{"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/8","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":8,"pages_in_order":14,"rows_per_page":100,"rows":[701,800],"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/7","next":"/task/model-compression/papers/9","papers":[{"url":null,"slug":"memory-efficient-vision-transformers-an","title":"Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy","date":"2024-02-08","arxiv_id":"2402.06004","repositories_listed":0,"syntology":null},{"url":null,"slug":"l4q-parameter-efficient-quantization-aware","title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","date":"2024-02-07","arxiv_id":"2402.04902","repositories_listed":0,"syntology":null},{"url":null,"slug":"expediting-in-network-federated-learning-by","title":"Expediting In-Network Federated Learning by Voting-Based Consensus Model Compression","date":"2024-02-06","arxiv_id":"2402.03815","repositories_listed":0,"syntology":null},{"url":null,"slug":"fed-cvlc-compressing-federated-learning","title":"Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes","date":"2024-02-06","arxiv_id":"2402.03770","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-potential-of-automl-for-recommender","title":"The Potential of AutoML for Recommender Systems","date":"2024-02-06","arxiv_id":"2402.04453","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-transformer-compression","title":"A Survey on Transformer Compression","date":"2024-02-05","arxiv_id":"2402.05964","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-sparse-learning-a-novel-paradigm-for","title":"Dynamic Sparse Learning: A Novel Paradigm for Efficient Recommendation","date":"2024-02-05","arxiv_id":"2402.02855","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobile-fitting-room-on-device-virtual-try-on","title":"Mobile Fitting Room: On-device Virtual Try-on via Diffusion Models","date":"2024-02-02","arxiv_id":"2402.01877","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-multi-stage-training-model-for-edge","title":"Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection","date":"2024-01-31","arxiv_id":"2401.17546","repositories_listed":0,"syntology":null},{"url":null,"slug":"epsd-early-pruning-with-self-distillation-for","title":"EPSD: Early Pruning with Self-Distillation for Efficient Model Compression","date":"2024-01-31","arxiv_id":"2402.00084","repositories_listed":0,"syntology":null},{"url":null,"slug":"radin-souping-on-a-budget","title":"RADIN: Souping on a Budget","date":"2024-01-31","arxiv_id":"2401.17790","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-diffusion-model-compression","title":"Diffusion Model Compression for Image-to-Image Translation","date":"2024-01-31","arxiv_id":"2401.17547","repositories_listed":0,"syntology":null},{"url":null,"slug":"swapnet-efficient-swapping-for-dnn-inference","title":"SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget","date":"2024-01-30","arxiv_id":"2401.16757","repositories_listed":0,"syntology":null},{"url":null,"slug":"compactifai-extreme-compression-of-large","title":"CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks","date":"2024-01-25","arxiv_id":"2401.14109","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-receptive-field-strategy-and-important","title":"Large receptive field strategy and important feature extraction strategy in 3D object detection","date":"2024-01-22","arxiv_id":"2401.11913","repositories_listed":0,"syntology":null},{"url":null,"slug":"elrt-efficient-low-rank-training-for-compact","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","date":"2024-01-18","arxiv_id":"2401.10341","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-network-compression-via","title":"Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning","date":"2024-01-15","arxiv_id":"2401.08014","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffsplit-split-feed-forward-network-for","title":"FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference","date":"2024-01-08","arxiv_id":"2401.04044","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-llms-a-comprehensive-overview","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","date":"2024-01-04","arxiv_id":"2401.02038","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-quantization-via-pseudo-label","title":"Data-Free Quantization via Pseudo-label Filtering","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unleashing-channel-potential-space-frequency","title":"Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainability-driven-leaf-disease","title":"Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation","date":"2023-12-30","arxiv_id":"2401.00334","repositories_listed":0,"syntology":null},{"url":null,"slug":"dmt-comprehensive-distillation-with-multiple","title":"DMT: Comprehensive Distillation with Multiple Self-supervised Teachers","date":"2023-12-19","arxiv_id":"2312.11938","repositories_listed":0,"syntology":null},{"url":null,"slug":"coupling-fairness-and-pruning-in-a-single-run","title":"Integrating Fairness and Model Pruning Through Bi-level Optimization","date":"2023-12-15","arxiv_id":"2312.10181","repositories_listed":0,"syntology":null},{"url":null,"slug":"rankdvqa-mini-knowledge-distillation-driven","title":"RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment","date":"2023-12-14","arxiv_id":"2312.08864","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-key-factors-of-knowledge","title":"Unraveling Key Factors of Knowledge Distillation","date":"2023-12-14","arxiv_id":"2312.08585","repositories_listed":0,"syntology":null},{"url":null,"slug":"usm-lite-quantization-and-sparsity-aware-fine","title":"USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models","date":"2023-12-13","arxiv_id":"2312.08553","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-multimodal-model-compression-via","title":"Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup","date":"2023-12-10","arxiv_id":"2312.05795","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-codesign-for-fast-bragg","title":"Neural Architecture Codesign for Fast Bragg Peak Analysis","date":"2023-12-10","arxiv_id":"2312.05978","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-efficiency-spectrum-of-large-language","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","date":"2023-12-01","arxiv_id":"2312.00678","repositories_listed":0,"syntology":null},{"url":null,"slug":"layercollapse-adaptive-compression-of-neural","title":"LayerCollapse: Adaptive compression of neural networks","date":"2023-11-29","arxiv_id":"2311.17943","repositories_listed":0,"syntology":null},{"url":null,"slug":"relationship-between-model-compression-and","title":"Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence","date":"2023-11-27","arxiv_id":"2311.15782","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosine-similarity-knowledge-distillation-for","title":"Cosine Similarity Knowledge Distillation for Individual Class Information Transfer","date":"2023-11-24","arxiv_id":"2311.14307","repositories_listed":0,"syntology":null},{"url":null,"slug":"education-distillation-getting-student-models","title":"Education distillation:getting student models to learn in shcools","date":"2023-11-23","arxiv_id":"2311.13811","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-based-semantic","title":"Knowledge Distillation Based Semantic Communications For Multiple Users","date":"2023-11-23","arxiv_id":"2311.13789","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-transformer-knowledge-distillation","title":"Efficient Transformer Knowledge Distillation: A Performance Review","date":"2023-11-22","arxiv_id":"2311.13657","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-parameter-efficient-fine","title":"Towards Better Parameter-Efficient Fine-Tuning for Large Language Models: A Position Paper","date":"2023-11-22","arxiv_id":"2311.13126","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-quantization-with-low-precision","title":"Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs","date":"2023-11-21","arxiv_id":"2311.12359","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-neural-networks-for-tiny-machine","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","date":"2023-11-20","arxiv_id":"2311.11883","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-speed-odyssey-for-deployable-quantization","title":"A Speed Odyssey for Deployable Quantization of LLMs","date":"2023-11-16","arxiv_id":"2311.09550","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-does-calibration-data-affect-the-post","title":"On the Impact of Calibration Data in Post-training Quantization and Pruning","date":"2023-11-16","arxiv_id":"2311.09755","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedcode-communication-efficient-federated","title":"FedCode: Communication-Efficient Federated Learning via Transferring Codebooks","date":"2023-11-15","arxiv_id":"2311.09270","repositories_listed":0,"syntology":null},{"url":null,"slug":"epim-efficient-processing-in-memory","title":"EPIM: Efficient Processing-In-Memory Accelerators based on Epitome","date":"2023-11-12","arxiv_id":"2311.07620","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-knowledge-transfer","title":"Supervised domain adaptation for building extraction from off-nadir aerial images","date":"2023-11-07","arxiv_id":"2311.03867","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-lost-in-knowledge-distillation","title":"What is Lost in Knowledge Distillation?","date":"2023-11-07","arxiv_id":"2311.04142","repositories_listed":0,"syntology":null},{"url":"/paper/asymmetric-masked-distillation-for-pre","slug":"asymmetric-masked-distillation-for-pre","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","date":"2023-11-06","arxiv_id":"2311.03149","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-distillation-of-language-model-by","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","date":"2023-11-03","arxiv_id":"2311.01689","repositories_listed":0,"syntology":null},{"url":null,"slug":"divergent-token-metrics-measuring-degradation","title":"Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization","date":"2023-11-02","arxiv_id":"2311.01544","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-based-knowledge-transfer-an","title":"Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression","date":"2023-10-24","arxiv_id":"2310.15594","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-knowledge-distillation-using","title":"Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images","date":"2023-10-20","arxiv_id":"2310.13782","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-defense-of-parameter-sharing-for-model","title":"In defense of parameter sharing for model-compression","date":"2023-10-17","arxiv_id":"2310.11611","repositories_listed":0,"syntology":null},{"url":null,"slug":"usdc-unified-static-and-dynamic-compression","title":"USDC: Unified Static and Dynamic Compression for Visual Transformer","date":"2023-10-17","arxiv_id":"2310.11117","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-apple-maturity-and-damage","title":"Efficient Apple Maturity and Damage Assessment: A Lightweight Detection Model with GAN and Attention Mechanism","date":"2023-10-13","arxiv_id":"2310.09347","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-larger-image-classifiers-memorise","title":"What do larger image classifiers memorise?","date":"2023-10-09","arxiv_id":"2310.05337","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-machine-learning-primitives-on","title":"Accelerating Machine Learning Primitives on Commodity Hardware","date":"2023-10-08","arxiv_id":"2310.05218","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-in-practice-lessons-learned","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","date":"2023-10-06","arxiv_id":"2310.04621","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-guided-image-synthesis-for-data","title":"Robustness-Guided Image Synthesis for Data-Free Quantization","date":"2023-10-05","arxiv_id":"2310.03661","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-deep-learning-for-time-series-data","title":"Sparse Deep Learning for Time Series Data: Theory and Applications","date":"2023-10-05","arxiv_id":"2310.03243","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecoflap-efficient-coarse-to-fine-layer-wise","title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","date":"2023-10-04","arxiv_id":"2310.02998","repositories_listed":0,"syntology":null},{"url":null,"slug":"sweeping-heterogeneity-with-smart-mops","title":"Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation","date":"2023-10-04","arxiv_id":"2310.02842","repositories_listed":0,"syntology":null},{"url":null,"slug":"artemis-he-aware-training-for-efficient","title":"Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning","date":"2023-10-02","arxiv_id":"2310.01664","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-foundation-models","title":"Bridging the Gap Between Foundation Models and Heterogeneous Federated Learning","date":"2023-09-30","arxiv_id":"2310.00247","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-inductive-bias-knowledge","title":"Distilling Inductive Bias: Knowledge Distillation Beyond Model Compression","date":"2023-09-30","arxiv_id":"2310.00369","repositories_listed":0,"syntology":null},{"url":null,"slug":"cait-triple-win-compression-towards-high","title":"CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs","date":"2023-09-27","arxiv_id":"2309.15755","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-impact-of-quantization-and-pruning-of","title":"On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks \"In-the-Wild''","date":"2023-09-25","arxiv_id":"2309.14462","repositories_listed":0,"syntology":null},{"url":null,"slug":"vic-kd-variance-invariance-covariance","title":"VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks","date":"2023-09-22","arxiv_id":"2309.12914","repositories_listed":0,"syntology":null},{"url":null,"slug":"pruning-large-language-models-via-accuracy","title":"Pruning Large Language Models via Accuracy Predictor","date":"2023-09-18","arxiv_id":"2309.09507","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-step-knowledge-distillation-for-tiny","title":"Two-Step Knowledge Distillation for Tiny Speech Enhancement","date":"2023-09-15","arxiv_id":"2309.08144","repositories_listed":0,"syntology":null},{"url":null,"slug":"colld-contrastive-layer-to-layer-distillation","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","date":"2023-09-14","arxiv_id":"2309.07707","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-acceleration-of-low-rank-decomposed","title":"Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization","date":"2023-09-07","arxiv_id":"2309.03824","repositories_listed":0,"syntology":null},{"url":null,"slug":"norm-tweaking-high-performance-low-bit","title":"Norm Tweaking: High-performance Low-bit Quantization of Large Language Models","date":"2023-09-06","arxiv_id":"2309.02784","repositories_listed":0,"syntology":null},{"url":null,"slug":"adc-dac-free-analog-acceleration-of-deep","title":"ADC/DAC-Free Analog Acceleration of Deep Neural Networks with Frequency Transformation","date":"2023-09-04","arxiv_id":"2309.01771","repositories_listed":0,"syntology":null},{"url":null,"slug":"computation-efficient-deep-learning-for","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","date":"2023-08-27","arxiv_id":"2308.13998","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-knowledge-distillation-for-bert","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","date":"2023-08-26","arxiv_id":"2308.13958","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlip-distilling-language-image-pre-training","title":"DLIP: Distilling Language-Image Pre-training","date":"2023-08-24","arxiv_id":"2308.12956","repositories_listed":0,"syntology":null},{"url":null,"slug":"qd-bev-quantization-aware-view-guided","title":"QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection","date":"2023-08-21","arxiv_id":"2308.10515","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-disentangled-representation-with","title":"Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking","date":"2023-08-20","arxiv_id":"2308.10262","repositories_listed":0,"syntology":null},{"url":null,"slug":"shark-a-lightweight-model-compression","title":"SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems","date":"2023-08-18","arxiv_id":"2308.09395","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-spike-and-slab","title":"Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks","date":"2023-08-17","arxiv_id":"2308.09104","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-adversarial-robustness-of","title":"Benchmarking Adversarial Robustness of Compressed Deep Learning Models","date":"2023-08-16","arxiv_id":"2308.08160","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-model-compression-for-large","title":"A Survey on Model Compression for Large Language Models","date":"2023-08-15","arxiv_id":"2308.07633","repositories_listed":0,"syntology":null},{"url":null,"slug":"shortcut-v2v-compression-framework-for-video","title":"Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction","date":"2023-08-15","arxiv_id":"2308.08011","repositories_listed":0,"syntology":null},{"url":null,"slug":"fededge-ai-tc-a-semi-supervised-traffic","title":"FedEdge AI-TC: A Semi-supervised Traffic Classification Method based on Trusted Federated Deep Learning for Mobile Edge Computing","date":"2023-08-14","arxiv_id":"2308.06924","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-neural-network-pruning-requires","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","date":"2023-08-03","arxiv_id":"2308.02060","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimonet-multi-input-multi-output-on-device","title":"MIMONet: Multi-Input Multi-Output On-Device Deep Learning","date":"2023-07-22","arxiv_id":"2307.11962","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-methods-for-yolov5-a-review","title":"Model Compression Methods for YOLOv5: A Review","date":"2023-07-21","arxiv_id":"2307.11904","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-disentanglement-on-pruning-neural","title":"Impact of Disentanglement on Pruning Neural Networks","date":"2023-07-19","arxiv_id":"2307.09994","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-object-detection-1","title":"Knowledge Distillation for Object Detection: from generic to remote sensing datasets","date":"2023-07-18","arxiv_id":"2307.09264","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-quantization-via-mixed-precision","title":"Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning","date":"2023-07-02","arxiv_id":"2307.00498","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensorgpt-efficient-compression-of-the","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","date":"2023-07-02","arxiv_id":"2307.00526","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-adversarial-distillation-for-point","title":"Feature Adversarial Distillation for Point Cloud Classification","date":"2023-06-25","arxiv_id":"2306.14221","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-prune-and-factorize-for-language","title":"Low-Rank Prune-And-Factorize for Language Model Compression","date":"2023-06-25","arxiv_id":"2306.14152","repositories_listed":0,"syntology":null},{"url":null,"slug":"partitioning-guided-k-means-extreme-empty","title":"Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression","date":"2023-06-24","arxiv_id":"2306.14031","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynaquant-compressing-deep-learning-training","title":"DynaQuant: Compressing Deep Learning Training Checkpoints via Dynamic Quantization","date":"2023-06-20","arxiv_id":"2306.11800","repositories_listed":0,"syntology":null},{"url":null,"slug":"losparse-structured-compression-of-large","title":"LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation","date":"2023-06-20","arxiv_id":"2306.11222","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-using-binarization","title":"Neural Network Compression using Binarization and Few Full-Precision Weights","date":"2023-06-15","arxiv_id":"2306.08960","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","repositories_listed":0,"syntology":null},{"url":null,"slug":"riemannian-low-rank-model-compression-for","title":"Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation","date":"2023-06-04","arxiv_id":"2306.02433","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-acoustic-scene-classification-2","title":"Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNet","date":"2023-06-03","arxiv_id":"2306.02054","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-agnostic-structured-pruning-of-speech","title":"Task-Agnostic Structured Pruning of Speech Representation Models","date":"2023-06-02","arxiv_id":"2306.01385","repositories_listed":0,"syntology":null}],"record_sha256":"ab252870ea8a656d778d49f7d604d6eaa53619712c23714961b4f58fe150e342","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}