{"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/9","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":9,"pages_in_order":14,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/model-compression/papers/10","papers":[{"url":null,"slug":"conaclip-exploring-distillation-of-fully","title":"ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval","date":"2023-05-28","arxiv_id":"2305.17652","repositories_listed":0,"syntology":null},{"url":null,"slug":"2-bit-conformer-quantization-for-automatic","title":"2-bit Conformer quantization for automatic speech recognition","date":"2023-05-26","arxiv_id":"2305.16619","repositories_listed":0,"syntology":null},{"url":null,"slug":"rand-robustness-aware-norm-decay-for","title":"RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models","date":"2023-05-24","arxiv_id":"2305.15536","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-data-augmentation-in-model","title":"Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study","date":"2023-05-22","arxiv_id":"2305.13232","repositories_listed":0,"syntology":null},{"url":null,"slug":"compress-then-prompt-improving-accuracy","title":"Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt","date":"2023-05-17","arxiv_id":"2305.11186","repositories_listed":0,"syntology":null},{"url":null,"slug":"snt-sharpness-minimizing-network","title":"CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation","date":"2023-05-08","arxiv_id":"2305.04526","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-pretrained-source-code-models","title":"Redundancy and Concept Analysis for Code-trained Language Models","date":"2023-05-01","arxiv_id":"2305.00875","repositories_listed":0,"syntology":null},{"url":null,"slug":"corsd-class-oriented-relational-self","title":"CORSD: Class-Oriented Relational Self Distillation","date":"2023-04-28","arxiv_id":"2305.00918","repositories_listed":0,"syntology":null},{"url":null,"slug":"guaranteed-quantization-error-computation-for","title":"Guaranteed Quantization Error Computation for Neural Network Model Compression","date":"2023-04-26","arxiv_id":"2304.13812","repositories_listed":0,"syntology":null},{"url":null,"slug":"bias-in-pruned-vision-models-in-depth","title":"Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures","date":"2023-04-25","arxiv_id":"2304.12622","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-collective-knowledge-distillation","title":"Deep Collective Knowledge Distillation","date":"2023-04-18","arxiv_id":"2304.08878","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-pruning-for-multi-task-deep-neural","title":"Structured Pruning for Multi-Task Deep Neural Networks","date":"2023-04-13","arxiv_id":"2304.06840","repositories_listed":0,"syntology":null},{"url":null,"slug":"surrogate-lagrangian-relaxation-a-path-to","title":"Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning","date":"2023-04-08","arxiv_id":"2304.04120","repositories_listed":0,"syntology":null},{"url":null,"slug":"oberta-improving-sparse-transfer-learning-via","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","date":"2023-03-30","arxiv_id":"2303.17612","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-emo-joint-pruning-with-multiple-sub","title":"A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking","date":"2023-03-28","arxiv_id":"2303.16212","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-gan-compression-with","title":"Information-Theoretic GAN Compression with Variational Energy-based Model","date":"2023-03-28","arxiv_id":"2303.16050","repositories_listed":0,"syntology":null},{"url":null,"slug":"tetra-aml-automatic-machine-learning-via","title":"Tetra-AML: Automatic Machine Learning via Tensor Networks","date":"2023-03-28","arxiv_id":"2303.16214","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-accurate-post-training-quantization","title":"Towards Accurate Post-Training Quantization for Vision Transformer","date":"2023-03-25","arxiv_id":"2303.14341","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-turkish-speech-recognition-via","title":"Exploring Turkish Speech Recognition via Hybrid CTC/Attention Architecture and Multi-feature Fusion Network","date":"2023-03-22","arxiv_id":"2303.12300","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-optimization-for-efficient-deep","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","date":"2023-03-22","arxiv_id":"2303.13635","repositories_listed":0,"syntology":null},{"url":"/paper/r-2-range-regularization-for-model","slug":"r-2-range-regularization-for-model","title":"R2 Loss: Range Restriction Loss for Model Compression and Quantization","date":"2023-03-14","arxiv_id":"2303.08253","repositories_listed":0,"syntology":null},{"url":null,"slug":"greener-yet-powerful-taming-large-code","title":"Greener yet Powerful: Taming Large Code Generation Models with Quantization","date":"2023-03-09","arxiv_id":"2303.05378","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-free-structured-pruning-with","title":"Gradient-Free Structured Pruning with Unlabeled Data","date":"2023-03-07","arxiv_id":"2303.04185","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-on-machine-learning-in","title":"Adversarial Attacks on Machine Learning in Embedded and IoT Platforms","date":"2023-03-03","arxiv_id":"2303.02214","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-domain-generalisation-in-asr-with","title":"Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation","date":"2023-03-01","arxiv_id":"2303.00550","repositories_listed":0,"syntology":null},{"url":null,"slug":"debiased-distillation-by-transplanting-the","title":"Debiased Distillation by Transplanting the Last Layer","date":"2023-02-22","arxiv_id":"2302.11187","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-bayesian-compression-for-deep-1","title":"Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach","date":"2023-02-21","arxiv_id":"2302.10483","repositories_listed":0,"syntology":null},{"url":null,"slug":"homodistil-homotopic-task-agnostic","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","date":"2023-02-19","arxiv_id":"2302.09632","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-and-a-taxonomy-of-edge-machine","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","date":"2023-02-16","arxiv_id":"2302.08571","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-optimal-compression-joint-pruning-and","title":"Towards Optimal Compression: Joint Pruning and Quantization","date":"2023-02-15","arxiv_id":"2302.07612","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-achieving-privacy-preserving-state-of-the","title":"On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence","date":"2023-02-10","arxiv_id":"2302.05323","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-in-vision-transformers","title":"Knowledge Distillation in Vision Transformers: A Critical Review","date":"2023-02-04","arxiv_id":"2302.02108","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-uncertainty-of-deep-neural","title":"Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications","date":"2023-02-02","arxiv_id":"2302.01440","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-on-graphs-a-survey","title":"Knowledge Distillation on Graphs: A Survey","date":"2023-02-01","arxiv_id":"2302.00219","repositories_listed":0,"syntology":null},{"url":null,"slug":"amd-adaptive-masked-distillation-for-object","title":"AMD: Adaptive Masked Distillation for Object Detection","date":"2023-01-31","arxiv_id":"2301.13538","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-knowledge-distillation-by-utilizing-1","title":"Improved knowledge distillation by utilizing backward pass knowledge in neural networks","date":"2023-01-27","arxiv_id":"2301.12006","repositories_listed":0,"syntology":null},{"url":null,"slug":"haloc-hardware-aware-automatic-low-rank","title":"HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks","date":"2023-01-20","arxiv_id":"2301.09422","repositories_listed":0,"syntology":null},{"url":null,"slug":"hce-improving-performance-and-efficiency-with","title":"HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble","date":"2023-01-18","arxiv_id":"2301.07794","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-focal-knowledge-from-imperfect","title":"Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"icd-face-intra-class-compactness-distillation","title":"ICD-Face: Intra-class Compactness Distillation for Face Recognition","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-friendly-scalable-super-resolution-via","title":"Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-model-for-mixed-precision","title":"One-Shot Model for Mixed-Precision Quantization","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tiny-updater-towards-efficient-neural-network","title":"Tiny Updater: Towards Efficient Neural Network-Driven Software Updating","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"flatenn-train-flat-for-enhanced-fault","title":"FlatENN: Train Flat for Enhanced Fault Tolerance of Quantized Deep Neural Networks","date":"2022-12-29","arxiv_id":"2301.00675","repositories_listed":0,"syntology":null},{"url":null,"slug":"bd-kd-balancing-the-divergences-for-online","title":"BD-KD: Balancing the Divergences for Online Knowledge Distillation","date":"2022-12-25","arxiv_id":"2212.12965","repositories_listed":0,"syntology":null},{"url":null,"slug":"fscnn-a-fast-sparse-convolution-neural","title":"FSCNN: A Fast Sparse Convolution Neural Network Inference System","date":"2022-12-17","arxiv_id":"2212.08815","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-find-strong-lottery-tickets-in","title":"Can We Find Strong Lottery Tickets in Generative Models?","date":"2022-12-16","arxiv_id":"2212.08311","repositories_listed":0,"syntology":null},{"url":null,"slug":"swing-distillation-a-privacy-preserving","title":"Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework","date":"2022-12-16","arxiv_id":"2212.08349","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-speech-representation-learning-with","title":"Efficient Speech Representation Learning with Low-Bit Quantization","date":"2022-12-14","arxiv_id":"2301.00652","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-aware-quantization-through-noise","title":"Error-aware Quantization through Noise Tempering","date":"2022-12-11","arxiv_id":"2212.05603","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-different-learning-styles-for","title":"Leveraging Different Learning Styles for Improved Knowledge Distillation in Biomedical Imaging","date":"2022-12-06","arxiv_id":"2212.02931","repositories_listed":0,"syntology":null},{"url":null,"slug":"cstar-towards-compact-and-structured-deep","title":"CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness","date":"2022-12-04","arxiv_id":"2212.01957","repositories_listed":0,"syntology":null},{"url":null,"slug":"gluefl-reconciling-client-sampling-and-model","title":"GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning","date":"2022-12-03","arxiv_id":"2212.01523","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-cross-lingual-multi-task-models","title":"Compressing Cross-Lingual Multi-Task Models at Qualtrics","date":"2022-11-29","arxiv_id":"2211.15927","repositories_listed":0,"syntology":null},{"url":null,"slug":"design-and-prototyping-distributed-cnn","title":"Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing","date":"2022-11-24","arxiv_id":"2211.13778","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-low-rank-representations-for-model","title":"Learning Low-Rank Representations for Model Compression","date":"2022-11-21","arxiv_id":"2211.11397","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-multiai-multi-tenancy-of-latency","title":"Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge","date":"2022-11-14","arxiv_id":"2211.07130","repositories_listed":0,"syntology":null},{"url":null,"slug":"xai-bayeshar-a-novel-framework-for-human","title":"XAI-BayesHAR: A novel Framework for Human Activity Recognition with Integrated Uncertainty and Shapely Values","date":"2022-11-07","arxiv_id":"2211.03451","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-for-dnn-based-text","title":"Model Compression for DNN-based Speaker Verification Using Weight Quantization","date":"2022-10-31","arxiv_id":"2210.17326","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-cross-layer-knowledge-distillation-on","title":"Online Cross-Layer Knowledge Distillation on Graph Neural Networks with Deep Supervision","date":"2022-10-25","arxiv_id":"2210.13743","repositories_listed":0,"syntology":null},{"url":null,"slug":"legal-tech-open-diaries-lesson-learned-on-how","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","date":"2022-10-24","arxiv_id":"2210.13086","repositories_listed":0,"syntology":null},{"url":null,"slug":"outsourcing-training-without-uploading-data","title":"Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling","date":"2022-10-23","arxiv_id":"2210.12575","repositories_listed":0,"syntology":null},{"url":null,"slug":"sub-network-multi-objective-evolutionary","title":"Sub-network Multi-objective Evolutionary Algorithm for Filter Pruning","date":"2022-10-22","arxiv_id":"2211.01957","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-model-hardware-tri-design-for-energy","title":"Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices","date":"2022-10-16","arxiv_id":"2210.08578","repositories_listed":0,"syntology":null},{"url":null,"slug":"fit-a-metric-for-model-sensitivity","title":"FIT: A Metric for Model Sensitivity","date":"2022-10-16","arxiv_id":"2210.08502","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-graph-neural-networks-via-adaptive","title":"Boosting Graph Neural Networks via Adaptive Knowledge Distillation","date":"2022-10-12","arxiv_id":"2210.05920","repositories_listed":0,"syntology":null},{"url":null,"slug":"sekron-a-decomposition-method-supporting-many","title":"SeKron: A Decomposition Method Supporting Many Factorization Structures","date":"2022-10-12","arxiv_id":"2210.06299","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-model-compression-using-network","title":"Deep learning model compression using network sensitivity and gradients","date":"2022-10-11","arxiv_id":"2210.05111","repositories_listed":0,"syntology":null},{"url":null,"slug":"alphatuning-quantization-aware-parameter","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","date":"2022-10-08","arxiv_id":"2210.03858","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-progressive-compression-of","title":"Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition","date":"2022-10-01","arxiv_id":"2210.00169","repositories_listed":0,"syntology":null},{"url":null,"slug":"match-to-win-analysing-sequences-lengths-for","title":"Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio","date":"2022-09-30","arxiv_id":"2209.15575","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-quantization-on-mlp-based-vision","title":"Analysis of Quantization on MLP-based Vision Models","date":"2022-09-14","arxiv_id":"2209.06383","repositories_listed":0,"syntology":null},{"url":null,"slug":"salenet-a-low-power-end-to-end-cnn","title":"SaleNet: A low-power end-to-end CNN accelerator for sustained attention level evaluation using EEG","date":"2022-09-03","arxiv_id":"2209.01386","repositories_listed":0,"syntology":null},{"url":null,"slug":"complexity-driven-cnn-compression-for","title":"Complexity-Driven CNN Compression for Resource-constrained Edge AI","date":"2022-08-26","arxiv_id":"2208.12816","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-computational-complexity-of-neural","title":"Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation","date":"2022-08-26","arxiv_id":"2208.12866","repositories_listed":0,"syntology":null},{"url":null,"slug":"design-automation-for-fast-lightweight-and","title":"Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey","date":"2022-08-22","arxiv_id":"2208.10498","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-targeted-attack-transferability-via","title":"Enhancing Targeted Attack Transferability via Diversified Weight Pruning","date":"2022-08-18","arxiv_id":"2208.08677","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-algorithm-hardware-co-optimized-framework","title":"An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers","date":"2022-08-12","arxiv_id":"2208.06118","repositories_listed":0,"syntology":null},{"url":null,"slug":"triple-sparsification-of-graph-convolutional","title":"Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy","date":"2022-08-06","arxiv_id":"2208.03559","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-blending-for-text-classification","title":"Model Blending for Text Classification","date":"2022-08-05","arxiv_id":"2208.02819","repositories_listed":0,"syntology":null},{"url":null,"slug":"quiver-neural-networks","title":"Quiver neural networks","date":"2022-07-26","arxiv_id":"2207.12773","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-for-resource-constrained","title":"Model Compression for Resource-Constrained Mobile Robots","date":"2022-07-20","arxiv_id":"2207.10082","repositories_listed":0,"syntology":null},{"url":null,"slug":"t-recx-tiny-resource-efficient-convolutional","title":"T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXit","date":"2022-07-14","arxiv_id":"2207.06613","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalized-feature-distillation-for-semantic","title":"Normalized Feature Distillation for Semantic Segmentation","date":"2022-07-12","arxiv_id":"2207.05256","repositories_listed":0,"syntology":null},{"url":null,"slug":"rank-based-filter-pruning-for-real-time-uav","title":"Rank-Based Filter Pruning for Real-Time UAV Tracking","date":"2022-07-05","arxiv_id":"2207.01768","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-neural-network-compression","title":"Quantum Neural Network Compression","date":"2022-07-04","arxiv_id":"2207.01578","repositories_listed":0,"syntology":null},{"url":null,"slug":"kroneckerbert-significant-compression-of-pre","title":"KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-compression-with-weighted-low-1","title":"Language model compression with weighted low-rank factorization","date":"2022-06-30","arxiv_id":"2207.00112","repositories_listed":0,"syntology":null},{"url":null,"slug":"quidam-a-framework-for-quantization-aware-dnn","title":"QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration","date":"2022-06-30","arxiv_id":"2206.15463","repositories_listed":0,"syntology":null},{"url":null,"slug":"fundamental-limits-of-communication","title":"Fundamental Limits of Communication Efficiency for Model Aggregation in Distributed Learning: A Rate-Distortion Approach","date":"2022-06-28","arxiv_id":"2206.13984","repositories_listed":0,"syntology":null},{"url":null,"slug":"qti-submission-to-dcase-2021-residual","title":"QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design","date":"2022-06-28","arxiv_id":"2206.13909","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-with-representative","title":"Representative Teacher Keys for Knowledge Distillation Model Compression Based on Attention Mechanism for Image Classification","date":"2022-06-26","arxiv_id":"2206.12788","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-automatic-and-efficient-bert-pruning-for","title":"An Automatic and Efficient BERT Pruning for Edge AI Systems","date":"2022-06-21","arxiv_id":"2206.10461","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-oriented-object","title":"Knowledge Distillation for Oriented Object Detection on Aerial Images","date":"2022-06-20","arxiv_id":"2206.09796","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-self-distillation","title":"Revisiting Self-Distillation","date":"2022-06-17","arxiv_id":"2206.08491","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-inference-and-language-model","title":"Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization","date":"2022-06-16","arxiv_id":"2206.07882","repositories_listed":0,"syntology":null},{"url":null,"slug":"atrial-fibrillation-detection-using-weight","title":"Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks","date":"2022-06-14","arxiv_id":"2206.07649","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-theoretical-understanding-of-neural-network","title":"A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation","date":"2022-06-11","arxiv_id":"2206.05604","repositories_listed":0,"syntology":null},{"url":null,"slug":"hidenseek-federated-lottery-ticket-via-server","title":"HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask","date":"2022-06-09","arxiv_id":"2206.04385","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-model-compression","title":"Differentially Private Model Compression","date":"2022-06-03","arxiv_id":"2206.01838","repositories_listed":0,"syntology":null}],"record_sha256":"131f52e358eed45e3a6dbbd768ab56381e76d659a81ca0d8e3d61746166df30f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}