{"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/10","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":10,"pages_in_order":14,"rows_per_page":100,"rows":[901,1000],"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/9","next":"/task/model-compression/papers/11","papers":[{"url":null,"slug":"resource-allocation-for-compression-aided","title":"Resource Allocation for Compression-aided Federated Learning with High Distortion Rate","date":"2022-06-02","arxiv_id":"2206.06976","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-label-regularization","title":"Do we need Label Regularization to Fine-tune Pre-trained Language Models?","date":"2022-05-25","arxiv_id":"2205.12428","repositories_listed":0,"syntology":null},{"url":null,"slug":"train-flat-then-compress-sharpness-aware","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","date":"2022-05-25","arxiv_id":"2205.12694","repositories_listed":0,"syntology":null},{"url":null,"slug":"dimensionality-reduced-training-by-pruning","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","date":"2022-05-17","arxiv_id":"2205.08099","repositories_listed":0,"syntology":null},{"url":null,"slug":"perturbation-of-deep-autoencoder-weights-for","title":"Perturbation of Deep Autoencoder Weights for Model Compression and Classification of Tabular Data","date":"2022-05-17","arxiv_id":"2205.08358","repositories_listed":0,"syntology":null},{"url":null,"slug":"qappa-quantization-aware-power-performance","title":"QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Accelerators","date":"2022-05-17","arxiv_id":"2205.08648","repositories_listed":0,"syntology":null},{"url":null,"slug":"dna-data-storage-sequencing-data-carrying-dna","title":"DNA data storage, sequencing data-carrying DNA","date":"2022-05-11","arxiv_id":"2205.05488","repositories_listed":0,"syntology":null},{"url":null,"slug":"serving-and-optimizing-machine-learning","title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","date":"2022-05-10","arxiv_id":"2205.04713","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-adversarial-knowledge-distillation","title":"Data-Free Adversarial Knowledge Distillation for Graph Neural Networks","date":"2022-05-08","arxiv_id":"2205.03811","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-block-wise-pruning-with-auxiliary","title":"Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks","date":"2022-05-07","arxiv_id":"2205.03602","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-model-compression-for-federated","title":"Online Model Compression for Federated Learning with Large Models","date":"2022-05-06","arxiv_id":"2205.03494","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-collaborative-learning-be-private-robust","title":"Can collaborative learning be private, robust and scalable?","date":"2022-05-05","arxiv_id":"2205.02652","repositories_listed":0,"syntology":null},{"url":null,"slug":"clusterq-semantic-feature-distribution","title":"Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization","date":"2022-04-30","arxiv_id":"2205.00179","repositories_listed":0,"syntology":null},{"url":null,"slug":"enable-deep-learning-on-mobile-devices","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","date":"2022-04-25","arxiv_id":"2204.11786","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-pruning-by-cooperative","title":"Neural Network Pruning by Cooperative Coevolution","date":"2022-04-12","arxiv_id":"2204.05639","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-deep-learning-for-all-in-edge","title":"Enabling All In-Edge Deep Learning: A Literature Review","date":"2022-04-07","arxiv_id":"2204.03326","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligned-weight-regularizers-for-pruning-1","title":"Aligned Weight Regularizers for Pruning Pretrained Neural Networks","date":"2022-04-04","arxiv_id":"2204.01385","repositories_listed":0,"syntology":null},{"url":null,"slug":"textpruner-a-model-pruning-toolkit-for-pre","title":"TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models","date":"2022-03-30","arxiv_id":"2203.15996","repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-modulation-a-parameter-efficient","title":"Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks","date":"2022-03-29","arxiv_id":"2203.15297","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-collide-recommendation-system","title":"Learning to Collide: Recommendation System Model Compression with Learned Hash Functions","date":"2022-03-28","arxiv_id":"2203.15837","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-gender-bias-in-distilled-language","title":"Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal","date":"2022-03-23","arxiv_id":"2203.12574","repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-of-generative-pre-trained","title":"Compression of Generative Pre-trained Language Models via Quantization","date":"2022-03-21","arxiv_id":"2203.10705","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrity-fingerprinting-of-dnn-with-double","title":"PublicCheck: Public Integrity Verification for Services of Run-time Deep Models","date":"2022-03-21","arxiv_id":"2203.10902","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-knowledge-distillation-with","title":"A Closer Look at Knowledge Distillation with Features, Logits, and Gradients","date":"2022-03-18","arxiv_id":"2203.10163","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-compressed-embeddings-for-on-device","title":"Learning Compressed Embeddings for On-Device Inference","date":"2022-03-18","arxiv_id":"2203.10135","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximability-and-generalisation","title":"Approximability and Generalisation","date":"2022-03-15","arxiv_id":"2203.07989","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mixed-integer-programming-approach-for","title":"A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural Networks","date":"2022-03-11","arxiv_id":"2203.07078","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-low-precision","title":"An Empirical Study of Low Precision Quantization for TinyML","date":"2022-03-10","arxiv_id":"2203.05492","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-be-so-dense-sparse-to-sparse-gan","title":"Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance","date":"2022-03-05","arxiv_id":"2203.02770","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-pruning-is-all-you-need-for","title":"Structured Pruning is All You Need for Pruning CNNs at Initialization","date":"2022-03-04","arxiv_id":"2203.02549","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-lang-energy-based-joint-inferencing-of-1","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","date":"2022-03-01","arxiv_id":"2203.00748","repositories_listed":0,"syntology":null},{"url":"/paper/kmir-a-benchmark-for-evaluating-knowledge","slug":"kmir-a-benchmark-for-evaluating-knowledge","title":"KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models","date":"2022-02-28","arxiv_id":"2202.13529","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-approach-for-modulation","title":"Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compression","date":"2022-02-26","arxiv_id":"2203.00517","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-architecture-slimming-method-for","title":"A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation","date":"2022-02-21","arxiv_id":"2202.10461","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-correlated-sparsification-for-efficient","title":"Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning","date":"2022-02-17","arxiv_id":"2202.08420","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-model-compression-for-natural","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","date":"2022-02-15","arxiv_id":"2202.07105","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-deep-learning-on-edge-devices","title":"Enabling Deep Learning on Edge Devices through Filter Pruning and Knowledge Transfer","date":"2022-01-22","arxiv_id":"2201.10947","repositories_listed":0,"syntology":null},{"url":null,"slug":"autodistill-an-end-to-end-framework-to","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","date":"2022-01-21","arxiv_id":"2201.08539","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-model-compression-improve-nlp-fairness","title":"Can Model Compression Improve NLP Fairness","date":"2022-01-21","arxiv_id":"2201.08542","repositories_listed":0,"syntology":null},{"url":null,"slug":"pcee-bert-accelerating-bert-inference-via","title":"PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"udc-unified-dnas-for-compressible-tinyml","title":"UDC: Unified DNAS for Compressible TinyML Models","date":"2022-01-15","arxiv_id":"2201.05842","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-pass-end-to-end-asr-model-compression","title":"Two-Pass End-to-End ASR Model Compression","date":"2022-01-08","arxiv_id":"2201.02741","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effect-of-model-compression-on-fairness","title":"The Effect of Model Compression on Fairness in Facial Expression Recognition","date":"2022-01-05","arxiv_id":"2201.01709","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreaming-to-prune-image-deraining-networks","title":"Dreaming To Prune Image Deraining Networks","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hodec-towards-efficient-high-order-decomposed","title":"HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-generative-data-free-knowledge","title":"Conditional Generative Data-free Knowledge Distillation","date":"2021-12-31","arxiv_id":"2112.15358","repositories_listed":0,"syntology":null},{"url":null,"slug":"croesus-multi-stage-processing-and","title":"Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems","date":"2021-12-31","arxiv_id":"2201.00063","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-knowledge-transfer-a-survey","title":"Data-Free Knowledge Transfer: A Survey","date":"2021-12-31","arxiv_id":"2112.15278","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-mixed-precision-quantization-search","title":"Automatic Mixed-Precision Quantization Search of BERT","date":"2021-12-30","arxiv_id":"2112.14938","repositories_listed":0,"syntology":null},{"url":null,"slug":"legodnn-block-grained-scaling-of-deep-neural","title":"LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision","date":"2021-12-18","arxiv_id":"2112.09852","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-object-detection","title":"Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation","date":"2021-12-09","arxiv_id":"2112.04840","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-tensor-decomposition-for-compression","title":"Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization","date":"2021-12-07","arxiv_id":"2112.03690","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-real-world-pathological-voice","title":"Toward Real-World Voice Disorder Classification","date":"2021-12-05","arxiv_id":"2112.02538","repositories_listed":0,"syntology":null},{"url":null,"slug":"formalizing-generalization-and-adversarial","title":"Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fedhm-efficient-federated-learning-for","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","date":"2021-11-29","arxiv_id":"2111.14655","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-low-cost-transformer-model","title":"Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions","date":"2021-11-27","arxiv_id":"2111.13999","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-deep-learning-with-dynamic-data","title":"Accelerating Deep Learning with Dynamic Data Pruning","date":"2021-11-24","arxiv_id":"2111.12621","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-mapping-of-the-best-suited-dnn","title":"Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration","date":"2021-11-22","arxiv_id":"2111.11581","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-selective-feature-distillation-for","title":"Local-Selective Feature Distillation for Single Image Super-Resolution","date":"2021-11-22","arxiv_id":"2111.10988","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-pruning-learns-compact-and","title":"Structured Pruning Learns Compact and Accurate Models","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-squeezing-reparameterization-for-2","title":"Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-symbol-level-precoding-a","title":"Learning-Based Symbol Level Precoding: A Memory-Efficient Unsupervised Learning Approach","date":"2021-11-15","arxiv_id":"2111.08110","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-generalization-on-efficient-acoustic","title":"Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization","date":"2021-11-12","arxiv_id":"2111.06531","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-interpretation-with-explainable","title":"Learning Interpretation with Explainable Knowledge Distillation","date":"2021-11-12","arxiv_id":"2111.06945","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-green-deep-learning","title":"A Survey on Green Deep Learning","date":"2021-11-08","arxiv_id":"2111.05193","repositories_listed":0,"syntology":null},{"url":null,"slug":"seofp-net-compression-and-acceleration-of","title":"SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points","date":"2021-11-08","arxiv_id":"2111.04436","repositories_listed":0,"syntology":null},{"url":null,"slug":"oracle-teacher-towards-better-knowledge","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","date":"2021-11-05","arxiv_id":"2111.03664","repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-block-or-unit-exploring-sparsity","title":"Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators","date":"2021-11-03","arxiv_id":"2111.02351","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-select-one-among-all-an-empirical","title":"How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ilmpq-an-intra-layer-multi-precision-deep","title":"ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA","date":"2021-10-30","arxiv_id":"2111.00155","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-fusion-of-heterogeneous-neural-networks-1","title":"On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks","date":"2021-10-29","arxiv_id":"2110.15538","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-compression-and-faster-inference","title":"Reconstructing Pruned Filters using Cheap Spatial Transformations","date":"2021-10-25","arxiv_id":"2110.12844","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-and-when-adversarial-robustness-transfers-1","title":"How and When Adversarial Robustness Transfers in Knowledge Distillation?","date":"2021-10-22","arxiv_id":"2110.12072","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-memory-consumption-by-neural","title":"Analysis of memory consumption by neural networks based on hyperparameters","date":"2021-10-21","arxiv_id":"2110.11424","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-knowledge-distillation-with-peer","title":"Augmenting Knowledge Distillation With Peer-To-Peer Mutual Learning For Model Compression","date":"2021-10-21","arxiv_id":"2110.11023","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-framework-of-transformer-by","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","date":"2021-10-19","arxiv_id":"2110.10030","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-short-study-on-compressing-decoder-based","title":"A Short Study on Compressing Decoder-Based Language Models","date":"2021-10-16","arxiv_id":"2110.08460","repositories_listed":0,"syntology":null},{"url":null,"slug":"pro-kd-progressive-distillation-by-following","title":"Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher","date":"2021-10-16","arxiv_id":"2110.08532","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-compressed-large-language-models","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","date":"2021-10-16","arxiv_id":"2110.08419","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-network-pruning-for","title":"Differentiable Network Pruning for Microcontrollers","date":"2021-10-15","arxiv_id":"2110.08350","repositories_listed":0,"syntology":null},{"url":null,"slug":"kronecker-decomposition-for-gpt-compression","title":"Kronecker Decomposition for GPT Compression","date":"2021-10-15","arxiv_id":"2110.08152","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-memory-efficient-learning-framework-for","title":"A Memory-Efficient Learning Framework for SymbolLevel Precoding with Quantized NN Weights","date":"2021-10-13","arxiv_id":"2110.06542","repositories_listed":0,"syntology":null},{"url":"/paper/rectifying-the-data-bias-in-knowledge","slug":"rectifying-the-data-bias-in-knowledge","title":"Rectifying the Data Bias in Knowledge Distillation","date":"2021-10-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feddq-communication-efficient-federated","title":"FedDQ: Communication-Efficient Federated Learning with Descending Quantization","date":"2021-10-05","arxiv_id":"2110.02291","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-knowledge-distillation-framework","title":"A Unified Knowledge Distillation Framework for Deep Directed Graphical Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hfsp-a-hardware-friendly-soft-pruning","title":"HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kimera-injecting-domain-knowledge-into-vacant","title":"KIMERA: Injecting Domain Knowledge into Vacant Transformer Heads","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-efficient-image-super-resolution","title":"Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-via-symmetries-of-the","title":"Model Compression via Symmetries of the Parameter Space","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"prototypical-contrastive-predictive-coding","title":"Prototypical Contrastive Predictive Coding","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-intent-recognition-method-based-on","title":"Robot Intent Recognition Method Based on State Grid Business Office","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-unbalanced-gan-training-with-in-time","title":"Sparse Unbalanced GAN Training with In-Time Over-Parameterization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-based-quality-estimation-small","title":"Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications","date":"2021-09-17","arxiv_id":"2109.08627","repositories_listed":0,"syntology":null},{"url":null,"slug":"realization-of-neural-network-based-optical","title":"Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization","date":"2021-09-15","arxiv_id":"2109.07204","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-accurate-simple-models-with-multihop","title":"Multihop: Leveraging Complex Models to Learn Accurate Simple Models","date":"2021-09-14","arxiv_id":"2109.06961","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-connection-between-knowledge","title":"A Note on Knowledge Distillation Loss Function for Object Classification","date":"2021-09-14","arxiv_id":"2109.06458","repositories_listed":0,"syntology":null},{"url":null,"slug":"kroneckerbert-learning-kronecker","title":"KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation","date":"2021-09-13","arxiv_id":"2109.06243","repositories_listed":0,"syntology":null},{"url":null,"slug":"bionetexplorer-architecture-space-exploration","title":"BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables","date":"2021-09-07","arxiv_id":"2109.02909","repositories_listed":0,"syntology":null},{"url":null,"slug":"gdp-stabilized-neural-network-pruning-via","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","date":"2021-09-06","arxiv_id":"2109.02220","repositories_listed":0,"syntology":null},{"url":null,"slug":"full-cycle-energy-consumption-benchmark-for","title":"Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision","date":"2021-08-30","arxiv_id":"2108.13465","repositories_listed":0,"syntology":null}],"record_sha256":"2b0c2cce936f185665867a94b2460895aeed28f8e9cec876996263ca17237f20","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}