{"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/knowledge-distillation/papers/43","list_of":"/task/knowledge-distillation","task":"Knowledge Distillation","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":43,"pages_in_order":43,"rows_per_page":100,"rows":[4201,4240],"of":4240,"counts":{"archive_papers_tagged":4240,"with_a_code_link":1740,"where_syntology_ran_a_sample":451,"not_listed_spam_title":0,"listed":4240,"listed_where_code_ran":451,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":380,"every_run_a_failure_of_syntologys_instrument":71,"listed_with_a_run_with_no_instrument_failure":380,"listed_every_run_a_failure_of_syntologys_instrument":71,"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/knowledge-distillation","prev":"/task/knowledge-distillation/papers/42","next":null,"papers":[{"url":null,"slug":"knowledge-distillation-from-few-samples-1","title":"Knowledge Distillation from Few Samples","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"label-denoising-with-large-ensembles-of","title":"Label Denoising with Large Ensembles of Heterogeneous Neural Networks","date":"2018-09-12","arxiv_id":"1809.04403","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-training-of-very-large-ensembles-of","title":"MotherNets: Rapid Deep Ensemble Learning","date":"2018-09-12","arxiv_id":"1809.04270","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-learning-via-progressive","title":"Lifelong Learning via Progressive Distillation and Retrospection","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-guided-answer-distillation-for","title":"Attention-Guided Answer Distillation for Machine Reading Comprehension","date":"2018-08-23","arxiv_id":"1808.07644","repositories_listed":0,"syntology":null},{"url":null,"slug":"whole-slide-mitosis-detection-in-he-breast","title":"Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks","date":"2018-08-17","arxiv_id":"1808.05896","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-denoising-for-distantly","title":"Cooperative Denoising for Distantly Supervised Relation Extraction","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-adversarial-training-of-neural","title":"Gradient Adversarial Training of Neural Networks","date":"2018-06-21","arxiv_id":"1806.08028","repositories_listed":0,"syntology":null},{"url":null,"slug":"coupled-end-to-end-transfer-learning-with","title":"Coupled End-to-End Transfer Learning With Generalized Fisher Information","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-learning-for-deep-neural","title":"Collaborative Learning for Deep Neural Networks","date":"2018-05-30","arxiv_id":"1805.11761","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-channel-pruning-method-for-deep","title":"A novel channel pruning method for deep neural network compression","date":"2018-05-29","arxiv_id":"1805.11394","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-relationship-detection-based-on-guided","title":"Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation","date":"2018-05-28","arxiv_id":"1805.10802","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-knowledge-distillation","title":"Recurrent knowledge distillation","date":"2018-05-18","arxiv_id":"1805.07170","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-in-generations-more","title":"Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students","date":"2018-05-15","arxiv_id":"1805.05551","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-compatibility-modeling-with-attentive","title":"Neural Compatibility Modeling with Attentive Knowledge Distillation","date":"2018-04-17","arxiv_id":"1805.00313","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-learning-of-neural-networks-from","title":"Few-shot learning of neural networks from scratch by pseudo example optimization","date":"2018-02-08","arxiv_id":"1802.03039","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-for-faster-structural","title":"Model compression for faster structural separation of macromolecules captured by Cellular Electron Cryo-Tomography","date":"2018-01-31","arxiv_id":"1801.10597","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-net-triage-analyzing-the-importance-of","title":"Deep Net Triage: Analyzing the Importance of Network Layers via Structural Compression","date":"2018-01-15","arxiv_id":"1801.04651","repositories_listed":0,"syntology":null},{"url":null,"slug":"generation-and-consolidation-of-recollections","title":"Generation and Consolidation of Recollections for Efficient Deep Lifelong Learning","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nestednet-learning-nested-sparse-structures","title":"NestedNet: Learning Nested Sparse Structures in Deep Neural Networks","date":"2017-12-11","arxiv_id":"1712.03781","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-efficient-object-detection-models","title":"Learning Efficient Object Detection Models with Knowledge Distillation","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-concentration-learning-100k-object","title":"Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN","date":"2017-11-21","arxiv_id":"1711.07607","repositories_listed":0,"syntology":null},{"url":null,"slug":"apprentice-using-knowledge-distillation","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","date":"2017-11-15","arxiv_id":"1711.05852","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-model-compression-and","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","date":"2017-10-23","arxiv_id":"1710.09282","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-distillation-with-knowledge-transfer","title":"Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification","date":"2017-09-09","arxiv_id":"1709.02929","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-shallow-and-thin-networks-for","title":"Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks","date":"2017-09-02","arxiv_id":"1709.00513","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-sequential-and-relational-model-for","title":"A Joint Sequential and Relational Model for Frame-Semantic Parsing","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-bilingual","title":"Knowledge Distillation for Bilingual Dictionary Induction","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/visual-relationship-detection-with-internal","slug":"visual-relationship-detection-with-internal","title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","date":"2017-07-28","arxiv_id":"1707.09423","repositories_listed":0,"syntology":null},{"url":"/paper/webchild-20-fine-grained-commonsense","slug":"webchild-20-fine-grained-commonsense","title":"WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tip-typifying-the-interpretability-of","title":"TIP: Typifying the Interpretability of Procedures","date":"2017-06-09","arxiv_id":"1706.02952","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-using-unlabeled","title":"Knowledge distillation using unlabeled mismatched images","date":"2017-03-21","arxiv_id":"1703.07131","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-adaptation-teaching-to-adapt","title":"Knowledge Adaptation: Teaching to Adapt","date":"2017-02-07","arxiv_id":"1702.02052","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-distillation-for-neural-machine","title":"Ensemble Distillation for Neural Machine Translation","date":"2017-02-06","arxiv_id":"1702.01802","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-machine-translation-from-simplified","title":"Neural Machine Translation from Simplified Translations","date":"2016-12-19","arxiv_id":"1612.06139","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-teacher-we-trust-learning-compressed","title":"In Teacher We Trust: Learning Compressed Models for Pedestrian Detection","date":"2016-12-01","arxiv_id":"1612.00478","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-scalable-convolutional-neural-network-for","title":"A scalable convolutional neural network for task-specified scenarios via knowledge distillation","date":"2016-09-19","arxiv_id":"1609.05695","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-small-footprint","title":"Knowledge Distillation for Small-footprint Highway Networks","date":"2016-08-02","arxiv_id":"1608.00892","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-models-to-signal-degradation-using","title":"Adapting Models to Signal Degradation using Distillation","date":"2016-04-01","arxiv_id":"1604.00433","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-knowledge-from-deep-networks-with","title":"Distilling Knowledge from Deep Networks with Applications to Healthcare Domain","date":"2015-12-11","arxiv_id":"1512.03542","repositories_listed":0,"syntology":null}],"record_sha256":"8d2d5bd9858c902923fa3cccd5218db1b75ad8117e2a29edca93da400baec84a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}