{"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":"/method/knowledge-distillation/papers/25","list_of":"/method/knowledge-distillation","method":"Knowledge Distillation","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":25,"pages_in_order":31,"rows_per_page":100,"rows":[2401,2500],"of":3071,"counts":{"archive_papers_tagged":3071,"with_a_code_link":1258,"where_syntology_ran_a_sample":320,"not_listed_spam_title":0,"listed":3071,"listed_where_code_ran":320,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":276,"every_run_a_failure_of_syntologys_instrument":44,"listed_with_a_run_with_no_instrument_failure":276,"listed_every_run_a_failure_of_syntologys_instrument":44,"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":"/method/knowledge-distillation","prev":"/method/knowledge-distillation/papers/24","next":"/method/knowledge-distillation/papers/26","papers":[{"paper":null,"slug":"ms-kd-multi-organ-segmentation-with-multiple","title":"MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets","date":"2021-08-05","arxiv_id":"2108.02559","n_code_links":0,"syntology":null},{"paper":"/paper/learning-compatible-embeddings","slug":"learning-compatible-embeddings","title":"Learning Compatible Embeddings","date":"2021-08-04","arxiv_id":"2108.01958","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["IrvingMeng/LCE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/online-knowledge-distillation-for-efficient","slug":"online-knowledge-distillation-for-efficient","title":"Online Knowledge Distillation for Efficient Pose Estimation","date":"2021-08-04","arxiv_id":"2108.02092","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["zhengli427/OKDHP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"semi-supervising-learning-transfer-learning","title":"Semi-Supervising Learning, Transfer Learning, and Knowledge Distillation with SimCLR","date":"2021-08-02","arxiv_id":"2108.00587","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-batch-negatives-for-knowledge-distillation","title":"In-Batch Negatives for Knowledge Distillation with Tightly-Coupled Teachers for Dense Retrieval","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-strategy-knowledge-distillation-based","title":"Multi-Strategy Knowledge Distillation Based Teacher-Student Framework for Machine Reading Comprehension","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"naist-english-to-japanese-simultaneous","title":"NAIST English-to-Japanese Simultaneous Translation System for IWSLT 2021 Simultaneous Text-to-text Task","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-knowledge-distillation-for-translating","title":"On Knowledge Distillation for Translating Erroneous Speech Transcriptions","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/pos-constrained-parallel-decoding-for-non","slug":"pos-constrained-parallel-decoding-for-non","title":"POS-Constrained Parallel Decoding for Non-autoregressive Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"trigger-is-not-sufficient-exploiting-frame","title":"Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/pose-guided-feature-learning-with-knowledge","slug":"pose-guided-feature-learning-with-knowledge","title":"Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification","date":"2021-07-31","arxiv_id":"2108.00139","n_code_links":0,"syntology":null},{"paper":null,"slug":"quped-quantized-personalization-via","title":"QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning","date":"2021-07-29","arxiv_id":"2107.13892","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-perturbed-length-aware-positional","title":"Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation","date":"2021-07-29","arxiv_id":"2107.13689","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-is-text-no-matter-what-unifying-text","title":"Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation","date":"2021-07-26","arxiv_id":"2107.12087","n_code_links":0,"syntology":null},{"paper":"/paper/rod-reception-aware-online-distillation-for","slug":"rod-reception-aware-online-distillation-for","title":"ROD: Reception-aware Online Distillation for Sparse Graphs","date":"2021-07-25","arxiv_id":"2107.11789","n_code_links":1,"syntology":null},{"paper":null,"slug":"follow-your-path-a-progressive-method-for","title":"Follow Your Path: a Progressive Method for Knowledge Distillation","date":"2021-07-20","arxiv_id":"2107.09305","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-ulmfit-and-self-distillation-with","title":"Learning ULMFiT and Self-Distillation with Calibration for Medical Dialogue System","date":"2021-07-20","arxiv_id":"2107.09625","n_code_links":0,"syntology":null},{"paper":null,"slug":"double-similarity-distillation-for-semantic","title":"Double Similarity Distillation for Semantic Image Segmentation","date":"2021-07-19","arxiv_id":"2107.08591","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-action-recognition-on-heterogeneous","title":"Federated Action Recognition on Heterogeneous Embedded Devices","date":"2021-07-18","arxiv_id":"2107.12147","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-adaptive-knowledge-distillation-for","title":"Scene-adaptive Knowledge Distillation for Sequential Recommendation via Differentiable Architecture Search","date":"2021-07-15","arxiv_id":"2107.07173","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-speech-translation-by-understanding","title":"Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task","date":"2021-07-12","arxiv_id":"2107.05782","n_code_links":0,"syntology":null},{"paper":null,"slug":"technical-report-of-team-graphmiracles-in-the","title":"Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021","date":"2021-07-12","arxiv_id":"2107.05476","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrast-r-cnn-for-continual-learning-in","title":"Contrast R-CNN for Continual Learning in Object Detection","date":"2021-07-11","arxiv_id":"2108.04224","n_code_links":0,"syntology":null},{"paper":"/paper/consensual-collaborative-training-and","slug":"consensual-collaborative-training-and","title":"Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations","date":"2021-07-10","arxiv_id":"2107.04746","n_code_links":3,"syntology":null},{"paper":null,"slug":"lifelong-twin-generative-adversarial-networks","title":"Lifelong Twin Generative Adversarial Networks","date":"2021-07-09","arxiv_id":"2107.04708","n_code_links":0,"syntology":null},{"paper":"/paper/categorical-relation-preserving-contrastive","slug":"categorical-relation-preserving-contrastive","title":"Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification","date":"2021-07-07","arxiv_id":"2107.03225","n_code_links":1,"syntology":null},{"paper":null,"slug":"novel-visual-category-discovery-with-dual","title":"Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation","date":"2021-07-07","arxiv_id":"2107.03358","n_code_links":0,"syntology":null},{"paper":null,"slug":"weclick-weakly-supervised-video-semantic","title":"WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations","date":"2021-07-07","arxiv_id":"2107.03088","n_code_links":0,"syntology":null},{"paper":null,"slug":"confidence-conditioned-knowledge-distillation","title":"Confidence Conditioned Knowledge Distillation","date":"2021-07-06","arxiv_id":"2107.06993","n_code_links":0,"syntology":null},{"paper":"/paper/cored-generalizing-fake-media-detection-with","slug":"cored-generalizing-fake-media-detection-with","title":"CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation","date":"2021-07-06","arxiv_id":"2107.02408","n_code_links":2,"syntology":{"ran":8,"of":15,"n_ran_checked":8,"n_instrument":0,"unverified":7,"pointer_only":5,"phrase":"8 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; 0 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":null,"slug":"embracing-the-dark-knowledge-domain","title":"Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation","date":"2021-07-06","arxiv_id":"2107.02629","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-accurate-human-activity-recognition","title":"A Light-weight Deep Human Activity Recognition Algorithm Using Multi-knowledge Distillation","date":"2021-07-06","arxiv_id":"2107.07331","n_code_links":0,"syntology":null},{"paper":"/paper/vidlankd-improving-language-understanding-via","slug":"vidlankd-improving-language-understanding-via","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","date":"2021-07-06","arxiv_id":"2107.02681","n_code_links":1,"syntology":null},{"paper":"/paper/continual-contrastive-self-supervised","slug":"continual-contrastive-self-supervised","title":"Continual Contrastive Learning for Image Classification","date":"2021-07-05","arxiv_id":"2107.01776","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["VDIGPKU/ContinualContrastiveLearning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-the-distribution-of-penultimate","title":"On The Distribution of Penultimate Activations of Classification Networks","date":"2021-07-05","arxiv_id":"2107.01900","n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-oriented-multimodal-machine","title":"Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model","date":"2021-07-04","arxiv_id":"2107.01571","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-vision-transformers-via-fine","slug":"efficient-vision-transformers-via-fine","title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","date":"2021-07-03","arxiv_id":"2107.01378","n_code_links":1,"syntology":null},{"paper":null,"slug":"isotonic-data-augmentation-for-knowledge","title":"Isotonic Data Augmentation for Knowledge Distillation","date":"2021-07-03","arxiv_id":"2107.01412","n_code_links":0,"syntology":null},{"paper":"/paper/pool-of-experts-realtime-querying-specialized","slug":"pool-of-experts-realtime-querying-specialized","title":"Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks","date":"2021-07-03","arxiv_id":"2107.01354","n_code_links":2,"syntology":null},{"paper":"/paper/split-and-bridge-adaptable-class-incremental","slug":"split-and-bridge-adaptable-class-incremental","title":"Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network","date":"2021-07-03","arxiv_id":"2107.01349","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":5,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["bigdata-inha/Split-and-Bridge"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"espnet-st-iwslt-2021-offline-speech","title":"ESPnet-ST IWSLT 2021 Offline Speech Translation System","date":"2021-07-01","arxiv_id":"2107.00636","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-knowledge-distillation-an-1","slug":"revisiting-knowledge-distillation-an-1","title":"Revisiting Knowledge Distillation: An Inheritance and Exploration Framework","date":"2021-07-01","arxiv_id":"2107.00181","n_code_links":1,"syntology":null},{"paper":null,"slug":"global-knowledge-distillation-in-federated","title":"Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data","date":"2021-06-30","arxiv_id":"2107.00051","n_code_links":0,"syntology":null},{"paper":"/paper/learning-without-forgetting-for-3d-point","slug":"learning-without-forgetting-for-3d-point","title":"Learning without Forgetting for 3D Point Cloud Objects","date":"2021-06-27","arxiv_id":"2106.14275","n_code_links":1,"syntology":null},{"paper":null,"slug":"reward-based-1-bit-compressed-federated","title":"Reward-Based 1-bit Compressed Federated Distillation on Blockchain","date":"2021-06-27","arxiv_id":"2106.14265","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapt-and-distill-developing-small-fast-and","title":"Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains","date":"2021-06-25","arxiv_id":"2106.13474","n_code_links":0,"syntology":null},{"paper":null,"slug":"pqk-model-compression-via-pruning","title":"PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation","date":"2021-06-25","arxiv_id":"2106.14681","n_code_links":0,"syntology":null},{"paper":"/paper/dns-distill-and-select-for-efficient-and","slug":"dns-distill-and-select-for-efficient-and","title":"DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval","date":"2021-06-24","arxiv_id":"2106.13266","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["mever-team/distill-and-select"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"dealing-with-training-and-test-segmentation","title":"Dealing with training and test segmentation mismatch: FBK@IWSLT2021","date":"2021-06-23","arxiv_id":"2106.12607","n_code_links":0,"syntology":null},{"paper":"/paper/ssul-semantic-segmentation-with-unknown-label","slug":"ssul-semantic-segmentation-with-unknown-label","title":"SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning","date":"2021-06-22","arxiv_id":"2106.11562","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":6,"n_instrument":0,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","official":{"repos":["clovaai/SSUL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knowledge-distillation-via-instance-level","title":"Knowledge Distillation via Instance-level Sequence Learning","date":"2021-06-21","arxiv_id":"2106.10885","n_code_links":0,"syntology":null},{"paper":"/paper/structured-sparse-r-cnn-for-direct-scene","slug":"structured-sparse-r-cnn-for-direct-scene","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","date":"2021-06-21","arxiv_id":"2106.10815","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["mcg-nju/structured-sparse-rcnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"capsulerrt-relationships-aware-regression","title":"CapsuleRRT: Relationships-Aware Regression Tracking via Capsules","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-modality-knowledge-distillation-for","slug":"cross-modality-knowledge-distillation-for","title":"Cross Modality Knowledge Distillation for Multi-Modal Aerial View Object Classification","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/learning-student-networks-in-the-wild","slug":"learning-student-networks-in-the-wild","title":"Learning Student Networks in the Wild","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"minimally-invasive-surgery-for-sparse-neural","title":"Minimally Invasive Surgery for Sparse Neural Networks in Contrastive Manner","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"space-time-distillation-for-video-super","title":"Space-Time Distillation for Video Super-Resolution","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tree-like-decision-distillation","title":"Tree-Like Decision Distillation","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-teacher-class-incremental-learning-with","title":"Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay","date":"2021-06-17","arxiv_id":"2106.09835","n_code_links":0,"syntology":null},{"paper":null,"slug":"topology-distillation-for-recommender-system","title":"Topology Distillation for Recommender System","date":"2021-06-16","arxiv_id":"2106.08700","n_code_links":0,"syntology":null},{"paper":"/paper/simon-says-evaluating-and-mitigating-bias-in","slug":"simon-says-evaluating-and-mitigating-bias-in","title":"Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation","date":"2021-06-15","arxiv_id":"2106.07849","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":2,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["codestar12/pruning-distilation-bias"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"codert-distilling-encoder-representations","title":"CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition","date":"2021-06-14","arxiv_id":"2106.07734","n_code_links":0,"syntology":null},{"paper":"/paper/context-aware-image-inpainting-with-learned","slug":"context-aware-image-inpainting-with-learned","title":"Context-Aware Image Inpainting with Learned Semantic Priors","date":"2021-06-14","arxiv_id":"2106.07220","n_code_links":1,"syntology":null},{"paper":null,"slug":"energy-efficient-knowledge-distillation-for","title":"Energy-efficient Knowledge Distillation for Spiking Neural Networks","date":"2021-06-14","arxiv_id":"2106.07172","n_code_links":0,"syntology":null},{"paper":"/paper/guiding-teacher-forcing-with-seer-forcing-for","slug":"guiding-teacher-forcing-with-seer-forcing-for","title":"Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation","date":"2021-06-12","arxiv_id":"2106.06751","n_code_links":0,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/le-nas-learning-based-ensenble-with-nas-for","slug":"le-nas-learning-based-ensenble-with-nas-for","title":"LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction","date":"2021-06-12","arxiv_id":"2106.06733","n_code_links":1,"syntology":null},{"paper":"/paper/generate-annotate-and-learn-generative-models","slug":"generate-annotate-and-learn-generative-models","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","date":"2021-06-11","arxiv_id":"2106.06168","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xlhex/gal_syntex"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"refbert-compressing-bert-by-referencing-to","title":"RefBERT: Compressing BERT by Referencing to Pre-computed Representations","date":"2021-06-11","arxiv_id":"2106.08898","n_code_links":0,"syntology":null},{"paper":"/paper/does-knowledge-distillation-really-work","slug":"does-knowledge-distillation-really-work","title":"Does Knowledge Distillation Really Work?","date":"2021-06-10","arxiv_id":"2106.05945","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["samuelstanton/gnosis"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/marginal-utility-diminishes-exploring-the","slug":"marginal-utility-diminishes-exploring-the","title":"Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation","date":"2021-06-10","arxiv_id":"2106.05691","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["llyx97/Marginal-Utility-Diminishes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/distilling-image-classifiers-in-object","slug":"distilling-image-classifiers-in-object","title":"Distilling Image Classifiers in Object Detectors","date":"2021-06-09","arxiv_id":"2106.05209","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-a-good-teacher-is","slug":"knowledge-distillation-a-good-teacher-is","title":"Knowledge distillation: A good teacher is patient and consistent","date":"2021-06-09","arxiv_id":"2106.05237","n_code_links":10,"syntology":null},{"paper":null,"slug":"learning-by-distillation-a-self-supervised","title":"Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation","date":"2021-06-08","arxiv_id":"2106.04195","n_code_links":0,"syntology":null},{"paper":"/paper/meta-learning-for-knowledge-distillation","slug":"meta-learning-for-knowledge-distillation","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","date":"2021-06-08","arxiv_id":"2106.04570","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":2,"n_instrument":3,"unverified":4,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["JetRunner/MetaDistil"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/xtremedistiltransformers-task-transfer-for","slug":"xtremedistiltransformers-task-transfer-for","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","date":"2021-06-08","arxiv_id":"2106.04563","n_code_links":1,"syntology":null},{"paper":null,"slug":"rosearch-search-for-robust-student","title":"RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models","date":"2021-06-07","arxiv_id":"2106.03613","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-tiny-a-progressive-distillation","slug":"ernie-tiny-a-progressive-distillation","title":"ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression","date":"2021-06-04","arxiv_id":"2106.02241","n_code_links":1,"syntology":null},{"paper":null,"slug":"not-all-knowledge-is-created-equal","title":"Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge","date":"2021-06-02","arxiv_id":"2106.01489","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-teacher-is-enough-pre-trained-language","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","date":"2021-06-02","arxiv_id":"2106.01023","n_code_links":0,"syntology":null},{"paper":null,"slug":"claim-matching-beyond-english-to-scale-global","title":"Claim Matching Beyond English to Scale Global Fact-Checking","date":"2021-06-01","arxiv_id":"2106.00853","n_code_links":0,"syntology":null},{"paper":null,"slug":"continual-learning-for-neural-machine","title":"Continual Learning for Neural Machine Translation","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-effective-deployment-of-bert-models-in-1","title":"Cost-effective Deployment of BERT Models in Serverless Environment","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modality-specific-distillation-1","title":"Modality-specific Distillation","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-grained-knowledge-distillation-for","title":"Multi-Grained Knowledge Distillation for Named Entity Recognition","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-statistics-of-network-activations-and","title":"Natural Statistics of Network Activations and Implications for Knowledge Distillation","date":"2021-06-01","arxiv_id":"2106.00368","n_code_links":0,"syntology":null},{"paper":"/paper/towards-quantifiable-dialogue-coherence","slug":"towards-quantifiable-dialogue-coherence","title":"Towards Quantifiable Dialogue Coherence Evaluation","date":"2021-06-01","arxiv_id":"2106.00507","n_code_links":1,"syntology":null},{"paper":"/paper/greedy-layer-pruning-decreasing-inference","slug":"greedy-layer-pruning-decreasing-inference","title":"Greedy-layer Pruning: Speeding up Transformer Models for Natural Language Processing","date":"2021-05-31","arxiv_id":"2105.14839","n_code_links":1,"syntology":null},{"paper":null,"slug":"fretal-generalizing-deepfake-detection-using","title":"FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning","date":"2021-05-28","arxiv_id":"2105.13617","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-inheritance-for-pre-trained","slug":"knowledge-inheritance-for-pre-trained","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-05-28","arxiv_id":"2105.13880","n_code_links":2,"syntology":null},{"paper":"/paper/not-far-away-not-so-close-sample-efficient","slug":"not-far-away-not-so-close-sample-efficient","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","date":"2021-05-28","arxiv_id":"2105.13608","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-source-free-domain","slug":"transformer-based-source-free-domain","title":"Transformer-Based Source-Free Domain Adaptation","date":"2021-05-28","arxiv_id":"2105.14138","n_code_links":1,"syntology":null},{"paper":null,"slug":"fair-feature-distillation-for-visual","title":"Fair Feature Distillation for Visual Recognition","date":"2021-05-27","arxiv_id":"2106.04411","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-distilled-data-complexity-impact-the","title":"How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?","date":"2021-05-27","arxiv_id":"2105.12900","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-detnas-upgrade-your-detector-with-nas","title":"Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation","date":"2021-05-27","arxiv_id":"2105.12971","n_code_links":0,"syntology":null},{"paper":"/paper/selective-knowledge-distillation-for-neural","slug":"selective-knowledge-distillation-for-neural","title":"Selective Knowledge Distillation for Neural Machine Translation","date":"2021-05-27","arxiv_id":"2105.12967","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["LeslieOverfitting/selective_distillation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knowsr-knowledge-sharing-among-homogeneous","title":"KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning","date":"2021-05-25","arxiv_id":"2105.11611","n_code_links":0,"syntology":null},{"paper":null,"slug":"airnet-neural-network-transmission-over-the","title":"AirNet: Neural Network Transmission over the Air","date":"2021-05-24","arxiv_id":"2105.11166","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimenting-with-knowledge-distillation","title":"Experimenting with Knowledge Distillation techniques for performing Brain Tumor Segmentation","date":"2021-05-24","arxiv_id":"2105.11486","n_code_links":0,"syntology":null},{"paper":"/paper/backdoor-attacks-on-self-supervised-learning","slug":"backdoor-attacks-on-self-supervised-learning","title":"Backdoor Attacks on Self-Supervised Learning","date":"2021-05-21","arxiv_id":"2105.10123","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":5,"n_instrument":6,"unverified":2,"pointer_only":8,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["UMBCvision/SSL-Backdoor"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/data-free-knowledge-distillation-for-1","slug":"data-free-knowledge-distillation-for-1","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","date":"2021-05-20","arxiv_id":"2105.10056","n_code_links":4,"syntology":null}],"record_sha256":"8c0a762696f96b345dd266a629b3228f6e8ffde4b026ed1e8de182cf4954ca6c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}