{"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/15","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":15,"pages_in_order":31,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/method/knowledge-distillation/papers/16","papers":[{"paper":"/paper/teacher-agent-a-non-knowledge-distillation","slug":"teacher-agent-a-non-knowledge-distillation","title":"Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-based Video Incremental Learning","date":"2023-06-01","arxiv_id":"2306.00393","n_code_links":1,"syntology":null},{"paper":null,"slug":"accurate-and-structured-pruning-for-efficient","title":"Accurate and Structured Pruning for Efficient Automatic Speech Recognition","date":"2023-05-31","arxiv_id":"2305.19549","n_code_links":0,"syntology":null},{"paper":"/paper/plasma-making-small-language-models-better","slug":"plasma-making-small-language-models-better","title":"PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning","date":"2023-05-31","arxiv_id":"2305.19472","n_code_links":1,"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":["allenai/plasma"],"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/are-large-kernels-better-teachers-than","slug":"are-large-kernels-better-teachers-than","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","date":"2023-05-30","arxiv_id":"2305.19412","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 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) · 0 unverified","official":{"repos":["vita-group/slak"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"keyword-based-sampling-keys-for-large","title":"KEYword based Sampling (KEYS) for Large Language Models","date":"2023-05-30","arxiv_id":"2305.18679","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-multilingual-news-clustering","title":"Research on Multilingual News Clustering Based on Cross-Language Word Embeddings","date":"2023-05-30","arxiv_id":"2305.18880","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-pathological-image","slug":"semi-supervised-pathological-image","title":"Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions","date":"2023-05-30","arxiv_id":"2305.18830","n_code_links":1,"syntology":null},{"paper":null,"slug":"griprank-bridging-the-gap-between-retrieval","title":"GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking","date":"2023-05-29","arxiv_id":"2305.18144","n_code_links":0,"syntology":null},{"paper":"/paper/privileged-knowledge-distillation-for-sim-to","slug":"privileged-knowledge-distillation-for-sim-to","title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","date":"2023-05-29","arxiv_id":"2305.18464","n_code_links":1,"syntology":null},{"paper":null,"slug":"conaclip-exploring-distillation-of-fully","title":"ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval","date":"2023-05-28","arxiv_id":"2305.17652","n_code_links":0,"syntology":null},{"paper":"/paper/dphubert-joint-distillation-and-pruning-of","slug":"dphubert-joint-distillation-and-pruning-of","title":"DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models","date":"2023-05-28","arxiv_id":"2305.17651","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["pyf98/dphubert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/learning-to-learn-from-apis-black-box-data","slug":"learning-to-learn-from-apis-black-box-data","title":"Learning to Learn from APIs: Black-Box Data-Free Meta-Learning","date":"2023-05-28","arxiv_id":"2305.18413","n_code_links":1,"syntology":null},{"paper":"/paper/fopro-kd-fourier-prompted-effective-knowledge","slug":"fopro-kd-fourier-prompted-effective-knowledge","title":"FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image Recognition","date":"2023-05-27","arxiv_id":"2305.17421","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-performs-partial","slug":"knowledge-distillation-performs-partial","title":"Knowledge Distillation Performs Partial Variance Reduction","date":"2023-05-27","arxiv_id":"2305.17581","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["IST-DASLab/KDVR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/one-step-knowledge-distillation-and-fine","slug":"one-step-knowledge-distillation-and-fine","title":"One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification","date":"2023-05-27","arxiv_id":"2305.17394","n_code_links":1,"syntology":null},{"paper":"/paper/towards-better-entity-linking-with-multi-view","slug":"towards-better-entity-linking-with-multi-view","title":"Towards Better Entity Linking with Multi-View Enhanced Distillation","date":"2023-05-27","arxiv_id":"2305.17371","n_code_links":1,"syntology":null},{"paper":"/paper/vision-transformers-for-small-histological","slug":"vision-transformers-for-small-histological","title":"Vision Transformers for Small Histological Datasets Learned through Knowledge Distillation","date":"2023-05-27","arxiv_id":"2305.17370","n_code_links":1,"syntology":null},{"paper":null,"slug":"abc-kd-attention-based-compression-knowledge","title":"ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression","date":"2023-05-26","arxiv_id":"2305.16665","n_code_links":0,"syntology":null},{"paper":"/paper/improving-knowledge-distillation-via-1","slug":"improving-knowledge-distillation-via-1","title":"Improving Knowledge Distillation via Regularizing Feature Norm and Direction","date":"2023-05-26","arxiv_id":"2305.17007","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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","official":{"repos":["wangyz1608/knowledge-distillation-via-nd"],"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/camera-incremental-object-re-identification","slug":"camera-incremental-object-re-identification","title":"Camera-Incremental Object Re-Identification with Identity Knowledge Evolution","date":"2023-05-25","arxiv_id":"2305.15909","n_code_links":1,"syntology":null},{"paper":null,"slug":"collective-knowledge-graph-completion-with","title":"Collective Knowledge Graph Completion with Mutual Knowledge Distillation","date":"2023-05-25","arxiv_id":"2305.15895","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-knowledge-distillation-for","title":"Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages","date":"2023-05-25","arxiv_id":"2305.16302","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairness-continual-learning-approach-to","title":"Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments","date":"2023-05-25","arxiv_id":"2305.15700","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-diffusion-for-distillation-1","slug":"knowledge-diffusion-for-distillation-1","title":"Knowledge Diffusion for Distillation","date":"2023-05-25","arxiv_id":"2305.15712","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-neural-transducer","title":"Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data","date":"2023-05-25","arxiv_id":"2305.15971","n_code_links":0,"syntology":null},{"paper":"/paper/on-architectural-compression-of-text-to-image","slug":"on-architectural-compression-of-text-to-image","title":"BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion","date":"2023-05-25","arxiv_id":"2305.15798","n_code_links":3,"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":["Nota-NetsPresso/BK-SDM","segmind/distill-sd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-the-impact-of-knowledge-distillation-for","title":"On the Impact of Knowledge Distillation for Model Interpretability","date":"2023-05-25","arxiv_id":"2305.15734","n_code_links":0,"syntology":null},{"paper":"/paper/ovo-open-vocabulary-occupancy","slug":"ovo-open-vocabulary-occupancy","title":"OVO: Open-Vocabulary Occupancy","date":"2023-05-25","arxiv_id":"2305.16133","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dzcgaara/OVO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"triplet-knowledge-distillation","title":"Triplet Knowledge Distillation","date":"2023-05-25","arxiv_id":"2305.15975","n_code_links":0,"syntology":null},{"paper":"/paper/vanillakd-revisit-the-power-of-vanilla","slug":"vanillakd-revisit-the-power-of-vanilla","title":"VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale","date":"2023-05-25","arxiv_id":"2305.15781","n_code_links":1,"syntology":null},{"paper":null,"slug":"2305-14700","title":"AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness","date":"2023-05-24","arxiv_id":"2305.14700","n_code_links":0,"syntology":null},{"paper":"/paper/colada-a-collaborative-label-denoising","slug":"colada-a-collaborative-label-denoising","title":"CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition","date":"2023-05-24","arxiv_id":"2305.14913","n_code_links":1,"syntology":null},{"paper":"/paper/how-to-distill-your-bert-an-empirical-study","slug":"how-to-distill-your-bert-an-empirical-study","title":"How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives","date":"2023-05-24","arxiv_id":"2305.15032","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mainlp/how-to-distill-your-bert"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"incorporating-ultrasound-tongue-images-for","title":"Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement through Knowledge Distillation","date":"2023-05-24","arxiv_id":"2305.14933","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-correlated-knowledge-distillation-for","title":"Deakin RF-Sensing: Experiments on Correlated Knowledge Distillation for Monitoring Human Postures with Radios","date":"2023-05-24","arxiv_id":"2305.14829","n_code_links":0,"syntology":null},{"paper":"/paper/decoupled-kullback-leibler-divergence-loss","slug":"decoupled-kullback-leibler-divergence-loss","title":"Decoupled Kullback-Leibler Divergence Loss","date":"2023-05-23","arxiv_id":"2305.13948","n_code_links":4,"syntology":{"ran":11,"of":11,"n_ran_checked":5,"n_instrument":6,"unverified":0,"pointer_only":4,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jiequancui/DKL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/norm-knowledge-distillation-via-n-to-one","slug":"norm-knowledge-distillation-via-n-to-one","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","date":"2023-05-23","arxiv_id":"2305.13803","n_code_links":1,"syntology":{"ran":1,"of":8,"n_ran_checked":1,"n_instrument":0,"unverified":7,"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) · 7 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["osvai/norm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sequence-level-knowledge-distillation-for-1","title":"Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding","date":"2023-05-23","arxiv_id":"2305.13899","n_code_links":0,"syntology":null},{"paper":"/paper/d-2-tv-dual-knowledge-distillation-and-target","slug":"d-2-tv-dual-knowledge-distillation-and-target","title":"D$^2$TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization","date":"2023-05-22","arxiv_id":"2305.12767","n_code_links":1,"syntology":null},{"paper":null,"slug":"ensiam-self-supervised-learning-with-ensemble","title":"EnSiam: Self-Supervised Learning With Ensemble Representations","date":"2023-05-22","arxiv_id":"2305.13391","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-robustness-in-knowledge","title":"Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation","date":"2023-05-22","arxiv_id":"2305.13067","n_code_links":0,"syntology":null},{"paper":"/paper/is-synthetic-data-from-diffusion-models-ready","slug":"is-synthetic-data-from-diffusion-models-ready","title":"Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?","date":"2023-05-22","arxiv_id":"2305.12954","n_code_links":1,"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":["zhengli97/dm-kd"],"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/lion-adversarial-distillation-of-closed","slug":"lion-adversarial-distillation-of-closed","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","date":"2023-05-22","arxiv_id":"2305.12870","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["yjiangcm/lion"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"revisiting-data-augmentation-in-model","title":"Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study","date":"2023-05-22","arxiv_id":"2305.13232","n_code_links":0,"syntology":null},{"paper":null,"slug":"dualvc-dual-mode-voice-conversion-using-intra","title":"DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding","date":"2023-05-21","arxiv_id":"2305.12425","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-effect-of-data-augmentation","title":"Understanding the Effect of Data Augmentation on Knowledge Distillation","date":"2023-05-21","arxiv_id":"2305.12565","n_code_links":0,"syntology":null},{"paper":null,"slug":"accurate-knowledge-distillation-with-n-best","title":"Accurate Knowledge Distillation with n-best Reranking","date":"2023-05-20","arxiv_id":"2305.12057","n_code_links":0,"syntology":null},{"paper":"/paper/lifting-the-curse-of-capacity-gap-in","slug":"lifting-the-curse-of-capacity-gap-in","title":"Lifting the Curse of Capacity Gap in Distilling Language Models","date":"2023-05-20","arxiv_id":"2305.12129","n_code_links":1,"syntology":{"ran":7,"of":13,"n_ran_checked":6,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["genezc/minimoe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/sentence-embedder-guided-utterance-encoder","slug":"sentence-embedder-guided-utterance-encoder","title":"Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding","date":"2023-05-20","arxiv_id":"2305.12301","n_code_links":1,"syntology":null},{"paper":null,"slug":"boost-vision-transformer-with-gpu-friendly-1","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","date":"2023-05-18","arxiv_id":"2305.10727","n_code_links":0,"syntology":null},{"paper":"/paper/catch-up-distillation-you-only-need-to-train","slug":"catch-up-distillation-you-only-need-to-train","title":"Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling","date":"2023-05-18","arxiv_id":"2305.10769","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shaoshitong/Catch-Up-Distillation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"student-friendly-knowledge-distillation","title":"Student-friendly Knowledge Distillation","date":"2023-05-18","arxiv_id":"2305.10893","n_code_links":0,"syntology":null},{"paper":null,"slug":"whisper-kdq-a-lightweight-whisper-via-guided","title":"DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition","date":"2023-05-18","arxiv_id":"2305.10788","n_code_links":0,"syntology":null},{"paper":"/paper/ad-kd-attribution-driven-knowledge","slug":"ad-kd-attribution-driven-knowledge","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","date":"2023-05-17","arxiv_id":"2305.10010","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["brucewsy/ad-kd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tailoring-instructions-to-student-s-learning","slug":"tailoring-instructions-to-student-s-learning","title":"Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation","date":"2023-05-16","arxiv_id":"2305.09651","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["twinkle0331/lgtm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bridging-the-domain-gap-self-supervised-3d","slug":"bridging-the-domain-gap-self-supervised-3d","title":"Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models","date":"2023-05-15","arxiv_id":"2305.08776","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-knowledge-for-short-to-long-term","title":"Distilling Knowledge for Short-to-Long Term Trajectory Prediction","date":"2023-05-15","arxiv_id":"2305.08553","n_code_links":0,"syntology":null},{"paper":null,"slug":"soft-prompt-decoding-for-multilingual-dense","title":"Soft Prompt Decoding for Multilingual Dense Retrieval","date":"2023-05-15","arxiv_id":"2305.09025","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-defensive-distillation-using","title":"Improving Defensive Distillation using Teacher Assistant","date":"2023-05-14","arxiv_id":"2305.08076","n_code_links":0,"syntology":null},{"paper":"/paper/on-enhancing-the-robustness-of-vision","slug":"on-enhancing-the-robustness-of-vision","title":"On enhancing the robustness of Vision Transformers: Defensive Diffusion","date":"2023-05-14","arxiv_id":"2305.08031","n_code_links":1,"syntology":null},{"paper":null,"slug":"black-box-source-free-domain-adaptation-via","title":"Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation","date":"2023-05-13","arxiv_id":"2305.07881","n_code_links":0,"syntology":null},{"paper":"/paper/gsb-group-superposition-binarization-for","slug":"gsb-group-superposition-binarization-for","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","date":"2023-05-13","arxiv_id":"2305.07931","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-lightweight-domain-adversarial-neural","title":"A Lightweight Domain Adversarial Neural Network Based on Knowledge Distillation for EEG-based Cross-subject Emotion Recognition","date":"2023-05-12","arxiv_id":"2305.07446","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-with-segment-anything","title":"Knowledge distillation with Segment Anything (SAM) model for Planetary Geological Mapping","date":"2023-05-12","arxiv_id":"2305.07586","n_code_links":0,"syntology":null},{"paper":"/paper/improving-continual-relation-extraction-by","slug":"improving-continual-relation-extraction-by","title":"Improving Continual Relation Extraction by Distinguishing Analogous Semantics","date":"2023-05-11","arxiv_id":"2305.06620","n_code_links":1,"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":["nju-websoft/cear"],"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/long-tailed-question-answering-in-an-open","slug":"long-tailed-question-answering-in-an-open","title":"Long-Tailed Question Answering in an Open World","date":"2023-05-11","arxiv_id":"2305.06557","n_code_links":1,"syntology":null},{"paper":"/paper/serial-contrastive-knowledge-distillation-for","slug":"serial-contrastive-knowledge-distillation-for","title":"Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction","date":"2023-05-11","arxiv_id":"2305.06616","n_code_links":1,"syntology":null},{"paper":null,"slug":"explainable-knowledge-distillation-for-on","title":"Explainable Knowledge Distillation for On-device Chest X-Ray Classification","date":"2023-05-10","arxiv_id":"2305.06244","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamickd-an-effective-knowledge-distillation","title":"DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing","date":"2023-05-09","arxiv_id":"2305.05233","n_code_links":0,"syntology":null},{"paper":"/paper/fednoro-towards-noise-robust-federated","slug":"fednoro-towards-noise-robust-federated","title":"FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity","date":"2023-05-09","arxiv_id":"2305.05230","n_code_links":3,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["wnn2000/fednoro"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-teacher-knowledge-distillation-for-text","slug":"multi-teacher-knowledge-distillation-for-text","title":"Multi-Teacher Knowledge Distillation For Text Image Machine Translation","date":"2023-05-09","arxiv_id":"2305.05226","n_code_links":1,"syntology":null},{"paper":null,"slug":"sril-selective-regularization-for-class","title":"SRIL: Selective Regularization for Class-Incremental Learning","date":"2023-05-09","arxiv_id":"2305.05175","n_code_links":0,"syntology":null},{"paper":"/paper/sur-adapter-enhancing-text-to-image-pre","slug":"sur-adapter-enhancing-text-to-image-pre","title":"SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models","date":"2023-05-09","arxiv_id":"2305.05189","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["Qrange-group/SUR-adapter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"do-not-blindly-imitate-the-teacher-using","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","date":"2023-05-08","arxiv_id":"2305.05010","n_code_links":0,"syntology":null},{"paper":"/paper/neurocomparatives-neuro-symbolic-distillation","slug":"neurocomparatives-neuro-symbolic-distillation","title":"NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge","date":"2023-05-08","arxiv_id":"2305.04978","n_code_links":1,"syntology":null},{"paper":null,"slug":"web-content-filtering-through-knowledge","title":"Web Content Filtering through knowledge distillation of Large Language Models","date":"2023-05-08","arxiv_id":"2305.05027","n_code_links":0,"syntology":null},{"paper":null,"slug":"structural-and-statistical-texture-knowledge-1","title":"Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation","date":"2023-05-06","arxiv_id":"2305.03944","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilled-mid-fusion-transformer-networks-for","title":"Distilled Mid-Fusion Transformer Networks for Multi-Modal Human Activity Recognition","date":"2023-05-05","arxiv_id":"2305.03810","n_code_links":0,"syntology":null},{"paper":"/paper/avatar-knowledge-distillation-self-ensemble","slug":"avatar-knowledge-distillation-self-ensemble","title":"Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty","date":"2023-05-04","arxiv_id":"2305.02722","n_code_links":1,"syntology":null},{"paper":"/paper/smaller3d-smaller-models-for-3d-semantic","slug":"smaller3d-smaller-models-for-3d-semantic","title":"Smaller3d: Smaller Models for 3D Semantic Segmentation Using Minkowski Engine and Knowledge Distillation Methods","date":"2023-05-04","arxiv_id":"2305.03188","n_code_links":1,"syntology":null},{"paper":"/paper/a-systematic-study-of-knowledge-distillation","slug":"a-systematic-study-of-knowledge-distillation","title":"A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training","date":"2023-05-03","arxiv_id":"2305.02031","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["nitaytech/kd4gen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/scott-self-consistent-chain-of-thought","slug":"scott-self-consistent-chain-of-thought","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","date":"2023-05-03","arxiv_id":"2305.01879","n_code_links":1,"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":["wangpf3/consistent-cot-distillation"],"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/deepaqua-self-supervised-semantic","slug":"deepaqua-self-supervised-semantic","title":"DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation","date":"2023-05-02","arxiv_id":"2305.01698","n_code_links":1,"syntology":null},{"paper":null,"slug":"distill-or-annotate-cost-efficient-fine","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","date":"2023-05-02","arxiv_id":"2305.01645","n_code_links":0,"syntology":null},{"paper":null,"slug":"structure-aware-incremental-learning-with","title":"Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems","date":"2023-05-02","arxiv_id":"2305.01204","n_code_links":0,"syntology":null},{"paper":"/paper/scaffolding-a-student-to-instill-knowledge","slug":"scaffolding-a-student-to-instill-knowledge","title":"Scaffolding a Student to Instill Knowledge","date":"2023-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/ensemble-modeling-with-contrastive-knowledge","slug":"ensemble-modeling-with-contrastive-knowledge","title":"Ensemble Modeling with Contrastive Knowledge Distillation for Sequential Recommendation","date":"2023-04-28","arxiv_id":"2304.14668","n_code_links":1,"syntology":null},{"paper":"/paper/multi-to-single-knowledge-distillation-for","slug":"multi-to-single-knowledge-distillation-for","title":"Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation","date":"2023-04-28","arxiv_id":"2304.14800","n_code_links":1,"syntology":null},{"paper":"/paper/learning-human-human-interactions-in-images","slug":"learning-human-human-interactions-in-images","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","date":"2023-04-27","arxiv_id":"2304.14104","n_code_links":0,"syntology":null},{"paper":"/paper/a-symmetric-dual-encoding-dense-retrieval","slug":"a-symmetric-dual-encoding-dense-retrieval","title":"A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering","date":"2023-04-26","arxiv_id":"2304.13649","n_code_links":1,"syntology":null},{"paper":"/paper/class-attention-transfer-based-knowledge","slug":"class-attention-transfer-based-knowledge","title":"Class Attention Transfer Based Knowledge Distillation","date":"2023-04-25","arxiv_id":"2304.12777","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gzyaftermath/cat-kd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/few-shot-class-incremental-pill-recognition","slug":"few-shot-class-incremental-pill-recognition","title":"A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition","date":"2023-04-24","arxiv_id":"2304.11959","n_code_links":1,"syntology":null},{"paper":"/paper/improving-knowledge-distillation-via","slug":"improving-knowledge-distillation-via","title":"Improving Knowledge Distillation via Transferring Learning Ability","date":"2023-04-24","arxiv_id":"2304.11923","n_code_links":1,"syntology":null},{"paper":null,"slug":"interruption-aware-cooperative-perception-for","title":"Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving","date":"2023-04-24","arxiv_id":"2304.11821","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-distillation-from-3d-to-bird-s-eye","slug":"knowledge-distillation-from-3d-to-bird-s-eye","title":"Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation","date":"2023-04-22","arxiv_id":"2304.11393","n_code_links":1,"syntology":null},{"paper":null,"slug":"decouple-non-parametric-knowledge","title":"Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation","date":"2023-04-20","arxiv_id":"2304.10295","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-leveraging-knowledge","slug":"an-empirical-study-of-leveraging-knowledge","title":"An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models","date":"2023-04-19","arxiv_id":"2304.09388","n_code_links":1,"syntology":null},{"paper":"/paper/attention-weighted-local-descriptors","slug":"attention-weighted-local-descriptors","title":"Attention Weighted Local Descriptors","date":"2023-04-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"biologically-inspired-structure-learning-with","title":"Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks","date":"2023-04-19","arxiv_id":"2304.09500","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-under-ideal-joint","title":"Knowledge Distillation Under Ideal Joint Classifier Assumption","date":"2023-04-19","arxiv_id":"2304.11004","n_code_links":0,"syntology":null}],"record_sha256":"c8b53d124e0100308282447de1627250064190b8e5b582e1be07b315f50a3c42","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}