{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/knowledge-distillation/papers/30","list_of":"/task/knowledge-distillation","task":"Knowledge Distillation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":30,"pages_in_order":43,"rows_per_page":100,"rows":[2901,3000],"of":4240,"counts":{"archive_papers_tagged":4240,"with_a_code_link":1740,"where_syntology_ran_a_sample":451,"not_listed_spam_title":0,"listed":4240,"listed_where_code_ran":451,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":380,"every_run_a_failure_of_syntologys_instrument":71,"listed_with_a_run_with_no_instrument_failure":380,"listed_every_run_a_failure_of_syntologys_instrument":71,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/knowledge-distillation","prev":"/task/knowledge-distillation/papers/29","next":"/task/knowledge-distillation/papers/31","papers":[{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"triplet-knowledge-distillation","title":"Triplet Knowledge Distillation","date":"2023-05-25","arxiv_id":"2305.15975","repositories_listed":0,"syntology":null},{"url":null,"slug":"2305-14700","title":"AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness","date":"2023-05-24","arxiv_id":"2305.14700","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-hard-augmentations-for-robust","title":"HARD: Hard Augmentations for Robust Distillation","date":"2023-05-24","arxiv_id":"2305.14890","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-distillation-doesn-t","title":"Just CHOP: Embarrassingly Simple LLM Compression","date":"2023-05-24","arxiv_id":"2305.14864","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-stop-training-of-multiple-capacity-models","title":"One-stop Training of Multiple Capacity Models","date":"2023-05-23","arxiv_id":"2305.14066","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-learning-trajectories-of-neural","title":"Transferring Learning Trajectories of Neural Networks","date":"2023-05-23","arxiv_id":"2305.14122","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensiam-self-supervised-learning-with-ensemble","title":"EnSiam: Self-Supervised Learning With Ensemble Representations","date":"2023-05-22","arxiv_id":"2305.13391","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-federated-learning-for-leo","title":"One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes","date":"2023-05-21","arxiv_id":"2305.12316","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-knowledge-distillation-with-n-best","title":"Accurate Knowledge Distillation with n-best Reranking","date":"2023-05-20","arxiv_id":"2305.12057","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudo-label-training-and-model-inertia-in","title":"Pseudo-Label Training and Model Inertia in Neural Machine Translation","date":"2023-05-19","arxiv_id":"2305.11808","repositories_listed":0,"syntology":null},{"url":null,"slug":"berm-training-the-balanced-and-extractable","title":"BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval","date":"2023-05-18","arxiv_id":"2305.11052","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"student-friendly-knowledge-distillation","title":"Student-friendly Knowledge Distillation","date":"2023-05-18","arxiv_id":"2305.10893","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-gradient-descent-meets-derivative-free","title":"When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario","date":"2023-05-17","arxiv_id":"2305.10013","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-prompt-decoding-for-multilingual-dense","title":"Soft Prompt Decoding for Multilingual Dense Retrieval","date":"2023-05-15","arxiv_id":"2305.09025","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-compression-techniques-for-computer","title":"Analyzing Compression Techniques for Computer Vision","date":"2023-05-14","arxiv_id":"2305.08075","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-defensive-distillation-using","title":"Improving Defensive Distillation using Teacher Assistant","date":"2023-05-14","arxiv_id":"2305.08076","repositories_listed":0,"syntology":null},{"url":null,"slug":"amtss-an-adaptive-multi-teacher-single","title":"AMTSS: An Adaptive Multi-Teacher Single-Student Knowledge Distillation Framework For Multilingual Language Inference","date":"2023-05-13","arxiv_id":"2305.07928","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"sril-selective-regularization-for-class","title":"SRIL: Selective Regularization for Class-Incremental Learning","date":"2023-05-09","arxiv_id":"2305.05175","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"corsd-class-oriented-relational-self","title":"CORSD: Class-Oriented Relational Self Distillation","date":"2023-04-28","arxiv_id":"2305.00918","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"shape-net-room-layout-estimation-from","title":"Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs","date":"2023-04-25","arxiv_id":"2304.12624","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-sense-induction-with-knowledge-1","title":"Word Sense Induction with Knowledge Distillation from BERT","date":"2023-04-20","arxiv_id":"2304.10642","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-under-ideal-joint","title":"Knowledge Distillation Under Ideal Joint Classifier Assumption","date":"2023-04-19","arxiv_id":"2304.11004","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-collective-knowledge-distillation","title":"Deep Collective Knowledge Distillation","date":"2023-04-18","arxiv_id":"2304.08878","repositories_listed":0,"syntology":null},{"url":null,"slug":"always-strengthen-your-strengths-a-drift","title":"Always Strengthen Your Strengths: A Drift-Aware Incremental Learning Framework for CTR Prediction","date":"2023-04-17","arxiv_id":"2304.09062","repositories_listed":0,"syntology":null},{"url":null,"slug":"lasnn-layer-wise-ann-to-snn-distillation-for","title":"LaSNN: Layer-wise ANN-to-SNN Distillation for Effective and Efficient Training in Deep Spiking Neural Networks","date":"2023-04-17","arxiv_id":"2304.09101","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-incremental-learning-of-plant-and","title":"Class-Incremental Learning of Plant and Disease Detection: Growing Branches with Knowledge Distillation","date":"2023-04-13","arxiv_id":"2304.06619","repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-deep-spiking-neural-networks","title":"Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation","date":"2023-04-12","arxiv_id":"2304.05627","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-recent-teacher-student-learning","title":"A Survey on Recent Teacher-student Learning Studies","date":"2023-04-10","arxiv_id":"2304.04615","repositories_listed":0,"syntology":null},{"url":null,"slug":"grouped-knowledge-distillation-for-deep-face","title":"Grouped Knowledge Distillation for Deep Face Recognition","date":"2023-04-10","arxiv_id":"2304.04462","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-knowledge","title":"A Comprehensive Survey on Knowledge Distillation of Diffusion Models","date":"2023-04-09","arxiv_id":"2304.04262","repositories_listed":0,"syntology":null},{"url":null,"slug":"homogenizing-non-iid-datasets-via-in","title":"Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning","date":"2023-04-09","arxiv_id":"2304.04326","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperinr-a-fast-and-predictive-hypernetwork","title":"HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillation","date":"2023-04-09","arxiv_id":"2304.04188","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-agnostic-decentralized-collaborative","title":"Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation","date":"2023-04-08","arxiv_id":"2304.03947","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-detection-transformer-for","title":"Continual Detection Transformer for Incremental Object Detection","date":"2023-04-06","arxiv_id":"2304.03110","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-task-driven-model","title":"Towards Efficient Task-Driven Model Reprogramming with Foundation Models","date":"2023-04-05","arxiv_id":"2304.02263","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-class-feature-augmentation-for-class","title":"Cross-Class Feature Augmentation for Class Incremental Learning","date":"2023-04-04","arxiv_id":"2304.01899","repositories_listed":0,"syntology":null},{"url":null,"slug":"madeye-boosting-live-video-analytics-accuracy","title":"MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations","date":"2023-04-04","arxiv_id":"2304.02101","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distilled-graph-neural-networks-for","title":"Knowledge-Distilled Graph Neural Networks for Personalized Epileptic Seizure Detection","date":"2023-04-03","arxiv_id":"2304.06038","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-compression-framework-for-efficient","title":"A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation","date":"2023-04-02","arxiv_id":"2304.00471","repositories_listed":0,"syntology":null},{"url":null,"slug":"gvp-generative-volumetric-primitives","title":"GVP: Generative Volumetric Primitives","date":"2023-03-31","arxiv_id":"2303.18193","repositories_listed":0,"syntology":null},{"url":null,"slug":"quick-dense-retrievers-consume-kale-post","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","date":"2023-03-31","arxiv_id":"2304.01016","repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-knowledge-distillation-for-non","title":"Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation","date":"2023-03-31","arxiv_id":"2303.17910","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetric-face-recognition-with-cross-model","title":"Asymmetric Image Retrieval with Cross Model Compatible Ensembles","date":"2023-03-30","arxiv_id":"2303.17531","repositories_listed":0,"syntology":null},{"url":null,"slug":"if-at-first-you-don-t-succeed-test-time-re","title":"If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval","date":"2023-03-30","arxiv_id":"2303.17703","repositories_listed":0,"syntology":null},{"url":null,"slug":"kd-dlgan-data-limited-image-generation-via","title":"KD-DLGAN: Data Limited Image Generation via Knowledge Distillation","date":"2023-03-30","arxiv_id":"2303.17158","repositories_listed":0,"syntology":null},{"url":null,"slug":"oberta-improving-sparse-transfer-learning-via","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","date":"2023-03-30","arxiv_id":"2303.17612","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-gan-compression-with","title":"Information-Theoretic GAN Compression with Variational Energy-based Model","date":"2023-03-28","arxiv_id":"2303.16050","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-dual-encoder-with-query-generator","title":"Empowering Dual-Encoder with Query Generator for Cross-Lingual Dense Retrieval","date":"2023-03-27","arxiv_id":"2303.14991","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutually-paced-knowledge-distillation-for","title":"Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning","date":"2023-03-27","arxiv_id":"2303.14898","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-frame-self-supervised-depth-estimation","title":"Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes","date":"2023-03-26","arxiv_id":"2303.14628","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-knowledge-distillation-transformer","title":"Multi-view knowledge distillation transformer for human action recognition","date":"2023-03-25","arxiv_id":"2303.14358","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-attentive-transformer-architecture-for","title":"Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation","date":"2023-03-25","arxiv_id":"2303.14423","repositories_listed":0,"syntology":null},{"url":null,"slug":"dylin-making-light-field-networks-dynamic","title":"DyLiN: Making Light Field Networks Dynamic","date":"2023-03-24","arxiv_id":"2303.14243","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-free-but-structure-aware-prototype","title":"Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs","date":"2023-03-24","arxiv_id":"2303.13763","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-unlabelled-photos-for-stronger","title":"Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR","date":"2023-03-24","arxiv_id":"2303.13779","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixed-type-wafer-classification-for-low","title":"Mixed-Type Wafer Classification For Low Memory Devices Using Knowledge Distillation","date":"2023-03-24","arxiv_id":"2303.13974","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-and-generic-framework-for-feature","title":"A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation","date":"2023-03-23","arxiv_id":"2303.13212","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-using-pseudo","title":"Open-Vocabulary Object Detection using Pseudo Caption Labels","date":"2023-03-23","arxiv_id":"2303.13040","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-wide-to-deep-dimension-lifting-network","title":"From Wide to Deep: Dimension Lifting Network for Parameter-efficient Knowledge Graph Embedding","date":"2023-03-22","arxiv_id":"2303.12816","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-branch-collaborative-learning","title":"Heterogeneous-Branch Collaborative Learning for Dialogue Generation","date":"2023-03-21","arxiv_id":"2303.11621","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-robustness-meets-data-privacy","title":"Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation","date":"2023-03-21","arxiv_id":"2303.11611","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-from-multiple","title":"Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition","date":"2023-03-20","arxiv_id":"2303.10917","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-from-less-self-supervised-knowledge","title":"More From Less: Self-Supervised Knowledge Distillation for Routine Histopathology Data","date":"2023-03-19","arxiv_id":"2303.10656","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-attention-and-generalization","title":"Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation","date":"2023-03-18","arxiv_id":"2303.10452","repositories_listed":0,"syntology":null},{"url":null,"slug":"crowd-counting-with-online-knowledge-learning","title":"Crowd Counting with Online Knowledge Learning","date":"2023-03-18","arxiv_id":"2303.10318","repositories_listed":0,"syntology":null},{"url":null,"slug":"dc-ccl-device-cloud-collaborative-controlled","title":"DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models","date":"2023-03-18","arxiv_id":"2303.10361","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillw2v2-a-small-and-streaming-wav2vec-2-0","title":"DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model","date":"2023-03-16","arxiv_id":"2303.09278","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-adaptive-mri","title":"Knowledge Distillation for Adaptive MRI Prostate Segmentation Based on Limit-Trained Multi-Teacher Models","date":"2023-03-16","arxiv_id":"2303.09494","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-search-for-effective","title":"Neural Architecture Search for Effective Teacher-Student Knowledge Transfer in Language Models","date":"2023-03-16","arxiv_id":"2303.09639","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-smaller-student-capacity-dynamic","title":"Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval","date":"2023-03-16","arxiv_id":"2303.09230","repositories_listed":0,"syntology":null},{"url":null,"slug":"identity-preserving-knowledge-distillation","title":"Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation","date":"2023-03-15","arxiv_id":"2303.08665","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-rich-audio-model-inversion-for-data","title":"Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification","date":"2023-03-14","arxiv_id":"2303.07643","repositories_listed":0,"syntology":null},{"url":null,"slug":"metamixer-a-regularization-strategy-for","title":"MetaMixer: A Regularization Strategy for Online Knowledge Distillation","date":"2023-03-14","arxiv_id":"2303.07951","repositories_listed":0,"syntology":null}],"record_sha256":"7c3aaf539914b8de45d71b105532836bce60d1153e1e6045ce26e1decb90d56c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}