{"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/14","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":14,"pages_in_order":31,"rows_per_page":100,"rows":[1301,1400],"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/13","next":"/method/knowledge-distillation/papers/15","papers":[{"paper":"/paper/vqgraph-graph-vector-quantization-for","slug":"vqgraph-graph-vector-quantization-for","title":"VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs","date":"2023-08-04","arxiv_id":"2308.02117","n_code_links":1,"syntology":{"ran":23,"of":30,"n_ran_checked":10,"n_instrument":13,"unverified":7,"pointer_only":30,"phrase":"23 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 4 violated, 5 with no contract checked; 13 where Syntology's instrument failed) · 7 unverified","official":{"repos":["yangling0818/vqgraph"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":1,"n_ran_no_instrument_failure":10,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-vision-transformer-based-framework-for","title":"A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models","date":"2023-08-02","arxiv_id":"2308.01328","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-generic-enhancing-image-captioning","slug":"beyond-generic-enhancing-image-captioning","title":"Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model","date":"2023-08-02","arxiv_id":"2308.01126","n_code_links":1,"syntology":null},{"paper":"/paper/improved-knowledge-distillation-for-crowd","slug":"improved-knowledge-distillation-for-crowd","title":"Improved Knowledge Distillation for Crowd Counting on IoT Device","date":"2023-08-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-expert-models-for-training-deep","title":"Leveraging Expert Models for Training Deep Neural Networks in Scarce Data Domains: Application to Offline Handwritten Signature Verification","date":"2023-08-02","arxiv_id":"2308.01136","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-better-query-classification-with","title":"Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search","date":"2023-08-02","arxiv_id":"2308.01098","n_code_links":0,"syntology":null},{"paper":null,"slug":"ada-dqa-adaptive-diverse-quality-aware","title":"Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment","date":"2023-08-01","arxiv_id":"2308.00729","n_code_links":0,"syntology":null},{"paper":"/paper/normkd-normalized-logits-for-knowledge","slug":"normkd-normalized-logits-for-knowledge","title":"NormKD: Normalized Logits for Knowledge Distillation","date":"2023-08-01","arxiv_id":"2308.00520","n_code_links":1,"syntology":null},{"paper":"/paper/online-prototype-learning-for-online","slug":"online-prototype-learning-for-online","title":"Online Prototype Learning for Online Continual Learning","date":"2023-08-01","arxiv_id":"2308.00301","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":["weilllllls/onpro"],"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":"federated-learning-for-data-and-model","title":"Federated Learning for Data and Model Heterogeneity in Medical Imaging","date":"2023-07-31","arxiv_id":"2308.00155","n_code_links":0,"syntology":null},{"paper":null,"slug":"sampling-to-distill-knowledge-transfer-from","title":"Sampling to Distill: Knowledge Transfer from Open-World Data","date":"2023-07-31","arxiv_id":"2307.16601","n_code_links":0,"syntology":null},{"paper":"/paper/subspace-distillation-for-continual-learning","slug":"subspace-distillation-for-continual-learning","title":"Subspace Distillation for Continual Learning","date":"2023-07-31","arxiv_id":"2307.16419","n_code_links":1,"syntology":null},{"paper":null,"slug":"upfl-unsupervised-personalized-federated","title":"UPFL: Unsupervised Personalized Federated Learning towards New Clients","date":"2023-07-29","arxiv_id":"2307.15994","n_code_links":0,"syntology":null},{"paper":"/paper/f-divergence-minimization-for-sequence-level","slug":"f-divergence-minimization-for-sequence-level","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","date":"2023-07-27","arxiv_id":"2307.15190","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"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) · 1 unverified","official":{"repos":["manga-uofa/fdistill"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/fitting-auditory-filterbanks-with","slug":"fitting-auditory-filterbanks-with","title":"Fitting Auditory Filterbanks with Multiresolution Neural Networks","date":"2023-07-25","arxiv_id":"2307.13821","n_code_links":2,"syntology":null},{"paper":null,"slug":"mitigating-cross-client-gans-based-attack-in","title":"Mitigating Cross-client GANs-based Attack in Federated Learning","date":"2023-07-25","arxiv_id":"2307.13314","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-good-student-is-cooperative-and-reliable","title":"A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation","date":"2023-07-24","arxiv_id":"2307.12574","n_code_links":0,"syntology":null},{"paper":null,"slug":"hetefedrec-federated-recommender-systems-with","title":"HeteFedRec: Federated Recommender Systems with Model Heterogeneity","date":"2023-07-24","arxiv_id":"2307.12810","n_code_links":0,"syntology":null},{"paper":null,"slug":"distribution-shift-matters-for-knowledge","title":"Distribution Shift Matters for Knowledge Distillation with Webly Collected Images","date":"2023-07-21","arxiv_id":"2307.11469","n_code_links":0,"syntology":null},{"paper":"/paper/dpm-ot-a-new-diffusion-probabilistic-model","slug":"dpm-ot-a-new-diffusion-probabilistic-model","title":"DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport","date":"2023-07-21","arxiv_id":"2307.11308","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":7,"n_instrument":2,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["cognaclee/dpm-ot"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/cluster-aware-semi-supervised-learning","slug":"cluster-aware-semi-supervised-learning","title":"Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering","date":"2023-07-20","arxiv_id":"2307.11030","n_code_links":1,"syntology":{"ran":15,"of":18,"n_ran_checked":14,"n_instrument":1,"unverified":3,"pointer_only":5,"phrase":"15 ran (of which 3 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"quantized-feature-distillation-for-network","title":"Quantized Feature Distillation for Network Quantization","date":"2023-07-20","arxiv_id":"2307.10638","n_code_links":0,"syntology":null},{"paper":"/paper/reverse-knowledge-distillation-training-a","slug":"reverse-knowledge-distillation-training-a","title":"Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited Data","date":"2023-07-20","arxiv_id":"2307.10698","n_code_links":1,"syntology":null},{"paper":"/paper/lightpath-lightweight-and-scalable-path","slug":"lightpath-lightweight-and-scalable-path","title":"LightPath: Lightweight and Scalable Path Representation Learning","date":"2023-07-19","arxiv_id":"2307.10171","n_code_links":1,"syntology":null},{"paper":"/paper/class-relation-knowledge-distillation-for","slug":"class-relation-knowledge-distillation-for","title":"Class-relation Knowledge Distillation for Novel Class Discovery","date":"2023-07-18","arxiv_id":"2307.09158","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":1,"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":["kleinzcy/cr-kd-ncd"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"knowledge-distillation-for-object-detection-1","title":"Knowledge Distillation for Object Detection: from generic to remote sensing datasets","date":"2023-07-18","arxiv_id":"2307.09264","n_code_links":0,"syntology":null},{"paper":null,"slug":"teach-model-to-answer-questions-after","title":"Teach model to answer questions after comprehending the document","date":"2023-07-18","arxiv_id":"2307.08931","n_code_links":0,"syntology":null},{"paper":"/paper/cumulative-spatial-knowledge-distillation-for","slug":"cumulative-spatial-knowledge-distillation-for","title":"Cumulative Spatial Knowledge Distillation for Vision Transformers","date":"2023-07-17","arxiv_id":"2307.08500","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["Zzzzz1/CSKD"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"domain-knowledge-distillation-from-large","title":"Domain Knowledge Distillation from Large Language Model: An Empirical Study in the Autonomous Driving Domain","date":"2023-07-17","arxiv_id":"2307.11769","n_code_links":0,"syntology":null},{"paper":"/paper/improving-end-to-end-speech-translation-by-2","slug":"improving-end-to-end-speech-translation-by-2","title":"Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts","date":"2023-07-17","arxiv_id":"2307.08426","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-lingual-ner-for-financial-transaction","title":"Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages","date":"2023-07-16","arxiv_id":"2307.08714","n_code_links":0,"syntology":null},{"paper":null,"slug":"mint-boosting-generalization-in-mathematical","title":"MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning","date":"2023-07-16","arxiv_id":"2307.07951","n_code_links":0,"syntology":null},{"paper":null,"slug":"intuitive-access-to-smartphone-settings-using","title":"Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning","date":"2023-07-15","arxiv_id":"2307.09177","n_code_links":0,"syntology":null},{"paper":null,"slug":"soccerkdnet-a-knowledge-distillation","title":"SoccerKDNet: A Knowledge Distillation Framework for Action Recognition in Soccer Videos","date":"2023-07-15","arxiv_id":"2307.07768","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-retrieve-in-context-examples-for","slug":"learning-to-retrieve-in-context-examples-for","title":"Learning to Retrieve In-Context Examples for Large Language Models","date":"2023-07-14","arxiv_id":"2307.07164","n_code_links":2,"syntology":null},{"paper":"/paper/multimodal-distillation-for-egocentric-action","slug":"multimodal-distillation-for-egocentric-action","title":"Multimodal Distillation for Egocentric Action Recognition","date":"2023-07-14","arxiv_id":"2307.07483","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["gorjanradevski/multimodal-distillation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-metric-learning-approach-for-endoscopic","title":"A metric learning approach for endoscopic kidney stone identification","date":"2023-07-13","arxiv_id":"2307.07046","n_code_links":0,"syntology":null},{"paper":"/paper/regression-oriented-knowledge-distillation","slug":"regression-oriented-knowledge-distillation","title":"Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images","date":"2023-07-13","arxiv_id":"2307.06566","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-staged-knowledge-distillation-in-video","title":"The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework","date":"2023-07-11","arxiv_id":"2307.05201","n_code_links":0,"syntology":null},{"paper":"/paper/customizing-synthetic-data-for-data-free","slug":"customizing-synthetic-data-for-data-free","title":"Customizing Synthetic Data for Data-Free Student Learning","date":"2023-07-10","arxiv_id":"2307.04542","n_code_links":1,"syntology":null},{"paper":"/paper/mclip-multilingual-clip-via-cross-lingual","slug":"mclip-multilingual-clip-via-cross-lingual","title":"mCLIP: Multilingual CLIP via Cross-lingual Transfer","date":"2023-07-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/cmdfusion-bidirectional-fusion-network-with","slug":"cmdfusion-bidirectional-fusion-network-with","title":"CMDFusion: Bidirectional Fusion Network with Cross-modality Knowledge Distillation for LIDAR Semantic Segmentation","date":"2023-07-09","arxiv_id":"2307.04091","n_code_links":1,"syntology":null},{"paper":"/paper/distilling-universal-and-joint-knowledge-for","slug":"distilling-universal-and-joint-knowledge-for","title":"Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data","date":"2023-07-07","arxiv_id":"2307.03347","n_code_links":1,"syntology":null},{"paper":"/paper/contextual-affinity-distillation-for-image","slug":"contextual-affinity-distillation-for-image","title":"Contextual Affinity Distillation for Image Anomaly Detection","date":"2023-07-06","arxiv_id":"2307.03101","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-device-constrained-self-supervised-speech","title":"On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation","date":"2023-07-06","arxiv_id":"2307.02720","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-missing-modality-knowledge-from","title":"Distilling Missing Modality Knowledge from Ultrasound for Endometriosis Diagnosis with Magnetic Resonance Images","date":"2023-07-05","arxiv_id":"2307.02000","n_code_links":0,"syntology":null},{"paper":"/paper/mdvit-multi-domain-vision-transformer-for","slug":"mdvit-multi-domain-vision-transformer-for","title":"MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets","date":"2023-07-05","arxiv_id":"2307.02100","n_code_links":2,"syntology":null},{"paper":"/paper/kdstm-neural-semi-supervised-topic-modeling","slug":"kdstm-neural-semi-supervised-topic-modeling","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","date":"2023-07-04","arxiv_id":"2307.01878","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 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) · 2 unverified","official":null}},{"paper":null,"slug":"review-helps-learn-better-temporal-supervised","title":"Review helps learn better: Temporal Supervised Knowledge Distillation","date":"2023-07-03","arxiv_id":"2307.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"shared-growth-of-graph-neural-networks-via","title":"Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation","date":"2023-07-02","arxiv_id":"2307.00534","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-tailed-continual-learning-for-visual","title":"Long-Tailed Continual Learning For Visual Food Recognition","date":"2023-07-01","arxiv_id":"2307.00183","n_code_links":0,"syntology":null},{"paper":"/paper/variation-aware-vision-transformer","slug":"variation-aware-vision-transformer","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","date":"2023-07-01","arxiv_id":"2307.00331","n_code_links":2,"syntology":null},{"paper":"/paper/audio-embeddings-as-teachers-for-music","slug":"audio-embeddings-as-teachers-for-music","title":"Audio Embeddings as Teachers for Music Classification","date":"2023-06-30","arxiv_id":"2306.17424","n_code_links":1,"syntology":null},{"paper":"/paper/naturalinversion-data-free-image-synthesis","slug":"naturalinversion-data-free-image-synthesis","title":"NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency","date":"2023-06-29","arxiv_id":"2306.16661","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["kdst-team/naturalinversion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"streaming-egocentric-action-anticipation-an","title":"Streaming egocentric action anticipation: An evaluation scheme and approach","date":"2023-06-29","arxiv_id":"2306.16682","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-overfitting-of-the-episodic","title":"Understanding the Overfitting of the Episodic Meta-training","date":"2023-06-29","arxiv_id":"2306.16873","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dimensional-structure-based-knowledge","title":"A Dimensional Structure based Knowledge Distillation Method for Cross-Modal Learning","date":"2023-06-28","arxiv_id":"2306.15977","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-the-accuracy-robustness-trade-off","slug":"mitigating-the-accuracy-robustness-trade-off","title":"Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation","date":"2023-06-28","arxiv_id":"2306.16170","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":["zhaoshiji123/mtard-extension"],"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","unlocated"]}}},{"paper":"/paper/exploring-dual-model-knowledge-distillation","slug":"exploring-dual-model-knowledge-distillation","title":"Exploring Dual Model Knowledge Distillation for Anomaly Detection","date":"2023-06-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reducing-the-gap-between-streaming-and-non","title":"Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation","date":"2023-06-27","arxiv_id":"2306.15171","n_code_links":0,"syntology":null},{"paper":null,"slug":"shoggoth-towards-efficient-edge-cloud","title":"Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning","date":"2023-06-27","arxiv_id":"2306.15333","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-molecular-graph-neural-networks","title":"Accelerating Molecular Graph Neural Networks via Knowledge Distillation","date":"2023-06-26","arxiv_id":"2306.14818","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-architecture-distillation-for-face","title":"Cross Architecture Distillation for Face Recognition","date":"2023-06-26","arxiv_id":"2306.14662","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-learning-on-non-iid-data-via-local","title":"Federated Learning on Non-iid Data via Local and Global Distillation","date":"2023-06-26","arxiv_id":"2306.14443","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-mapless-trajectory-prediction","title":"Enhancing Mapless Trajectory Prediction through Knowledge Distillation","date":"2023-06-25","arxiv_id":"2306.14177","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-adversarial-distillation-for-point","title":"Feature Adversarial Distillation for Point Cloud Classification","date":"2023-06-25","arxiv_id":"2306.14221","n_code_links":0,"syntology":null},{"paper":null,"slug":"gkd-generalized-knowledge-distillation-for","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","date":"2023-06-23","arxiv_id":"2306.13649","n_code_links":0,"syntology":null},{"paper":"/paper/depth-and-dof-cues-make-a-better-defocus-blur","slug":"depth-and-dof-cues-make-a-better-defocus-blur","title":"Depth and DOF Cues Make A Better Defocus Blur Detector","date":"2023-06-20","arxiv_id":"2306.11334","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-via-token-level","title":"Knowledge Distillation via Token-level Relationship Graph","date":"2023-06-20","arxiv_id":"2306.12442","n_code_links":0,"syntology":null},{"paper":null,"slug":"categories-of-response-based-feature-based","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","date":"2023-06-19","arxiv_id":"2306.10687","n_code_links":0,"syntology":null},{"paper":null,"slug":"fsar-federated-skeleton-based-action","title":"FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation","date":"2023-06-19","arxiv_id":"2306.11046","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-learning-for-multi-label","title":"Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Study","date":"2023-06-18","arxiv_id":"2306.10494","n_code_links":0,"syntology":null},{"paper":"/paper/coaching-a-teachable-student-1","slug":"coaching-a-teachable-student-1","title":"Coaching a Teachable Student","date":"2023-06-16","arxiv_id":"2306.10014","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["h2xlab/CaT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"knowledge-distillation-for-efficient-audio","title":"Knowledge Distillation for Efficient Audio-Visual Video Captioning","date":"2023-06-16","arxiv_id":"2306.09947","n_code_links":0,"syntology":null},{"paper":"/paper/mixedteacher-knowledge-distillation-for-fast","slug":"mixedteacher-knowledge-distillation-for-fast","title":"MixedTeacher : Knowledge Distillation for fast inference textural anomaly detection","date":"2023-06-16","arxiv_id":"2306.09859","n_code_links":1,"syntology":null},{"paper":null,"slug":"squeezing-nnu-nets-with-knowledge","title":"Squeezing nnU-Nets with Knowledge Distillation for On-Board Cloud Detection","date":"2023-06-16","arxiv_id":"2306.09886","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-the-gap-between-decision-and-logits","slug":"bridging-the-gap-between-decision-and-logits","title":"Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models","date":"2023-06-15","arxiv_id":"2306.08909","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":["thunlp-mt/dbkd-plm"],"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":null,"slug":"self-knowledge-distillation-for-surgical","title":"Self-Knowledge Distillation for Surgical Phase Recognition","date":"2023-06-15","arxiv_id":"2306.08961","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-continual-learning-1","title":"Heterogeneous Continual Learning","date":"2023-06-14","arxiv_id":"2306.08593","n_code_links":0,"syntology":null},{"paper":"/paper/bpkd-boundary-privileged-knowledge","slug":"bpkd-boundary-privileged-knowledge","title":"BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation","date":"2023-06-13","arxiv_id":"2306.08075","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-multimodal-representation-learning-1","title":"Enhanced Multimodal Representation Learning with Cross-modal KD","date":"2023-06-13","arxiv_id":"2306.07646","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-multi-teacher-knowledge-distillation","slug":"adaptive-multi-teacher-knowledge-distillation","title":"Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning","date":"2023-06-11","arxiv_id":"2306.06634","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":["rorozhl/mmkd"],"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-intermediate-layers-and-labels-really","slug":"are-intermediate-layers-and-labels-really","title":"Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method","date":"2023-06-11","arxiv_id":"2306.06625","n_code_links":1,"syntology":null},{"paper":"/paper/easyguide-esg-issue-identification-framework","slug":"easyguide-esg-issue-identification-framework","title":"EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models","date":"2023-06-11","arxiv_id":"2306.06662","n_code_links":1,"syntology":null},{"paper":"/paper/gkd-a-general-knowledge-distillation","slug":"gkd-a-general-knowledge-distillation","title":"GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model","date":"2023-06-11","arxiv_id":"2306.06629","n_code_links":1,"syntology":null},{"paper":"/paper/rankformer-listwise-learning-to-rank-using","slug":"rankformer-listwise-learning-to-rank-using","title":"RankFormer: Listwise Learning-to-Rank Using Listwide Labels","date":"2023-06-09","arxiv_id":"2306.05808","n_code_links":1,"syntology":null},{"paper":null,"slug":"boot-data-free-distillation-of-denoising","title":"BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping","date":"2023-06-08","arxiv_id":"2306.05544","n_code_links":0,"syntology":null},{"paper":null,"slug":"population-based-evolutionary-gaming-for","title":"Population-Based Evolutionary Gaming for Unsupervised Person Re-identification","date":"2023-06-08","arxiv_id":"2306.05236","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-economic-trade-offs-of-large-language","title":"The economic trade-offs of large language models: A case study","date":"2023-06-08","arxiv_id":"2306.07402","n_code_links":0,"syntology":null},{"paper":"/paper/vid2act-activate-offline-videos-for-visual-rl","slug":"vid2act-activate-offline-videos-for-visual-rl","title":"Model-Based Reinforcement Learning with Multi-Task Offline Pretraining","date":"2023-06-06","arxiv_id":"2306.03360","n_code_links":1,"syntology":null},{"paper":"/paper/joint-pre-training-and-local-re-training","slug":"joint-pre-training-and-local-re-training","title":"Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge Graphs","date":"2023-06-05","arxiv_id":"2306.02679","n_code_links":1,"syntology":null},{"paper":"/paper/unveiling-the-two-faced-truth-disentangling","slug":"unveiling-the-two-faced-truth-disentangling","title":"Unveiling the Two-Faced Truth: Disentangling Morphed Identities for Face Morphing Detection","date":"2023-06-05","arxiv_id":"2306.03002","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-framework-for-satellite-image","title":"Zero shot framework for satellite image restoration","date":"2023-06-05","arxiv_id":"2306.02921","n_code_links":0,"syntology":null},{"paper":"/paper/i-3-retriever-incorporating-implicit","slug":"i-3-retriever-incorporating-implicit","title":"I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval","date":"2023-06-04","arxiv_id":"2306.02371","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["deriq-qian-dong/iii-retriever"],"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":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-data-free-knowledge-distillation","slug":"revisiting-data-free-knowledge-distillation","title":"Revisiting Data-Free Knowledge Distillation with Poisoned Teachers","date":"2023-06-04","arxiv_id":"2306.02368","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["illidanlab/abd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-classifier-mimicry-without-data-access","slug":"deep-classifier-mimicry-without-data-access","title":"Deep Classifier Mimicry without Data Access","date":"2023-06-03","arxiv_id":"2306.02090","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-multi-grained-knowledge-reuse-for","slug":"efficient-multi-grained-knowledge-reuse-for","title":"Evolving Knowledge Mining for Class Incremental Segmentation","date":"2023-06-03","arxiv_id":"2306.02027","n_code_links":1,"syntology":null},{"paper":"/paper/group-channel-pruning-and-spatial-attention","slug":"group-channel-pruning-and-spatial-attention","title":"Group channel pruning and spatial attention distilling for object detection","date":"2023-06-02","arxiv_id":"2306.01526","n_code_links":1,"syntology":null},{"paper":null,"slug":"speech-translation-with-foundation-models-and","title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","date":"2023-06-02","arxiv_id":"2306.01327","n_code_links":0,"syntology":null}],"record_sha256":"9c2fde2114df98e05b2d76a8aa5b5606ec9cd32b4b8c32a6b115da2f3969519c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}