907.04018","repositories_listed":0,"syntology":null},{"url":null,"slug":"shrinkml-end-to-end-asr-model-compression","title":"ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning","date":"2019-07-08","arxiv_id":"1907.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoslim-an-automatic-dnn-structured-pruning","title":"AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates","date":"2019-07-06","arxiv_id":"1907.03141","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-structured-dnn-weight-pruning-considered","title":"Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?","date":"2019-07-03","arxiv_id":"1907.02124","repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-normalization-based-quantization-for","title":"Weight Normalization based Quantization for Deep Neural Network Compression","date":"2019-07-01","arxiv_id":"1907.00593","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-pruning-on-activations-and-weights-for","title":"Joint Regularization on Activations and Weights for Efficient Neural Network Pruning","date":"2019-06-19","arxiv_id":"1906.07875","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-by-entropy-penalized","title":"Scalable Model Compression by Entropy Penalized Reparameterization","date":"2019-06-15","arxiv_id":"1906.06624","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconciling-utility-and-membership-privacy","title":"Membership Privacy for Machine Learning Models Through Knowledge Transfer","date":"2019-06-15","arxiv_id":"1906.06589","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-learning-require-memorization-a-short","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","date":"2019-06-12","arxiv_id":"1906.05271","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-implosion-effective-model-compression","title":"Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining","date":"2019-06-10","arxiv_id":"1906.03826","repositories_listed":0,"syntology":null},{"url":null,"slug":"190600619","title":"Deep Face Recognition Model Compression via Knowledge Transfer and Distillation","date":"2019-06-03","arxiv_id":"1906.00619","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-model-compression-by","title":"Cross Domain Model Compression by Structurally Weight Sharing","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-precision-quantized-neural-networks-via","title":"Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1","date":"2019-05-31","arxiv_id":"1905.13389","repositories_listed":0,"syntology":null},{"url":null,"slug":"hadanets-flexible-quantization-strategies-for","title":"HadaNets: Flexible Quantization Strategies for Neural Networks","date":"2019-05-26","arxiv_id":"1905.10759","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-low-rank-approximation-for-cnns","title":"Learning Low-Rank Approximation for CNNs","date":"2019-05-24","arxiv_id":"1905.10145","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-compression-by-unstructured","title":"Structured Compression by Weight Encryption for Unstructured Pruning and Quantization","date":"2019-05-24","arxiv_id":"1905.10138","repositories_listed":0,"syntology":null},{"url":null,"slug":"darc-differentiable-architecture-compression","title":"DARC: Differentiable ARchitecture Compression","date":"2019-05-20","arxiv_id":"1905.08170","repositories_listed":0,"syntology":null},{"url":null,"slug":"dream-distillation-a-data-independent-model","title":"Dream Distillation: A Data-Independent Model Compression Framework","date":"2019-05-17","arxiv_id":"1905.07072","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-pruning-for-low-rank-binary-indexing","title":"Network Pruning for Low-Rank Binary Indexing","date":"2019-05-14","arxiv_id":"1905.05686","repositories_listed":0,"syntology":null},{"url":null,"slug":"190503362","title":"2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval","date":"2019-05-08","arxiv_id":"1905.03362","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-lightweight-object-detectors-with","title":"Creating Lightweight Object Detectors with Model Compression for Deployment on Edge Devices","date":"2019-05-06","arxiv_id":"1905.01787","repositories_listed":0,"syntology":null},{"url":null,"slug":"190500571","title":"26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone","date":"2019-05-02","arxiv_id":"1905.00571","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-extremely-low-bit-and-lossless","title":"Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM","date":"2019-05-02","arxiv_id":"1905.00789","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-viterbi-weight-encoding-for-high","title":"Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"integral-pruning-on-activations-and-weights","title":"Integral Pruning on Activations and Weights for Efficient Neural Networks","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-with-generative-adversarial-1","title":"Model Compression with Generative Adversarial Networks","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"n-ary-quantization-for-cnn-model-compression","title":"N-Ary Quantization for CNN Model Compression and Inference Acceleration","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-convolutional-units-improving-cnns","title":"Selective Convolutional Units: Improving CNNs via Channel Selectivity","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-teacher-student-learning","title":"Conditional Teacher-Student Learning","date":"2019-04-28","arxiv_id":"1904.12399","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-dropout-methods-for-deep-neural","title":"Survey of Dropout Methods for Deep Neural Networks","date":"2019-04-25","arxiv_id":"1904.13310","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-with-multi-task-knowledge","title":"Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System","date":"2019-04-21","arxiv_id":"1904.09636","repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-and-localization-in-reinforcement","title":"Compression and Localization in Reinforcement Learning for ATARI Games","date":"2019-04-20","arxiv_id":"1904.09489","repositories_listed":0,"syntology":null},{"url":"/paper/matrix-and-tensor-decompositions-for-training","slug":"matrix-and-tensor-decompositions-for-training","title":"Matrix and tensor decompositions for training binary neural networks","date":"2019-04-16","arxiv_id":"1904.07852","repositories_listed":0,"syntology":null},{"url":null,"slug":"3dq-compact-quantized-neural-networks-for","title":"3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation","date":"2019-04-05","arxiv_id":"1904.03110","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-backbone-for-semantic-segmentation","title":"Real time backbone for semantic segmentation","date":"2019-03-16","arxiv_id":"1903.06922","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-convolution-for-compact-and-cost","title":"Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical Study","date":"2019-02-26","arxiv_id":"1902.09809","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-memory-management-for-gpu-based","title":"Efficient Memory Management for GPU-based Deep Learning Systems","date":"2019-02-19","arxiv_id":"1903.06631","repositories_listed":0,"syntology":null},{"url":null,"slug":"architecture-compression","title":"Architecture Compression","date":"2019-02-08","arxiv_id":"1902.03326","repositories_listed":0,"syntology":null},{"url":null,"slug":"micik-mining-cross-layer-inherent-similarity","title":"MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression","date":"2019-02-03","arxiv_id":"1902.00918","repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsically-sparse-long-short-term-memory","title":"Intrinsically Sparse Long Short-Term Memory Networks","date":"2019-01-26","arxiv_id":"1901.09208","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-3d-architectures-of-deep","title":"Exploring the 3D architectures of deep material network in data-driven multiscale mechanics","date":"2019-01-02","arxiv_id":"1901.04832","repositories_listed":0,"syntology":null},{"url":null,"slug":"natively-interpretable-machine-learning-and","title":"Natively Interpretable Machine Learning and Artificial Intelligence: Preliminary Results and Future Directions","date":"2019-01-02","arxiv_id":"1901.00246","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-low-effort-approach-to-structured-cnn","title":"A Low Effort Approach to Structured CNN Design Using PCA","date":"2018-12-15","arxiv_id":"1812.06224","repositories_listed":0,"syntology":null},{"url":null,"slug":"droppruning-for-model-compression","title":"Stochastic Model Pruning via Weight Dropping Away and Back","date":"2018-12-05","arxiv_id":"1812.02035","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-filter-correlations-for-deep-model","title":"Leveraging Filter Correlations for Deep Model Compression","date":"2018-11-26","arxiv_id":"1811.10559","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-mobile-computing-for-the-visually","title":"A Survey of Mobile Computing for the Visually Impaired","date":"2018-11-25","arxiv_id":"1811.10120","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-neural-architecture-search-and","title":"Joint Neural Architecture Search and Quantization","date":"2018-11-23","arxiv_id":"1811.09426","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-adaptive-pruning-for-efficient","title":"Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks","date":"2018-11-21","arxiv_id":"1811.08589","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-based-filter-pruning-for","title":"Stability Based Filter Pruning for Accelerating Deep CNNs","date":"2018-11-20","arxiv_id":"1811.08321","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-dimensional-convolutional-neural","title":"Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method","date":"2018-11-19","arxiv_id":"1811.07555","repositories_listed":0,"syntology":null},{"url":null,"slug":"private-model-compression-via-knowledge","title":"Private Model Compression via Knowledge Distillation","date":"2018-11-13","arxiv_id":"1811.05072","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-level-knowledge-distillation-for","title":"Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition","date":"2018-11-12","arxiv_id":"1811.04531","repositories_listed":0,"syntology":null},{"url":null,"slug":"flops-as-a-direct-optimization-objective-for","title":"FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks","date":"2018-11-07","arxiv_id":"1811.03060","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-framework-of-dnn-weight-pruning-and","title":"A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM","date":"2018-11-05","arxiv_id":"1811.01907","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeptwist-learning-model-compression-via","title":"DeepTwist: Learning Model Compression via Occasional Weight Distortion","date":"2018-10-30","arxiv_id":"1810.12823","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-with-performance-enhanced-students","title":"Distilling with Performance Enhanced Students","date":"2018-10-24","arxiv_id":"1810.10460","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-compress-or-not-to-compress-characterizing","title":"To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference","date":"2018-10-21","arxiv_id":"1810.08899","repositories_listed":0,"syntology":null},{"url":null,"slug":"block-wise-intermediate-representation","title":"Block-wise Intermediate Representation Training for Model Compression","date":"2018-10-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-of-deep-neural-networks-by","title":"Compression of Deep Neural Networks by combining pruning and low rank decomposition","date":"2018-10-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pruning-at-a-glance-a-structured-class-blind","title":"Pruning at a Glance: A Structured Class-Blind Pruning Technique for Model Compression","date":"2018-10-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-convolutions-a-model-compression","title":"Recurrent Convolutions: A Model Compression Point of View","date":"2018-10-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-weight-pruning-of-deep-neural","title":"Progressive Weight Pruning of Deep Neural Networks using ADMM","date":"2018-10-17","arxiv_id":"1810.07378","repositories_listed":0,"syntology":null},{"url":null,"slug":"rate-distortion-for-model-compression-from","title":"Rate Distortion For Model Compression: From Theory To Practice","date":"2018-10-09","arxiv_id":"1810.06401","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-computation-of-quantized-neural","title":"Efficient Computation of Quantized Neural Networks by {−1, +1} Encoding Decomposition","date":"2018-10-08","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"bcba214f37601e1f531e22dae84ec8ef3b80e44ab3f3124de856e70b1761f981","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}