{"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/33","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":33,"pages_in_order":43,"rows_per_page":100,"rows":[3201,3300],"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/32","next":"/task/knowledge-distillation/papers/34","papers":[{"url":null,"slug":"asymmetric-distillation-post-segmentation","title":"ADPS: Asymmetric Distillation Post-Segmentation for Image Anomaly Detection","date":"2022-10-19","arxiv_id":"2210.10495","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-effects-of-knowledge-distillation-on","title":"On effects of Knowledge Distillation on Transfer Learning","date":"2022-10-18","arxiv_id":"2210.09668","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-with-privacy-preserving","title":"Federated Learning with Privacy-Preserving Ensemble Attention Distillation","date":"2022-10-16","arxiv_id":"2210.08464","repositories_listed":0,"syntology":null},{"url":null,"slug":"ros-kd-a-robust-stochastic-knowledge","title":"RoS-KD: A Robust Stochastic Knowledge Distillation Approach for Noisy Medical Imaging","date":"2022-10-15","arxiv_id":"2210.08388","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-integration-of-object-level","title":"Probabilistic Integration of Object Level Annotations in Chest X-ray Classification","date":"2022-10-13","arxiv_id":"2210.06980","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-can-have-your-data-and-balance-it-too","title":"You Can Have Your Data and Balance It Too: Towards Balanced and Efficient Multilingual Models","date":"2022-10-13","arxiv_id":"2210.07135","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-graph-neural-networks-via-adaptive","title":"Boosting Graph Neural Networks via Adaptive Knowledge Distillation","date":"2022-10-12","arxiv_id":"2210.05920","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-soft-and-hard-target-rnn-t","title":"Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR","date":"2022-10-11","arxiv_id":"2210.05793","repositories_listed":0,"syntology":null},{"url":null,"slug":"linkless-link-prediction-via-relational","title":"Linkless Link Prediction via Relational Distillation","date":"2022-10-11","arxiv_id":"2210.05801","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-unreasonable-effectiveness-of-fully","title":"The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes","date":"2022-10-11","arxiv_id":"2210.05657","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetric-temperature-scaling-makes-larger","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","date":"2022-10-10","arxiv_id":"2210.04427","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-transfer-sets-and","title":"Knowledge Distillation Transfer Sets and their Impact on Downstream NLU Tasks","date":"2022-10-10","arxiv_id":"2210.04834","repositories_listed":0,"syntology":null},{"url":null,"slug":"students-taught-by-multimodal-teachers-are","title":"Students taught by multimodal teachers are superior action recognizers","date":"2022-10-09","arxiv_id":"2210.04331","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutual-learning-of-single-and-multi-channel","title":"Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization","date":"2022-10-07","arxiv_id":"2210.03459","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-graph-self-supervised-learning-via","title":"Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation","date":"2022-10-05","arxiv_id":"2210.02099","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-ensemble-parameter-learning","title":"Meta-Ensemble Parameter Learning","date":"2022-10-05","arxiv_id":"2210.01973","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-the-efficiency-and-generalization","title":"A Study on the Efficiency and Generalization of Light Hybrid Retrievers","date":"2022-10-04","arxiv_id":"2210.01371","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-discrepancy-aware-distillation-for","title":"Domain Discrepancy Aware Distillation for Model Aggregation in Federated Learning","date":"2022-10-04","arxiv_id":"2210.02190","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-based-contextual","title":"Knowledge Distillation based Contextual Relevance Matching for E-commerce Product Search","date":"2022-10-04","arxiv_id":"2210.01701","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-active-distillation","title":"Robust Active Distillation","date":"2022-10-03","arxiv_id":"2210.01213","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-zero-shot-multilingual-text","title":"Improving Zero-Shot Multilingual Text Generation via Iterative Distillation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-transfer-with-visual-prompt-in","title":"Knowledge Transfer with Visual Prompt in multi-modal Dialogue Understanding and Generation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-progressive-compression-of","title":"Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition","date":"2022-10-01","arxiv_id":"2210.00169","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-interpretable-logic-tensor-network","title":"Sentiment Interpretable Logic Tensor Network for Aspect-Term Sentiment Analysis","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-knowledge-from-structure-aware-1","title":"Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-and-training-of-lightweight-neural","title":"Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillation","date":"2022-09-30","arxiv_id":"2209.15560","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-unified-view-of-affinity-based","title":"Towards a Unified View of Affinity-Based Knowledge Distillation","date":"2022-09-30","arxiv_id":"2209.15555","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-knowledge-distillation-to-improve","title":"Using Knowledge Distillation to improve interpretable models in a retail banking context","date":"2022-09-30","arxiv_id":"2209.15496","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-driven-knowledge-distillation-for","title":"Label driven Knowledge Distillation for Federated Learning with non-IID Data","date":"2022-09-29","arxiv_id":"2209.14520","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-explaining-autonomy-with-verbalised","title":"Towards Explaining Autonomy with Verbalised Decision Tree States","date":"2022-09-28","arxiv_id":"2209.13985","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-to-ensemble-global-and","title":"Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models","date":"2022-09-26","arxiv_id":"2209.12420","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-speech-activity-and-overlap-detection","title":"Joint Speech Activity and Overlap Detection with Multi-Exit Architecture","date":"2022-09-24","arxiv_id":"2209.11906","repositories_listed":0,"syntology":null},{"url":null,"slug":"drkf-distilled-rotated-kernel-fusion-for","title":"DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching","date":"2022-09-22","arxiv_id":"2209.10907","repositories_listed":0,"syntology":null},{"url":null,"slug":"momentum-adversarial-distillation-handling","title":"Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation","date":"2022-09-21","arxiv_id":"2209.10359","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-efficient-conformers-via-sharing","title":"Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition","date":"2022-09-17","arxiv_id":"2209.08326","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-for-class-and-domain","title":"Continual Learning for Class- and Domain-Incremental Semantic Segmentation","date":"2022-09-16","arxiv_id":"2209.08023","repositories_listed":0,"syntology":null},{"url":null,"slug":"ces-kd-curriculum-based-expert-selection-for","title":"CES-KD: Curriculum-based Expert Selection for Guided Knowledge Distillation","date":"2022-09-15","arxiv_id":"2209.07606","repositories_listed":0,"syntology":null},{"url":null,"slug":"layerwise-bregman-representation-learning","title":"Layerwise Bregman Representation Learning with Applications to Knowledge Distillation","date":"2022-09-15","arxiv_id":"2209.07080","repositories_listed":0,"syntology":null},{"url":null,"slug":"plastil-plastic-and-stable-memory-free-class","title":"PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning","date":"2022-09-14","arxiv_id":"2209.06606","repositories_listed":0,"syntology":null},{"url":null,"slug":"tasked-transformer-based-adversarial-learning","title":"TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation","date":"2022-09-14","arxiv_id":"2209.09092","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-continual-learning-via-the-meta","title":"Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation","date":"2022-09-12","arxiv_id":"2209.06107","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserving-privacy-in-federated-learning-with","title":"Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation","date":"2022-09-10","arxiv_id":"2209.04599","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-situ-animal-behavior-classification-using","title":"In-situ animal behavior classification using knowledge distillation and fixed-point quantization","date":"2022-09-09","arxiv_id":"2209.04130","repositories_listed":0,"syntology":null},{"url":null,"slug":"selecting-related-knowledge-via-efficient","title":"Selecting Related Knowledge via Efficient Channel Attention for Online Continual Learning","date":"2022-09-09","arxiv_id":"2209.04212","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-self-knowledge-distillation-approach","title":"A Novel Self-Knowledge Distillation Approach with Siamese Representation Learning for Action Recognition","date":"2022-09-03","arxiv_id":"2209.01311","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamics-adaptive-continual-reinforcement","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","date":"2022-09-01","arxiv_id":"2209.00347","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-sustainable-neural","title":"Knowledge Distillation for Sustainable Neural Machine Translation","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"removing-rain-streaks-via-task-transfer","title":"Removing Rain Streaks via Task Transfer Learning","date":"2022-08-28","arxiv_id":"2208.13133","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-dense-depth-distillation","title":"Dense Depth Distillation with Out-of-Distribution Simulated Images","date":"2022-08-26","arxiv_id":"2208.12464","repositories_listed":0,"syntology":null},{"url":null,"slug":"debias-the-black-box-a-fair-ranking-framework","title":"Debias the Black-box: A Fair Ranking Framework via Knowledge Distillation","date":"2022-08-24","arxiv_id":"2208.11628","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-learning-for-neural-powered-mixed","title":"Lifelong Learning for Neural powered Mixed Integer Programming","date":"2022-08-24","arxiv_id":"2208.12226","repositories_listed":0,"syntology":null},{"url":"/paper/multi-view-attention-transfer-for-efficient","slug":"multi-view-attention-transfer-for-efficient","title":"Multi-View Attention Transfer for Efficient Speech Enhancement","date":"2022-08-22","arxiv_id":"2208.10367","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-compressions-for-multiplicative","title":"Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks","date":"2022-08-20","arxiv_id":"2208.09684","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectiveness-of-function-matching-in-driving","title":"Effectiveness of Function Matching in Driving Scene Recognition","date":"2022-08-20","arxiv_id":"2208.09694","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-the-knowledge-in-a-dnn-to-explain","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","date":"2022-08-18","arxiv_id":"2208.08741","repositories_listed":0,"syntology":null},{"url":null,"slug":"leukocyte-classification-using-multimodal","title":"Leukocyte Classification using Multimodal Architecture Enhanced by Knowledge Distillation","date":"2022-08-17","arxiv_id":"2208.08331","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-cross-modal-knowledge","title":"Progressive Cross-modal Knowledge Distillation for Human Action Recognition","date":"2022-08-17","arxiv_id":"2208.08090","repositories_listed":0,"syntology":null},{"url":null,"slug":"rawtobit-a-fully-end-to-end-camera-isp","title":"RAWtoBit: A Fully End-to-end Camera ISP Network","date":"2022-08-16","arxiv_id":"2208.07639","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-for-2","title":"Unsupervised Domain Adaptation for Segmentation with Black-box Source Model","date":"2022-08-16","arxiv_id":"2208.07769","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-knowledge-distillation-based-backdoor","title":"A Knowledge Distillation-Based Backdoor Attack in Federated Learning","date":"2022-08-12","arxiv_id":"2208.06176","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-autoregressive-sign-language-production","title":"Non-Autoregressive Sign Language Production via Knowledge Distillation","date":"2022-08-12","arxiv_id":"2208.06183","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-knowledge-distillation-via-dropout","title":"Self-Knowledge Distillation via Dropout","date":"2022-08-11","arxiv_id":"2208.05642","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-semantic-knowledge-distillation-for","title":"Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation","date":"2022-08-07","arxiv_id":"2208.03763","repositories_listed":0,"syntology":null},{"url":null,"slug":"study-of-encoder-decoder-architectures-for","title":"Study of Encoder-Decoder Architectures for Code-Mix Search Query Translation","date":"2022-08-07","arxiv_id":"2208.03713","repositories_listed":0,"syntology":null},{"url":null,"slug":"pgx-a-multi-level-gnn-explanation-framework","title":"PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes","date":"2022-08-05","arxiv_id":"2208.03075","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-balanced-distillation-for-object","title":"Task-Balanced Distillation for Object Detection","date":"2022-08-05","arxiv_id":"2208.03006","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-semi-supervised-and-self-supervised","title":"Deep Semi-Supervised and Self-Supervised Learning for Diabetic Retinopathy Detection","date":"2022-08-04","arxiv_id":"2208.02408","repositories_listed":0,"syntology":null},{"url":null,"slug":"pose-uncertainty-aware-movement-synchrony","title":"Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer","date":"2022-08-01","arxiv_id":"2208.01161","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdbert-sparsedistilbert-a-faster-and-smaller","title":"SDBERT: SparseDistilBERT, a faster and smaller BERT model","date":"2022-07-28","arxiv_id":"2208.10246","repositories_listed":0,"syntology":null},{"url":null,"slug":"nicest-noisy-label-correction-and-training","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","date":"2022-07-27","arxiv_id":"2207.13316","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-object-detection-by-knowledge","title":"Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations","date":"2022-07-25","arxiv_id":"2207.12049","repositories_listed":0,"syntology":null},{"url":null,"slug":"hire-distilling-high-order-relational","title":"HIRE: Distilling High-order Relational Knowledge From Heterogeneous Graph Neural Networks","date":"2022-07-25","arxiv_id":"2207.11887","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-semi-supervised-domain-adaptation","title":"Federated Semi-Supervised Domain Adaptation via Knowledge Transfer","date":"2022-07-21","arxiv_id":"2207.10727","repositories_listed":0,"syntology":null},{"url":null,"slug":"aware-of-the-history-trajectory-forecasting","title":"Aware of the History: Trajectory Forecasting with the Local Behavior Data","date":"2022-07-20","arxiv_id":"2207.09646","repositories_listed":0,"syntology":null},{"url":null,"slug":"many-to-one-knowledge-distillation-of-real","title":"Many-to-One Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Internet of Things Systems","date":"2022-07-20","arxiv_id":"2208.00885","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-for-resource-constrained","title":"Model Compression for Resource-Constrained Mobile Robots","date":"2022-07-20","arxiv_id":"2207.10082","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-with-a-class-aware","title":"Knowledge distillation with a class-aware loss for endoscopic disease detection","date":"2022-07-19","arxiv_id":"2207.09530","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-knowledge-representation-with-meta","title":"Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution","date":"2022-07-18","arxiv_id":"2207.08356","repositories_listed":0,"syntology":null},{"url":null,"slug":"subclass-knowledge-distillation-with-known","title":"Subclass Knowledge Distillation with Known Subclass Labels","date":"2022-07-17","arxiv_id":"2207.08063","repositories_listed":0,"syntology":null},{"url":"/paper/ssmtl-revisiting-self-supervised-multi-task","slug":"ssmtl-revisiting-self-supervised-multi-task","title":"SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection","date":"2022-07-16","arxiv_id":"2207.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-versus-wide-an-analysis-of-student","title":"Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models","date":"2022-07-14","arxiv_id":"2207.06867","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-attention-mechanism-in-time-series","title":"Rethinking Attention Mechanism in Time Series Classification","date":"2022-07-14","arxiv_id":"2207.07564","repositories_listed":0,"syntology":null},{"url":null,"slug":"dspnet-towards-slimmable-pretrained-networks","title":"DSPNet: Towards Slimmable Pretrained Networks based on Discriminative Self-supervised Learning","date":"2022-07-13","arxiv_id":"2207.06075","repositories_listed":0,"syntology":null},{"url":null,"slug":"rich-feature-distillation-with-feature","title":"Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing","date":"2022-07-13","arxiv_id":"2207.11250","repositories_listed":0,"syntology":null},{"url":null,"slug":"slimseg-slimmable-semantic-segmentation-with","title":"SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision","date":"2022-07-13","arxiv_id":"2207.06242","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-architecture-knowledge-distillation","title":"Cross-Architecture Knowledge Distillation","date":"2022-07-12","arxiv_id":"2207.05273","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalized-feature-distillation-for-semantic","title":"Normalized Feature Distillation for Semantic Segmentation","date":"2022-07-12","arxiv_id":"2207.05256","repositories_listed":0,"syntology":null},{"url":null,"slug":"1st-place-solution-to-the-epic-kitchens","title":"1st Place Solution to the EPIC-Kitchens Action Anticipation Challenge 2022","date":"2022-07-10","arxiv_id":"2207.05730","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-streaming-end-to-end-asr-on","title":"Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies","date":"2022-07-06","arxiv_id":"2207.02495","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-low-footprint-wake-word","title":"Low-resource Low-footprint Wake-word Detection using Knowledge Distillation","date":"2022-07-06","arxiv_id":"2207.03331","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-framework-for-personalized","title":"A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacy","date":"2022-07-05","arxiv_id":"2207.01771","repositories_listed":0,"syntology":null},{"url":null,"slug":"glance-global-to-local-architecture-neutral","title":"GLANCE: Global to Local Architecture-Neutral Concept-based Explanations","date":"2022-07-05","arxiv_id":"2207.01917","repositories_listed":0,"syntology":null},{"url":null,"slug":"vem-2-l-a-plug-and-play-framework-for-fusing","title":"VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion","date":"2022-07-04","arxiv_id":"2207.01528","repositories_listed":0,"syntology":null},{"url":null,"slug":"fasterai-a-lightweight-library-for-creating","title":"FasterAI: A Lightweight Library for Creating Sparse Neural Networks","date":"2022-07-03","arxiv_id":"2207.01088","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-investigating-model","title":"Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation","date":"2022-07-02","arxiv_id":"2207.03334","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-convergence-in-multi-task","title":"Asynchronous Convergence in Multi-Task Learning via Knowledge Distillation from Converged Tasks","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-simultaneous-speech-translation","title":"End-to-End Simultaneous Speech Translation with Pretraining and Distillation: Huawei Noah’s System for AutoSimTranS 2022","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kroneckerbert-significant-compression-of-pre","title":"KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lost-in-distillation-a-case-study-in-toxicity","title":"Lost in Distillation: A Case Study in Toxicity Modeling","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"why-knowledge-distillation-amplifies-gender","title":"Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"3471e7633300297ae0ac33fccdcf4fcd8fd61acb5881f7e3e954167364f45bca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}