{"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/18","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":18,"pages_in_order":31,"rows_per_page":100,"rows":[1701,1800],"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/17","next":"/method/knowledge-distillation/papers/19","papers":[{"paper":null,"slug":"bd-kd-balancing-the-divergences-for-online","title":"BD-KD: Balancing the Divergences for Online Knowledge Distillation","date":"2022-12-25","arxiv_id":"2212.12965","n_code_links":0,"syntology":null},{"paper":null,"slug":"camembert-cascading-assistant-mediated","title":"CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT","date":"2022-12-22","arxiv_id":"2212.11456","n_code_links":0,"syntology":null},{"paper":null,"slug":"adam-dense-retrieval-distillation-with","title":"Adam: Dense Retrieval Distillation with Adaptive Dark Examples","date":"2022-12-20","arxiv_id":"2212.10192","n_code_links":0,"syntology":null},{"paper":null,"slug":"diff-glat-diffusion-glancing-transformer-for","title":"Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning","date":"2022-12-20","arxiv_id":"2212.10240","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-grained-distillation-for-long-document","title":"Fine-Grained Distillation for Long Document Retrieval","date":"2022-12-20","arxiv_id":"2212.10423","n_code_links":0,"syntology":null},{"paper":"/paper/rangeaugment-efficient-online-augmentation","slug":"rangeaugment-efficient-online-augmentation","title":"RangeAugment: Efficient Online Augmentation with Range Learning","date":"2022-12-20","arxiv_id":"2212.10553","n_code_links":1,"syntology":null},{"paper":null,"slug":"i2d2-inductive-knowledge-distillation-with","title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation","date":"2022-12-19","arxiv_id":"2212.09246","n_code_links":0,"syntology":null},{"paper":"/paper/learning-object-level-point-augmentor-for","slug":"learning-object-level-point-augmentor-for","title":"Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection","date":"2022-12-19","arxiv_id":"2212.09273","n_code_links":1,"syntology":null},{"paper":"/paper/continually-learning-from-existing-models","slug":"continually-learning-from-existing-models","title":"Continual Knowledge Distillation for Neural Machine Translation","date":"2022-12-18","arxiv_id":"2212.09097","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-point-cloud-pre-training-with-knowledge","title":"3D Point Cloud Pre-training with Knowledge Distillation from 2D Images","date":"2022-12-17","arxiv_id":"2212.08974","n_code_links":0,"syntology":null},{"paper":null,"slug":"swing-distillation-a-privacy-preserving","title":"Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework","date":"2022-12-16","arxiv_id":"2212.08349","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-based-intra-attention-pruning-on-pre","slug":"gradient-based-intra-attention-pruning-on-pre","title":"Gradient-based Intra-attention Pruning on Pre-trained Language Models","date":"2022-12-15","arxiv_id":"2212.07634","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["airaria/grain"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"domain-adaptation-for-dense-retrieval-through","title":"Domain Adaptation for Dense Retrieval through Self-Supervision by Pseudo-Relevance Labeling","date":"2022-12-13","arxiv_id":"2212.06552","n_code_links":0,"syntology":null},{"paper":null,"slug":"mmnet-multi-modal-fusion-with-mutual-learning","title":"Multimodal Matching-aware Co-attention Networks with Mutual Knowledge Distillation for Fake News Detection","date":"2022-12-12","arxiv_id":"2212.05699","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-what-you-should-learn","title":"Teaching What You Should Teach: A Data-Based Distillation Method","date":"2022-12-11","arxiv_id":"2212.05422","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-adversarial-faster-rcnn-with-paradigm","title":"Multi-adversarial Faster-RCNN with Paradigm Teacher for Unrestricted Object Detection","date":"2022-12-11","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"complete-to-partial-4d-distillation-for-self","title":"Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning","date":"2022-12-10","arxiv_id":"2212.05330","n_code_links":0,"syntology":null},{"paper":"/paper/lead-liberal-feature-based-distillation-for","slug":"lead-liberal-feature-based-distillation-for","title":"LEAD: Liberal Feature-based Distillation for Dense Retrieval","date":"2022-12-10","arxiv_id":"2212.05225","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-applied-to-optical","title":"Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection","date":"2022-12-08","arxiv_id":"2212.04569","n_code_links":0,"syntology":null},{"paper":null,"slug":"occlusion-robust-fau-recognition-by-mining","title":"Occlusion-Robust FAU Recognition by Mining Latent Space of Masked Autoencoders","date":"2022-12-08","arxiv_id":"2212.04029","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-low-density-eeg-based-brain","slug":"enhancing-low-density-eeg-based-brain","title":"Enhancing Low-Density EEG-Based Brain-Computer Interfaces with Similarity-Keeping Knowledge Distillation","date":"2022-12-06","arxiv_id":"2212.03329","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-different-learning-styles-for","title":"Leveraging Different Learning Styles for Improved Knowledge Distillation in Biomedical Imaging","date":"2022-12-06","arxiv_id":"2212.02931","n_code_links":0,"syntology":null},{"paper":null,"slug":"life-long-learning-for-multilingual-neural","title":"Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation","date":"2022-12-06","arxiv_id":"2212.02800","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-world-detr-transformer-based-open-world","title":"Open World DETR: Transformer based Open World Object Detection","date":"2022-12-06","arxiv_id":"2212.02969","n_code_links":0,"syntology":null},{"paper":null,"slug":"da-cil-towards-domain-adaptive-class","title":"DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection","date":"2022-12-05","arxiv_id":"2212.02057","n_code_links":0,"syntology":null},{"paper":"/paper/fedukd-federated-unet-model-with-knowledge","slug":"fedukd-federated-unet-model-with-knowledge","title":"FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street Views","date":"2022-12-05","arxiv_id":"2212.02196","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-royalflush-system-for-the-wmt-2022","title":"The RoyalFlush System for the WMT 2022 Efficiency Task","date":"2022-12-03","arxiv_id":"2212.01543","n_code_links":0,"syntology":null},{"paper":"/paper/improving-simultaneous-machine-translation","slug":"improving-simultaneous-machine-translation","title":"Improving Simultaneous Machine Translation with Monolingual Data","date":"2022-12-02","arxiv_id":"2212.01188","n_code_links":1,"syntology":null},{"paper":null,"slug":"injecting-spatial-information-for-monaural","title":"Injecting Spatial Information for Monaural Speech Enhancement via Knowledge Distillation","date":"2022-12-02","arxiv_id":"2212.01012","n_code_links":0,"syntology":null},{"paper":null,"slug":"structvpr-distill-structural-knowledge-with","title":"StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition","date":"2022-12-02","arxiv_id":"2212.00937","n_code_links":0,"syntology":null},{"paper":"/paper/bev-lgkd-a-unified-lidar-guided-knowledge","slug":"bev-lgkd-a-unified-lidar-guided-knowledge","title":"BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection","date":"2022-12-01","arxiv_id":"2212.00623","n_code_links":1,"syntology":null},{"paper":"/paper/distilling-multi-step-reasoning-capabilities","slug":"distilling-multi-step-reasoning-capabilities","title":"Distilling Reasoning Capabilities into Smaller Language Models","date":"2022-12-01","arxiv_id":"2212.00193","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-based-depth-distillation-with-3d","title":"Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection","date":"2022-11-30","arxiv_id":"2211.16779","n_code_links":0,"syntology":null},{"paper":null,"slug":"coordinating-cross-modal-distillation-for","title":"Coordinating Cross-modal Distillation for Molecular Property Prediction","date":"2022-11-30","arxiv_id":"2211.16712","n_code_links":0,"syntology":null},{"paper":null,"slug":"explicit-knowledge-transfer-for-weakly","title":"Explicit Knowledge Transfer for Weakly-Supervised Code Generation","date":"2022-11-30","arxiv_id":"2211.16740","n_code_links":0,"syntology":null},{"paper":null,"slug":"heat-hardware-efficient-automatic-tensor","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","date":"2022-11-30","arxiv_id":"2211.16749","n_code_links":0,"syntology":null},{"paper":null,"slug":"hint-dynamic-knowledge-distillation","title":"Hint-dynamic Knowledge Distillation","date":"2022-11-30","arxiv_id":"2211.17059","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-distillation-based-degradation","slug":"knowledge-distillation-based-degradation","title":"Knowledge Distillation based Degradation Estimation for Blind Super-Resolution","date":"2022-11-30","arxiv_id":"2211.16928","n_code_links":1,"syntology":null},{"paper":null,"slug":"random-copolymer-inverse-design-system","title":"Random Copolymer inverse design system orienting on Accurate discovering of Antimicrobial peptide-mimetic copolymers","date":"2022-11-30","arxiv_id":"2212.00023","n_code_links":0,"syntology":null},{"paper":"/paper/curriculum-temperature-for-knowledge","slug":"curriculum-temperature-for-knowledge","title":"Curriculum Temperature for Knowledge Distillation","date":"2022-11-29","arxiv_id":"2211.16231","n_code_links":1,"syntology":{"ran":8,"of":15,"n_ran_checked":3,"n_instrument":5,"unverified":7,"pointer_only":2,"phrase":"8 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; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["zhengli97/ctkd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/feature-based-adaptive-contrastive","slug":"feature-based-adaptive-contrastive","title":"Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution","date":"2022-11-29","arxiv_id":"2211.15951","n_code_links":0,"syntology":null},{"paper":"/paper/dense-interspecies-face-embedding","slug":"dense-interspecies-face-embedding","title":"Dense Interspecies Face Embedding","date":"2022-11-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"inter-kd-intermediate-knowledge-distillation","title":"Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition","date":"2022-11-28","arxiv_id":"2211.15075","n_code_links":0,"syntology":null},{"paper":"/paper/sgva-clip-semantic-guided-visual-adapting-of","slug":"sgva-clip-semantic-guided-visual-adapting-of","title":"SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification","date":"2022-11-28","arxiv_id":"2211.16191","n_code_links":1,"syntology":null},{"paper":null,"slug":"class-aware-information-for-logit-based","title":"Class-aware Information for Logit-based Knowledge Distillation","date":"2022-11-27","arxiv_id":"2211.14773","n_code_links":0,"syntology":null},{"paper":"/paper/unbiased-knowledge-distillation-for","slug":"unbiased-knowledge-distillation-for","title":"Unbiased Knowledge Distillation for Recommendation","date":"2022-11-27","arxiv_id":"2211.14729","n_code_links":1,"syntology":null},{"paper":null,"slug":"skdbert-compressing-bert-via-stochastic","title":"SKDBERT: Compressing BERT via Stochastic Knowledge Distillation","date":"2022-11-26","arxiv_id":"2211.14466","n_code_links":0,"syntology":null},{"paper":"/paper/a-strong-baseline-for-generalized-few-shot","slug":"a-strong-baseline-for-generalized-few-shot","title":"A Strong Baseline for Generalized Few-Shot Semantic Segmentation","date":"2022-11-25","arxiv_id":"2211.14126","n_code_links":2,"syntology":null},{"paper":"/paper/mpcvit-searching-for-mpc-friendly-vision","slug":"mpcvit-searching-for-mpc-friendly-vision","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","date":"2022-11-25","arxiv_id":"2211.13955","n_code_links":1,"syntology":null},{"paper":"/paper/xkd-cross-modal-knowledge-distillation-with","slug":"xkd-cross-modal-knowledge-distillation-with","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","date":"2022-11-25","arxiv_id":"2211.13929","n_code_links":1,"syntology":null},{"paper":"/paper/distilling-knowledge-from-self-supervised","slug":"distilling-knowledge-from-self-supervised","title":"Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment","date":"2022-11-23","arxiv_id":"2211.13264","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yccm/ega"],"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"]}}},{"paper":"/paper/on-the-transferability-of-visual-features-in","slug":"on-the-transferability-of-visual-features-in","title":"On the Transferability of Visual Features in Generalized Zero-Shot Learning","date":"2022-11-22","arxiv_id":"2211.12494","n_code_links":1,"syntology":null},{"paper":"/paper/blind-knowledge-distillation-for-robust-image","slug":"blind-knowledge-distillation-for-robust-image","title":"Blind Knowledge Distillation for Robust Image Classification","date":"2022-11-21","arxiv_id":"2211.11355","n_code_links":1,"syntology":null},{"paper":"/paper/directed-acyclic-graph-factorization-machines","slug":"directed-acyclic-graph-factorization-machines","title":"Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation","date":"2022-11-21","arxiv_id":"2211.11159","n_code_links":1,"syntology":null},{"paper":"/paper/multi-level-knowledge-distillation-for-out-of","slug":"multi-level-knowledge-distillation-for-out-of","title":"Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text","date":"2022-11-21","arxiv_id":"2211.11300","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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","official":{"repos":["microsoft/KC"],"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"]}}},{"paper":null,"slug":"scalable-collaborative-learning-via","title":"Scalable Collaborative Learning via Representation Sharing","date":"2022-11-20","arxiv_id":"2211.10943","n_code_links":0,"syntology":null},{"paper":null,"slug":"dasecount-domain-agnostic-sample-efficient","title":"DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-shot Learning","date":"2022-11-18","arxiv_id":"2211.10040","n_code_links":0,"syntology":null},{"paper":"/paper/eeg-aided-boosting-of-single-lead-ecg-based","slug":"eeg-aided-boosting-of-single-lead-ecg-based","title":"EEG aided boosting of single-lead ECG based sleep staging with Deep Knowledge Distillation","date":"2022-11-18","arxiv_id":"2211.13125","n_code_links":1,"syntology":null},{"paper":"/paper/bevdistill-cross-modal-bev-distillation-for","slug":"bevdistill-cross-modal-bev-distillation-for","title":"BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection","date":"2022-11-17","arxiv_id":"2211.09386","n_code_links":1,"syntology":null},{"paper":"/paper/conner-consistency-training-for-cross-lingual","slug":"conner-consistency-training-for-cross-lingual","title":"ConNER: Consistency Training for Cross-lingual Named Entity Recognition","date":"2022-11-17","arxiv_id":"2211.09394","n_code_links":1,"syntology":null},{"paper":null,"slug":"d-3-etr-decoder-distillation-for-detection","title":"D$^3$ETR: Decoder Distillation for Detection Transformer","date":"2022-11-17","arxiv_id":"2211.09768","n_code_links":0,"syntology":null},{"paper":null,"slug":"detrdistill-a-universal-knowledge","title":"DETRDistill: A Universal Knowledge Distillation Framework for DETR-families","date":"2022-11-17","arxiv_id":"2211.10156","n_code_links":0,"syntology":null},{"paper":null,"slug":"yield-evaluation-of-citrus-fruits-based-on","title":"Yield Evaluation of Citrus Fruits based on the YoloV5 compressed by Knowledge Distillation","date":"2022-11-16","arxiv_id":"2211.08743","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-active-learning-pipeline-for","title":"An Efficient Active Learning Pipeline for Legal Text Classification","date":"2022-11-15","arxiv_id":"2211.08112","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-joint-use-of-rehearsal-and","slug":"exploring-the-joint-use-of-rehearsal-and","title":"An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding","date":"2022-11-15","arxiv_id":"2211.08161","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-for-detection","slug":"knowledge-distillation-for-detection","title":"Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2022-11-15","arxiv_id":"2211.08071","n_code_links":2,"syntology":null},{"paper":null,"slug":"an-interpretable-neuron-embedding-for-static","title":"An Interpretable Neuron Embedding for Static Knowledge Distillation","date":"2022-11-14","arxiv_id":"2211.07647","n_code_links":0,"syntology":null},{"paper":"/paper/cabvit-cross-attention-among-blocks-for","slug":"cabvit-cross-attention-among-blocks-for","title":"Fcaformer: Forward Cross Attention in Hybrid Vision Transformer","date":"2022-11-14","arxiv_id":"2211.07198","n_code_links":2,"syntology":null},{"paper":"/paper/cross-modality-knowledge-distillation-network","slug":"cross-modality-knowledge-distillation-network","title":"Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection","date":"2022-11-14","arxiv_id":"2211.07171","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["Cc-Hy/CMKD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"structured-knowledge-distillation-towards","title":"Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection","date":"2022-11-14","arxiv_id":"2211.08398","n_code_links":0,"syntology":null},{"paper":null,"slug":"fan-trans-online-knowledge-distillation-for","title":"FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection","date":"2022-11-11","arxiv_id":"2211.06143","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-distillation-from-cross-teaching","slug":"knowledge-distillation-from-cross-teaching","title":"Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CT","date":"2022-11-11","arxiv_id":"2211.05942","n_code_links":1,"syntology":null},{"paper":null,"slug":"pile-pairwise-iterative-logits-ensemble-for","title":"PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation","date":"2022-11-11","arxiv_id":"2211.06059","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-large-scale-audio-tagging-via","slug":"efficient-large-scale-audio-tagging-via","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","date":"2022-11-09","arxiv_id":"2211.04772","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fschmid56/efficientat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"knowledge-distillation-for-federated-learning","title":"Knowledge Distillation for Federated Learning: a Practical Guide","date":"2022-11-09","arxiv_id":"2211.04742","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-fairness-and-environmental","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","date":"2022-11-08","arxiv_id":"2211.04256","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-the-role-of-mixup-in-knowledge","slug":"understanding-the-role-of-mixup-in-knowledge","title":"Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study","date":"2022-11-08","arxiv_id":"2211.03946","n_code_links":1,"syntology":null},{"paper":"/paper/alphapose-whole-body-regional-multi-person","slug":"alphapose-whole-body-regional-multi-person","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","date":"2022-11-07","arxiv_id":"2211.03375","n_code_links":8,"syntology":null},{"paper":null,"slug":"closing-the-gap-between-client-and-global","title":"Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning","date":"2022-11-07","arxiv_id":"2211.03457","n_code_links":0,"syntology":null},{"paper":"/paper/conmix-for-source-free-single-and-multi","slug":"conmix-for-source-free-single-and-multi","title":"CoNMix for Source-free Single and Multi-target Domain Adaptation","date":"2022-11-07","arxiv_id":"2211.03876","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"2 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["vcl-iisc/CoNMix"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"peak-first-ctc-reducing-the-peak-latency-of","title":"Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization","date":"2022-11-07","arxiv_id":"2211.03284","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-trade-off-in-personalized-speech","title":"Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation","date":"2022-11-05","arxiv_id":"2211.02944","n_code_links":0,"syntology":null},{"paper":"/paper/ssda-yolo-semi-supervised-domain-adaptive","slug":"ssda-yolo-semi-supervised-domain-adaptive","title":"SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection","date":"2022-11-04","arxiv_id":"2211.02213","n_code_links":1,"syntology":null},{"paper":"/paper/gradient-knowledge-distillation-for-pre","slug":"gradient-knowledge-distillation-for-pre","title":"Gradient Knowledge Distillation for Pre-trained Language Models","date":"2022-11-02","arxiv_id":"2211.01071","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":0,"n_instrument":4,"unverified":3,"pointer_only":7,"phrase":"4 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; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lancopku/gkd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lightvessel-exploring-lightweight-coronary","title":"LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation","date":"2022-11-02","arxiv_id":"2211.00899","n_code_links":0,"syntology":null},{"paper":"/paper/mpcformer-fast-performant-and-private","slug":"mpcformer-fast-performant-and-private","title":"MPCFormer: fast, performant and private Transformer inference with MPC","date":"2022-11-02","arxiv_id":"2211.01452","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-level-distillation-of-semantic","title":"Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model","date":"2022-11-02","arxiv_id":"2211.01200","n_code_links":0,"syntology":null},{"paper":null,"slug":"ardir-improving-robustness-using-knowledge","title":"ARDIR: Improving Robustness using Knowledge Distillation of Internal Representation","date":"2022-11-01","arxiv_id":"2211.00239","n_code_links":0,"syntology":null},{"paper":null,"slug":"maximum-likelihood-distillation-for-robust","title":"Maximum Likelihood Distillation for Robust Modulation Classification","date":"2022-11-01","arxiv_id":"2211.00748","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-negative-text-replay-for-continual","title":"Generative Negative Text Replay for Continual Vision-Language Pretraining","date":"2022-10-31","arxiv_id":"2210.17322","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-neural-network-with-knowledge","title":"Lightweight Neural Network with Knowledge Distillation for CSI Feedback","date":"2022-10-31","arxiv_id":"2210.17113","n_code_links":0,"syntology":null},{"paper":"/paper/quala-minilm-a-quantized-length-adaptive","slug":"quala-minilm-a-quantized-length-adaptive","title":"QuaLA-MiniLM: a Quantized Length Adaptive MiniLM","date":"2022-10-31","arxiv_id":"2210.17114","n_code_links":2,"syntology":null},{"paper":null,"slug":"application-of-knowledge-distillation-to","title":"Application of Knowledge Distillation to Multi-task Speech Representation Learning","date":"2022-10-29","arxiv_id":"2210.16611","n_code_links":0,"syntology":null},{"paper":"/paper/bebert-efficient-and-robust-binary-ensemble","slug":"bebert-efficient-and-robust-binary-ensemble","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","date":"2022-10-28","arxiv_id":"2210.15976","n_code_links":1,"syntology":null},{"paper":null,"slug":"completely-heterogeneous-federated-learning","title":"Completely Heterogeneous Federated Learning","date":"2022-10-28","arxiv_id":"2210.15865","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-and-high-fidelity-end-to-end-text","slug":"lightweight-and-high-fidelity-end-to-end-text","title":"Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform","date":"2022-10-28","arxiv_id":"2210.15975","n_code_links":1,"syntology":null},{"paper":null,"slug":"semi-uformer-semi-supervised-uncertainty","title":"Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing","date":"2022-10-28","arxiv_id":"2210.16057","n_code_links":0,"syntology":null},{"paper":null,"slug":"teacher-student-architecture-for-knowledge","title":"Teacher-Student Architecture for Knowledge Learning: A Survey","date":"2022-10-28","arxiv_id":"2210.17332","n_code_links":0,"syntology":null},{"paper":"/paper/a-knowledge-distillation-framework-for","slug":"a-knowledge-distillation-framework-for","title":"A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG Data","date":"2022-10-27","arxiv_id":"2211.02638","n_code_links":1,"syntology":null},{"paper":null,"slug":"collaborative-multi-teacher-knowledge","title":"Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks","date":"2022-10-27","arxiv_id":"2210.16103","n_code_links":0,"syntology":null}],"record_sha256":"82e9f6caf7ce74ef6c2729467dff817b79c68eb978a70a2033aab80aaec2da6f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}