{"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/5","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":5,"pages_in_order":14,"rows_per_page":100,"rows":[401,500],"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/4","next":"/task/model-compression/papers/6","papers":[{"url":"/paper/adversarial-robustness-vs-model-compression","slug":"adversarial-robustness-vs-model-compression","title":"Adversarial Robustness vs. Model Compression, or Both?","date":"2019-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/190910364","slug":"190910364","title":"Class-dependent Compression of Deep Neural Networks","date":"2019-09-23","arxiv_id":"1909.10364","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/190910364#ran","syntology_url":"https://syntology.ai/paper/1909.10364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10364"}},"official":{"repos":["rahimentezari/Sensys-ml2020"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lit-learned-intermediate-representation","slug":"lit-learned-intermediate-representation","title":"LIT: Learned Intermediate Representation Training for Model Compression","date":"2019-09-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-for-end-to-endperson","slug":"knowledge-distillation-for-end-to-endperson","title":"Knowledge Distillation for End-to-End Person Search","date":"2019-09-03","arxiv_id":"1909.01058","repositories_listed":1,"syntology":null},{"url":"/paper/einconv-exploring-unexplored-tensor","slug":"einconv-exploring-unexplored-tensor","title":"Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks","date":"2019-08-13","arxiv_id":"1908.04471","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/einconv-exploring-unexplored-tensor#ran","syntology_url":"https://syntology.ai/paper/1908.04471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.04471"}},"official":{"repos":["pfnet-research/einconv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-correlation-tracking-via-joint","slug":"real-time-correlation-tracking-via-joint","title":"Real-Time Correlation Tracking via Joint Model Compression and Transfer","date":"2019-07-23","arxiv_id":"1907.09831","repositories_listed":1,"syntology":null},{"url":"/paper/cop-customized-deep-model-compression-via","slug":"cop-customized-deep-model-compression-via","title":"COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning","date":"2019-06-25","arxiv_id":"1906.10337","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/cop-customized-deep-model-compression-via#ran","syntology_url":"https://syntology.ai/paper/1906.10337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10337"}},"official":{"repos":["ZJULearning/COP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/compressing-convolutional-neural-networks-via","slug":"compressing-convolutional-neural-networks-via","title":"Compressing Convolutional Neural Networks via Factorized Convolutional Filters","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-tensorized-neural-networks-with","slug":"bayesian-tensorized-neural-networks-with","title":"Bayesian Tensorized Neural Networks with Automatic Rank Selection","date":"2019-05-24","arxiv_id":"1905.10478","repositories_listed":1,"syntology":null},{"url":"/paper/compressed-learning-of-deep-neural-networks","slug":"compressed-learning-of-deep-neural-networks","title":"Compressed Learning of Deep Neural Networks for OpenCL-Capable Embedded Systems","date":"2019-05-20","arxiv_id":"1905.07931","repositories_listed":1,"syntology":null},{"url":"/paper/play-and-prune-adaptive-filter-pruning-for","slug":"play-and-prune-adaptive-filter-pruning-for","title":"Play and Prune: Adaptive Filter Pruning for Deep Model Compression","date":"2019-05-11","arxiv_id":"1905.04446","repositories_listed":1,"syntology":null},{"url":"/paper/legr-filter-pruning-via-learned-global","slug":"legr-filter-pruning-via-learned-global","title":"Towards Efficient Model Compression via Learned Global Ranking","date":"2019-04-28","arxiv_id":"1904.12368","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/legr-filter-pruning-via-learned-global#ran","syntology_url":"https://syntology.ai/paper/1904.12368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12368"}},"official":{"repos":["cmu-enyac/LeGR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/shakeout-a-new-approach-to-regularized-deep","slug":"shakeout-a-new-approach-to-regularized-deep","title":"Shakeout: A New Approach to Regularized Deep Neural Network Training","date":"2019-04-13","arxiv_id":"1904.06593","repositories_listed":1,"syntology":null},{"url":"/paper/model-slicing-for-supporting-complex","slug":"model-slicing-for-supporting-complex","title":"Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource Constraints","date":"2019-04-03","arxiv_id":"1904.01831","repositories_listed":1,"syntology":null},{"url":"/paper/second-rethinking-of-network-pruning-in-the","slug":"second-rethinking-of-network-pruning-in-the","title":"Adversarial Robustness vs Model Compression, or Both?","date":"2019-03-29","arxiv_id":"1903.12561","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/second-rethinking-of-network-pruning-in-the#ran","syntology_url":"https://syntology.ai/paper/1903.12561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.12561"}},"official":{"repos":["yeshaokai/Robustness-Aware-Pruning-ADMM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/efficient-and-effective-quantization-for","slug":"efficient-and-effective-quantization-for","title":"Focused Quantization for Sparse CNNs","date":"2019-03-07","arxiv_id":"1903.03046","repositories_listed":1,"syntology":null},{"url":"/paper/tensorized-embedding-layers-for-efficient","slug":"tensorized-embedding-layers-for-efficient","title":"Tensorized Embedding Layers for Efficient Model Compression","date":"2019-01-30","arxiv_id":"1901.10787","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-understanding-of","slug":"information-theoretic-understanding-of","title":"Information-Theoretic Understanding of Population Risk Improvement with Model Compression","date":"2019-01-27","arxiv_id":"1901.09421","repositories_listed":1,"syntology":null},{"url":"/paper/learning-efficient-detector-with-semi","slug":"learning-efficient-detector-with-semi","title":"Learning Efficient Detector with Semi-supervised Adaptive Distillation","date":"2019-01-02","arxiv_id":"1901.00366","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-efficient-detector-with-semi#ran","syntology_url":"https://syntology.ai/paper/1901.00366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.00366"}},"official":{"repos":["Tangshitao/Semi-supervised-Adaptive-Distillation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/admm-nn-an-algorithm-hardware-co-design","slug":"admm-nn-an-algorithm-hardware-co-design","title":"ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers","date":"2018-12-31","arxiv_id":"1812.11677","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-kernel-sparsity-and-entropy-for","slug":"exploiting-kernel-sparsity-and-entropy-for","title":"Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression","date":"2018-12-11","arxiv_id":"1812.04368","repositories_listed":1,"syntology":null},{"url":"/paper/model-compression-with-generative-adversarial","slug":"model-compression-with-generative-adversarial","title":"Teacher-Student Compression with Generative Adversarial Networks","date":"2018-12-05","arxiv_id":"1812.02271","repositories_listed":1,"syntology":null},{"url":"/paper/javascript-convolutional-neural-networks-for","slug":"javascript-convolutional-neural-networks-for","title":"JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental Analysis","date":"2018-10-30","arxiv_id":"1810.12859","repositories_listed":1,"syntology":null},{"url":"/paper/discrimination-aware-channel-pruning-for-deep","slug":"discrimination-aware-channel-pruning-for-deep","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","date":"2018-10-28","arxiv_id":"1810.11809","repositories_listed":1,"syntology":null},{"url":"/paper/a-miniaturized-semantic-segmentation-method","slug":"a-miniaturized-semantic-segmentation-method","title":"A Miniaturized Semantic Segmentation Method for Remote Sensing Image","date":"2018-10-27","arxiv_id":"1810.11603","repositories_listed":1,"syntology":null},{"url":"/paper/pocketflow-an-automated-framework-for","slug":"pocketflow-an-automated-framework-for","title":"PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural Networks","date":"2018-10-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-compression-from-limited-unlabeled","slug":"learning-compression-from-limited-unlabeled","title":"Learning Compression from Limited Unlabeled Data","date":"2018-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-device-neural-language-model-based-word","slug":"on-device-neural-language-model-based-word","title":"On-Device Neural Language Model Based Word Prediction","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/slimnets-an-exploration-of-deep-model","slug":"slimnets-an-exploration-of-deep-model","title":"SlimNets: An Exploration of Deep Model Compression and Acceleration","date":"2018-08-01","arxiv_id":"1808.00496","repositories_listed":1,"syntology":null},{"url":"/paper/adam-admm-a-unified-systematic-framework-of","slug":"adam-admm-a-unified-systematic-framework-of","title":"StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs","date":"2018-07-29","arxiv_id":"1807.11091","repositories_listed":1,"syntology":null},{"url":"/paper/alearning-compressiona-algorithms-for-neural","slug":"alearning-compressiona-algorithms-for-neural","title":"“Learning-Compression” Algorithms for Neural Net Pruning","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-binary-networks-optimizing-for","slug":"hybrid-binary-networks-optimizing-for","title":"Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory","date":"2018-04-11","arxiv_id":"1804.03867","repositories_listed":1,"syntology":null},{"url":"/paper/learning-deep-and-compact-models-for-gesture","slug":"learning-deep-and-compact-models-for-gesture","title":"Learning Deep and Compact Models for Gesture Recognition","date":"2017-12-29","arxiv_id":"1712.10136","repositories_listed":1,"syntology":null},{"url":"/paper/strassennets-deep-learning-with-a","slug":"strassennets-deep-learning-with-a","title":"StrassenNets: Deep Learning with a Multiplication Budget","date":"2017-12-11","arxiv_id":"1712.03942","repositories_listed":1,"syntology":null},{"url":"/paper/model-compression-as-constrained-optimization","slug":"model-compression-as-constrained-optimization","title":"Model compression as constrained optimization, with application to neural nets. Part II: quantization","date":"2017-07-13","arxiv_id":"1707.04319","repositories_listed":1,"syntology":null},{"url":"/paper/model-compression-as-constrained-optimization-1","slug":"model-compression-as-constrained-optimization-1","title":"Model compression as constrained optimization, with application to neural nets. Part I: general framework","date":"2017-07-05","arxiv_id":"1707.01209","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-distillation-for-text","slug":"cross-lingual-distillation-for-text","title":"Cross-lingual Distillation for Text Classification","date":"2017-05-05","arxiv_id":"1705.02073","repositories_listed":1,"syntology":null},{"url":"/paper/the-shallow-end-empowering-shallower-deep","slug":"the-shallow-end-empowering-shallower-deep","title":"The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs","date":"2016-11-06","arxiv_id":"1611.01773","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-model-knowledge","slug":"distilling-model-knowledge","title":"Distilling Model Knowledge","date":"2015-10-08","arxiv_id":"1510.02437","repositories_listed":1,"syntology":null},{"url":"/paper/deepfont-identify-your-font-from-an-image","slug":"deepfont-identify-your-font-from-an-image","title":"DeepFont: Identify Your Font from An Image","date":"2015-07-12","arxiv_id":"1507.03196","repositories_listed":1,"syntology":null},{"url":null,"slug":"linr-pcgc-lossless-implicit-neural","title":"LINR-PCGC: Lossless Implicit Neural Representations for Point Cloud Geometry Compression","date":"2025-07-21","arxiv_id":"2507.15686","repositories_listed":0,"syntology":null},{"url":null,"slug":"dipsvd-dual-importance-protected-svd-for","title":"DipSVD: Dual-importance Protected SVD for Efficient LLM Compression","date":"2025-06-25","arxiv_id":"2506.20353","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlrc-reinforcement-learning-based-recovery","title":"RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models","date":"2025-06-21","arxiv_id":"2506.17639","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-using-knowledge","title":"Model compression using knowledge distillation with integrated gradients","date":"2025-06-17","arxiv_id":"2506.14440","repositories_listed":0,"syntology":null},{"url":null,"slug":"eaquant-enhancing-post-training-quantization","title":"EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization","date":"2025-06-16","arxiv_id":"2506.13329","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-quantization-for-video-matting","title":"Post-Training Quantization for Video Matting","date":"2025-06-12","arxiv_id":"2506.10840","repositories_listed":0,"syntology":null},{"url":null,"slug":"awp-activation-aware-weight-pruning-and","title":"AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent","date":"2025-06-11","arxiv_id":"2506.10205","repositories_listed":0,"syntology":null},{"url":null,"slug":"insight-a-survey-of-in-network-systems-for","title":"INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization","date":"2025-05-30","arxiv_id":"2505.24269","repositories_listed":0,"syntology":null},{"url":null,"slug":"smooth-model-compression-without-fine-tuning","title":"Smooth Model Compression without Fine-Tuning","date":"2025-05-30","arxiv_id":"2505.24469","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-and-efficient-one-pass-compression","title":"Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates","date":"2025-05-28","arxiv_id":"2505.22608","repositories_listed":0,"syntology":null},{"url":null,"slug":"pangu-light-weight-re-initialization-for","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","date":"2025-05-26","arxiv_id":"2505.20155","repositories_listed":0,"syntology":null},{"url":null,"slug":"ressvd-residual-compensated-svd-for-large","title":"ResSVD: Residual Compensated SVD for Large Language Model Compression","date":"2025-05-26","arxiv_id":"2505.20112","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-models-architectures","title":"Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation","date":"2025-05-26","arxiv_id":"2505.19529","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensorization-is-a-powerful-but-underexplored","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","date":"2025-05-26","arxiv_id":"2505.20132","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-workload-aware-llm-serving-via","title":"Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing","date":"2025-05-24","arxiv_id":"2506.02006","repositories_listed":0,"syntology":null},{"url":null,"slug":"making-deep-neural-networks-work-for-medical","title":"Making deep neural networks work for medical audio: representation, compression and domain adaptation","date":"2025-05-24","arxiv_id":"2506.13970","repositories_listed":0,"syntology":null},{"url":null,"slug":"latentllm-attention-aware-joint-tensor","title":"LatentLLM: Attention-Aware Joint Tensor Compression","date":"2025-05-23","arxiv_id":"2505.18413","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-first-language-model-inference-models","title":"Edge-First Language Model Inference: Models, Metrics, and Tradeoffs","date":"2025-05-22","arxiv_id":"2505.16508","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-quantum-optimization-ready-an-effort","title":"Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing","date":"2025-05-22","arxiv_id":"2505.16332","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-multilingual-encoder-language-model","title":"On Multilingual Encoder Language Model Compression for Low-Resource Languages","date":"2025-05-22","arxiv_id":"2505.16956","repositories_listed":0,"syntology":null},{"url":null,"slug":"saten-sparse-augmented-tensor-networks-for","title":"Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models","date":"2025-05-20","arxiv_id":"2505.14871","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-inference-in-continual","title":"Low-Complexity Inference in Continual Learning via Compressed Knowledge Transfer","date":"2025-05-13","arxiv_id":"2505.08327","repositories_listed":0,"syntology":null},{"url":null,"slug":"kdh-mltc-knowledge-distillation-for","title":"KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification","date":"2025-05-12","arxiv_id":"2505.07162","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-retention-and-extreme-compression-in","title":"Semantic Retention and Extreme Compression in LLMs: Can We Have Both?","date":"2025-05-12","arxiv_id":"2505.07289","repositories_listed":0,"syntology":null},{"url":null,"slug":"sponge-attacks-on-sensing-ai-energy-latency","title":"Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning","date":"2025-05-09","arxiv_id":"2505.06454","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-optimized-deep-learning-pattern","title":"Edge-Optimized Deep Learning & Pattern Recognition Techniques for Non-Intrusive Load Monitoring of Energy Time Series","date":"2025-05-07","arxiv_id":"2505.06289","repositories_listed":0,"syntology":null},{"url":null,"slug":"onboard-optimization-and-learning-a-survey","title":"Onboard Optimization and Learning: A Survey","date":"2025-05-07","arxiv_id":"2505.08793","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-llms-for-resource-constrained","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","date":"2025-05-05","arxiv_id":"2505.02309","repositories_listed":0,"syntology":null},{"url":"/paper/radio-rate-distortion-optimization-for-large","slug":"radio-rate-distortion-optimization-for-large","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","date":"2025-05-05","arxiv_id":"2505.03031","repositories_listed":0,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/radio-rate-distortion-optimization-for-large#ran","syntology_url":"https://syntology.ai/paper/2505.03031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.03031"}},"official":null}},{"url":null,"slug":"smart-environmental-monitoring-of-marine","title":"Smart Environmental Monitoring of Marine Pollution using Edge AI","date":"2025-04-30","arxiv_id":"2504.21759","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-matrix-approximation-for-neural","title":"Low-Rank Matrix Approximation for Neural Network Compression","date":"2025-04-25","arxiv_id":"2504.20078","repositories_listed":0,"syntology":null},{"url":null,"slug":"aerial-image-classification-in-scarce-and","title":"Aerial Image Classification in Scarce and Unconstrained Environments via Conformal Prediction","date":"2025-04-24","arxiv_id":"2504.17655","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-device-qwen2-5-efficient-llm-inference","title":"On-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration","date":"2025-04-24","arxiv_id":"2504.17376","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-large-to-super-tiny-end-to-end","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","date":"2025-04-18","arxiv_id":"2504.13471","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-2-moe-dual-routing-and-dynamic-scheduling","title":"D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving","date":"2025-04-17","arxiv_id":"2504.15299","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-hybrid-language-model-compression","title":"Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","date":"2025-04-15","arxiv_id":"2504.11409","repositories_listed":0,"syntology":null},{"url":null,"slug":"apsq-additive-partial-sum-quantization-with","title":"APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design","date":"2025-04-10","arxiv_id":"2505.03748","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-is-better-than-one-efficient-ensemble","title":"Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models","date":"2025-04-07","arxiv_id":"2504.04747","repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-laws-for-large-language-models","title":"Compression Laws for Large Language Models","date":"2025-04-06","arxiv_id":"2504.04342","repositories_listed":0,"syntology":null},{"url":null,"slug":"ringmoe-mixture-of-modality-experts-multi","title":"RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation","date":"2025-04-04","arxiv_id":"2504.03166","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositionality-unlocks-deep-interpretable","title":"Compositionality Unlocks Deep Interpretable Models","date":"2025-04-03","arxiv_id":"2504.02667","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-conditioning-with-distillation-for","title":"Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression","date":"2025-04-02","arxiv_id":"2504.02011","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-semantic-communications-via-large","title":"Multi-Task Semantic Communications via Large Models","date":"2025-03-28","arxiv_id":"2503.22064","repositories_listed":0,"syntology":null},{"url":null,"slug":"penrose-tiled-low-rank-compression-and","title":"Penrose Tiled Low-Rank Compression and Section-Wise Q&A Fine-Tuning: A General Framework for Domain-Specific Large Language Model Adaptation","date":"2025-03-28","arxiv_id":"2503.22074","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-low-power-streaming-speech-enhancement","title":"A Low-Power Streaming Speech Enhancement Accelerator For Edge Devices","date":"2025-03-27","arxiv_id":"2503.21335","repositories_listed":0,"syntology":null},{"url":null,"slug":"delving-deep-into-semantic-relation","title":"Delving Deep into Semantic Relation Distillation","date":"2025-03-27","arxiv_id":"2503.21269","repositories_listed":0,"syntology":null},{"url":null,"slug":"moqa-rethinking-moe-quantization-with-multi","title":"MoQa: Rethinking MoE Quantization with Multi-stage Data-model Distribution Awareness","date":"2025-03-27","arxiv_id":"2503.21135","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-mambair-accurate-quantized-mamba-for","title":"Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration","date":"2025-03-27","arxiv_id":"2503.21970","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-compression-via-the","title":"Large Language Model Compression via the Nested Activation-Aware Decomposition","date":"2025-03-21","arxiv_id":"2503.17101","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-action-detection-model-compression","title":"Temporal Action Detection Model Compression by Progressive Block Drop","date":"2025-03-21","arxiv_id":"2503.16916","repositories_listed":0,"syntology":null},{"url":null,"slug":"inhibidistilbert-knowledge-distillation-for-a","title":"InhibiDistilbert: Knowledge Distillation for a ReLU and Addition-based Transformer","date":"2025-03-20","arxiv_id":"2503.15983","repositories_listed":0,"syntology":null},{"url":null,"slug":"cluscomp-a-simple-paradigm-for-model","title":"ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning","date":"2025-03-17","arxiv_id":"2503.13089","repositories_listed":0,"syntology":null},{"url":null,"slug":"compmarkgs-robust-watermarking-for","title":"CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting","date":"2025-03-17","arxiv_id":"2503.12836","repositories_listed":0,"syntology":null},{"url":null,"slug":"fragile-mastery-are-domain-specific-trade","title":"Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?","date":"2025-03-16","arxiv_id":"2503.22698","repositories_listed":0,"syntology":null},{"url":null,"slug":"sometimes-painful-but-certainly-promising","title":"Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge","date":"2025-03-12","arxiv_id":"2503.09114","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-aware-depth-decay-decoding-d-3","title":"Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency","date":"2025-03-11","arxiv_id":"2503.08524","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-we-there-yet-a-measurement-study-of","title":"Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices","date":"2025-03-10","arxiv_id":"2504.00002","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-superior-quantization-accuracy-a","title":"Towards Superior Quantization Accuracy: A Layer-sensitive Approach","date":"2025-03-09","arxiv_id":"2503.06518","repositories_listed":0,"syntology":null},{"url":null,"slug":"acam-kd-adaptive-and-cooperative-attention","title":"ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation","date":"2025-03-08","arxiv_id":"2503.06307","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-edge-intelligence-a-comprehensive","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","date":"2025-03-08","arxiv_id":"2503.06027","repositories_listed":0,"syntology":null}],"record_sha256":"338ffe3f21aa76045489fdaf00552c30fecf0ab0a0c0cfeca3d758b91bdf9380","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}