{"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/27","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":27,"pages_in_order":43,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/task/knowledge-distillation/papers/28","papers":[{"url":null,"slug":"scavenging-hyena-distilling-transformers-into","title":"Scavenging Hyena: Distilling Transformers into Long Convolution Models","date":"2024-01-31","arxiv_id":"2401.17574","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-of-compression","title":"A Comprehensive Survey of Compression Algorithms for Language Models","date":"2024-01-27","arxiv_id":"2401.15347","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-privileged-multimodal-information","title":"Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport","date":"2024-01-27","arxiv_id":"2401.15489","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-transformer-architecture-for","title":"Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks","date":"2024-01-27","arxiv_id":"2401.15275","repositories_listed":0,"syntology":null},{"url":null,"slug":"face-to-cartoon-incremental-super-resolution","title":"Face to Cartoon Incremental Super-Resolution using Knowledge Distillation","date":"2024-01-27","arxiv_id":"2401.15366","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-guided-knowledge","title":"Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection","date":"2024-01-26","arxiv_id":"2401.15123","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-video-object-segmentation-1","slug":"self-supervised-video-object-segmentation-1","title":"Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention","date":"2024-01-25","arxiv_id":"2401.13937","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-and-relation-distillation-for","title":"Towards Complementary Knowledge Distillation for Efficient Dense Image Prediction","date":"2024-01-24","arxiv_id":"2401.13174","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-garment-transfer-method-supervised-by","title":"A Novel Garment Transfer Method Supervised by Distilled Knowledge of Virtual Try-on Model","date":"2024-01-23","arxiv_id":"2401.12433","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-from-language-oriented","title":"Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control","date":"2024-01-23","arxiv_id":"2401.12624","repositories_listed":0,"syntology":null},{"url":null,"slug":"keep-decoding-parallel-with-effective","title":"Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers","date":"2024-01-22","arxiv_id":"2401.11700","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-on-spatial-temporal","title":"Knowledge Distillation on Spatial-Temporal Graph Convolutional Network for Traffic Prediction","date":"2024-01-22","arxiv_id":"2401.11798","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-to-distribution-shifts-of","title":"Robustness to distribution shifts of compressed networks for edge devices","date":"2024-01-22","arxiv_id":"2401.12014","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereo-matching-knowledge-distilled-monocular","title":"Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency","date":"2024-01-22","arxiv_id":"2401.12019","repositories_listed":0,"syntology":null},{"url":null,"slug":"zoom-shot-fast-and-efficient-unsupervised","title":"Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss","date":"2024-01-22","arxiv_id":"2401.11633","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-preservation-property-in-knowledge","title":"Confidence Preservation Property in Knowledge Distillation Abstractions","date":"2024-01-21","arxiv_id":"2401.11365","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-scalability-in-recommender-systems","title":"Enhancing Scalability in Recommender Systems through Lottery Ticket Hypothesis and Knowledge Distillation-based Neural Network Pruning","date":"2024-01-19","arxiv_id":"2401.10484","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-level-multi-instance-distillation-for","title":"Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization","date":"2024-01-16","arxiv_id":"2401.08860","repositories_listed":0,"syntology":null},{"url":"/paper/a-deep-hierarchical-feature-sparse-framework","slug":"a-deep-hierarchical-feature-sparse-framework","title":"A Deep Hierarchical Feature Sparse Framework for Occluded Person Re-Identification","date":"2024-01-15","arxiv_id":"2401.07469","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-modality-adaptation-to-sequential","title":"Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision","date":"2024-01-14","arxiv_id":"2401.07257","repositories_listed":0,"syntology":null},{"url":null,"slug":"evoke-emotion-enabled-virtual-avatar-mapping","title":"EVOKE: Emotion Enabled Virtual Avatar Mapping Using Optimized Knowledge Distillation","date":"2024-01-13","arxiv_id":"2401.06957","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-closed-source","title":"Knowledge Distillation of Black-Box Large Language Models","date":"2024-01-13","arxiv_id":"2401.07013","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-investigation-into-the-effect-of","title":"An Empirical Investigation into the Effect of Parameter Choices in Knowledge Distillation","date":"2024-01-12","arxiv_id":"2401.06356","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-distillation-between-different-domains","title":"Direct Distillation between Different Domains","date":"2024-01-12","arxiv_id":"2401.06826","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-self-and-cross-triplet-correlations","title":"Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection","date":"2024-01-11","arxiv_id":"2401.05676","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-diffusion-for-efficient-video","title":"Object-Centric Diffusion for Efficient Video Editing","date":"2024-01-11","arxiv_id":"2401.05735","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-knowledge-distillation-on-text","title":"Hierarchical Knowledge Distillation on Text Graph for Data-limited Attribute Inference","date":"2024-01-10","arxiv_id":"2401.06802","repositories_listed":0,"syntology":null},{"url":null,"slug":"logits-poisoning-attack-in-federated","title":"Logits Poisoning Attack in Federated Distillation","date":"2024-01-08","arxiv_id":"2401.03685","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-channel-multi-domain-based-knowledge","title":"Multi-Channel Multi-Domain based Knowledge Distillation Algorithm for Sleep Staging with Single-Channel EEG","date":"2024-01-07","arxiv_id":"2401.03430","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctc-blank-triggered-dynamic-layer-skipping","title":"CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition","date":"2024-01-04","arxiv_id":"2401.02046","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-temporal-knowledge-with-masked","title":"Distilling Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection","date":"2024-01-03","arxiv_id":"2401.01918","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-reflective-learning-through","title":"Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning","date":"2024-01-03","arxiv_id":"2401.01473","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-teacher-knowledge-distillation-with","title":"Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing","date":"2024-01-02","arxiv_id":"2401.01102","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-based-knowledge-sharing-for-open","title":"Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification","date":"2024-01-02","arxiv_id":"2401.01181","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-vision-language-models-on-solid","title":"Building Vision-Language Models on Solid Foundations with Masked Distillation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"c2kd-bridging-the-modality-gap-for-cross","title":"C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-clip-with-dual-guidance-for","title":"Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iq-vfi-implicit-quadratic-motion-estimation","title":"IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kd-detr-knowledge-distillation-for-detection","title":"KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-distillation-via-untargeted-and","title":"Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-adaptive-and-region-aware-multi-modal","title":"Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-guided-never-ending-learning-to","title":"Uncertainty-Guided Never-Ending Learning to Drive","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-deep-image-super-resolution","title":"Compressing Deep Image Super-resolution Models","date":"2023-12-31","arxiv_id":"2401.00523","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainability-driven-leaf-disease","title":"Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation","date":"2023-12-30","arxiv_id":"2401.00334","repositories_listed":0,"syntology":null},{"url":null,"slug":"clst-a-convolutional-transformer-framework","title":"ClST: A Convolutional Transformer Framework for Automatic Modulation Recognition by Knowledge Distillation","date":"2023-12-29","arxiv_id":"2312.17446","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedsdd-scalable-and-diversity-enhanced","title":"FedSDD: Scalable and Diversity-enhanced Distillation for Model Aggregation in Federated Learning","date":"2023-12-28","arxiv_id":"2312.17029","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-attack-unlearning-fast-and-accurate","title":"Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation","date":"2023-12-28","arxiv_id":"2312.16823","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-knowledge-distillation-for-time","title":"Temporal Knowledge Distillation for Time-Sensitive Financial Services Applications","date":"2023-12-28","arxiv_id":"2312.16799","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-modality-assisting-rgbt-object-tracking","title":"X Modality Assisting RGBT Object Tracking","date":"2023-12-27","arxiv_id":"2312.17273","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapterdistillation-non-destructive-task","title":"AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation","date":"2023-12-26","arxiv_id":"2312.16261","repositories_listed":0,"syntology":null},{"url":null,"slug":"cloud-device-collaborative-learning-for","title":"Cloud-Device Collaborative Learning for Multimodal Large Language Models","date":"2023-12-26","arxiv_id":"2312.16279","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-of-llm-for-education","title":"Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments","date":"2023-12-26","arxiv_id":"2312.15842","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-image-to-image-translation-gans","title":"Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold","date":"2023-12-22","arxiv_id":"2312.14776","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-or-more-from-teacher-exploiting","title":"Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation","date":"2023-12-22","arxiv_id":"2312.15112","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-prune-your-language-model-recovering","title":"How to Prune Your Language Model: Recovering Accuracy on the \"Sparsity May Cry'' Benchmark","date":"2023-12-21","arxiv_id":"2312.13547","repositories_listed":0,"syntology":null},{"url":null,"slug":"dsformer-effective-compression-of-text","title":"DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization","date":"2023-12-20","arxiv_id":"2312.13211","repositories_listed":0,"syntology":null},{"url":null,"slug":"expediting-contrastive-language-image","title":"Expediting Contrastive Language-Image Pretraining via Self-distilled Encoders","date":"2023-12-19","arxiv_id":"2312.12659","repositories_listed":0,"syntology":null},{"url":null,"slug":"radocc-learning-cross-modality-occupancy","title":"RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation","date":"2023-12-19","arxiv_id":"2312.11829","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixed-distillation-helps-smaller-language","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","date":"2023-12-17","arxiv_id":"2312.10730","repositories_listed":0,"syntology":null},{"url":null,"slug":"fastsr-nerf-improving-nerf-efficiency-on","title":"FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline","date":"2023-12-15","arxiv_id":"2312.11537","repositories_listed":0,"syntology":null},{"url":null,"slug":"student-as-an-inherent-denoiser-of-noisy","title":"Student as an Inherent Denoiser of Noisy Teacher","date":"2023-12-15","arxiv_id":"2312.10185","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-speech-detection-in-environmental","title":"Efficient speech detection in environmental audio using acoustic recognition and knowledge distillation","date":"2023-12-14","arxiv_id":"2312.09269","repositories_listed":0,"syntology":null},{"url":null,"slug":"rankdvqa-mini-knowledge-distillation-driven","title":"RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment","date":"2023-12-14","arxiv_id":"2312.08864","repositories_listed":0,"syntology":null},{"url":null,"slug":"rdimkd-generic-distillation-paradigm-by","title":"RdimKD: Generic Distillation Paradigm by Dimensionality Reduction","date":"2023-12-14","arxiv_id":"2312.08700","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-key-factors-of-knowledge","title":"Unraveling Key Factors of Knowledge Distillation","date":"2023-12-14","arxiv_id":"2312.08585","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-learning-for-cost-adaptive","title":"Cooperative Learning for Cost-Adaptive Inference","date":"2023-12-13","arxiv_id":"2312.08532","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-sampling-through-the-reuse-of-attention","title":"Fast Sampling Through The Reuse Of Attention Maps In Diffusion Models","date":"2023-12-13","arxiv_id":"2401.01008","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamic-interactive-learning-framework-for","title":"A dynamic interactive learning framework for automated 3D medical image segmentation","date":"2023-12-11","arxiv_id":"2312.06072","repositories_listed":0,"syntology":null},{"url":null,"slug":"fake-it-till-make-it-federated-learning-with","title":"Fake It Till Make It: Federated Learning with Consensus-Oriented Generation","date":"2023-12-10","arxiv_id":"2312.05966","repositories_listed":0,"syntology":null},{"url":null,"slug":"il-nerf-incremental-learning-for-neural","title":"IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment","date":"2023-12-10","arxiv_id":"2312.05748","repositories_listed":0,"syntology":null},{"url":null,"slug":"novacomet-open-commonsense-foundation-models","title":"NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation","date":"2023-12-10","arxiv_id":"2312.05979","repositories_listed":0,"syntology":null},{"url":null,"slug":"koala-self-attention-matters-in-knowledge","title":"KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis","date":"2023-12-07","arxiv_id":"2312.04005","repositories_listed":0,"syntology":null},{"url":null,"slug":"synchronization-is-all-you-need-exocentric-to","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","date":"2023-12-05","arxiv_id":"2312.02638","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-based-spectral-knowledge","title":"Contrastive Learning-Based Spectral Knowledge Distillation for Multi-Modality and Missing Modality Scenarios in Semantic Segmentation","date":"2023-12-04","arxiv_id":"2312.02240","repositories_listed":0,"syntology":null},{"url":null,"slug":"trident-triple-deep-network-training-for","title":"TriDeNT: Triple Deep Network Training for Privileged Knowledge Distillation in Histopathology","date":"2023-12-04","arxiv_id":"2312.02111","repositories_listed":0,"syntology":null},{"url":null,"slug":"oplixnet-towards-area-efficient-optical-split","title":"OplixNet: Towards Area-Efficient Optical Split-Complex Networks with Real-to-Complex Data Assignment and Knowledge Distillation","date":"2023-12-03","arxiv_id":"2312.01403","repositories_listed":0,"syntology":null},{"url":null,"slug":"s2p3-self-supervised-polarimetric-pose","title":"S2P3: Self-Supervised Polarimetric Pose Prediction","date":"2023-12-02","arxiv_id":"2312.01105","repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-of-end-to-end-non-autoregressive","title":"Compression of end-to-end non-autoregressive image-to-speech system for low-resourced devices","date":"2023-11-30","arxiv_id":"2312.00174","repositories_listed":0,"syntology":null},{"url":null,"slug":"iag-induction-augmented-generation-framework","title":"IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions","date":"2023-11-30","arxiv_id":"2311.18397","repositories_listed":0,"syntology":null},{"url":null,"slug":"layercollapse-adaptive-compression-of-neural","title":"LayerCollapse: Adaptive compression of neural networks","date":"2023-11-29","arxiv_id":"2311.17943","repositories_listed":0,"syntology":null},{"url":null,"slug":"propagate-distill-towards-effective-graph","title":"Propagate & Distill: Towards Effective Graph Learners Using Propagation-Embracing MLPs","date":"2023-11-29","arxiv_id":"2311.17781","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusiontalker-personalization-and","title":"DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser","date":"2023-11-28","arxiv_id":"2311.16565","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedal-black-box-federated-knowledge","title":"FedAL: Black-Box Federated Knowledge Distillation Enabled by Adversarial Learning","date":"2023-11-28","arxiv_id":"2311.16584","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-reverse-regularization-network-based","title":"Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification","date":"2023-11-26","arxiv_id":"2311.15231","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearning-via-sparse-representations","title":"Unlearning via Sparse Representations","date":"2023-11-26","arxiv_id":"2311.15268","repositories_listed":0,"syntology":null},{"url":null,"slug":"wired-perspectives-multi-view-wire-art","title":"Wired Perspectives: Multi-View Wire Art Embraces Generative AI","date":"2023-11-26","arxiv_id":"2311.15421","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosine-similarity-knowledge-distillation-for","title":"Cosine Similarity Knowledge Distillation for Individual Class Information Transfer","date":"2023-11-24","arxiv_id":"2311.14307","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-open-world-reinforcement-learning","title":"Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery","date":"2023-11-24","arxiv_id":"2311.14270","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximizing-discrimination-capability-of","title":"Maximizing Discrimination Capability of Knowledge Distillation with Energy Function","date":"2023-11-24","arxiv_id":"2311.14334","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudo-label-correction-for-instance","title":"Pseudo-label Correction for Instance-dependent Noise Using Teacher-student Framework","date":"2023-11-24","arxiv_id":"2311.14237","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-classical-and-quantum-machine","title":"Bridging Classical and Quantum Machine Learning: Knowledge Transfer From Classical to Quantum Neural Networks Using Knowledge Distillation","date":"2023-11-23","arxiv_id":"2311.13810","repositories_listed":0,"syntology":null},{"url":null,"slug":"education-distillation-getting-student-models","title":"Education distillation:getting student models to learn in shcools","date":"2023-11-23","arxiv_id":"2311.13811","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-based-semantic","title":"Knowledge Distillation Based Semantic Communications For Multiple Users","date":"2023-11-23","arxiv_id":"2311.13789","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-reinforced-knowledge-distillation","title":"Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning","date":"2023-11-23","arxiv_id":"2311.13934","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-transformer-knowledge-distillation","title":"Efficient Transformer Knowledge Distillation: A Performance Review","date":"2023-11-22","arxiv_id":"2311.13657","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-from-the-dark-side-entropy","title":"EA-KD: Entropy-based Adaptive Knowledge Distillation","date":"2023-11-22","arxiv_id":"2311.13621","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-unseen-potential-of-graph","title":"Unveiling the Unseen Potential of Graph Learning through MLPs: Effective Graph Learners Using Propagation-Embracing MLPs","date":"2023-11-20","arxiv_id":"2311.11759","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightbtseg-a-lightweight-breast-tumor","title":"LightBTSeg: A lightweight breast tumor segmentation model using ultrasound images via dual-path joint knowledge distillation","date":"2023-11-18","arxiv_id":"2311.11086","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-attention-exploring-shallow-feed","title":"Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers","date":"2023-11-17","arxiv_id":"2311.10642","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-vit-knowledge-distillation","title":"Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction","date":"2023-11-17","arxiv_id":"2311.10305","repositories_listed":0,"syntology":null}],"record_sha256":"e9ba41ef9f4eecafa8d78e587f05885b7f36b63992ebc85cf1575f50d059db5b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}