{"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/28","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":28,"pages_in_order":43,"rows_per_page":100,"rows":[2701,2800],"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/27","next":"/task/knowledge-distillation/papers/29","papers":[{"url":null,"slug":"a-knowledge-distillation-approach-for-sepsis","title":"A Knowledge Distillation Approach for Sepsis Outcome Prediction from Multivariate Clinical Time Series","date":"2023-11-16","arxiv_id":"2311.09566","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-constrained-bayesian-active","title":"Batch Selection and Communication for Active Learning with Edge Labeling","date":"2023-11-14","arxiv_id":"2311.08053","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlock-the-power-competitive-distillation-for","title":"Unlock the Power: Competitive Distillation for Multi-Modal Large Language Models","date":"2023-11-14","arxiv_id":"2311.08213","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-elastic-language-models","title":"On Elastic Language Models","date":"2023-11-13","arxiv_id":"2311.07204","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-me-with-a-whisper-enhancing-large","title":"Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings","date":"2023-11-13","arxiv_id":"2311.07014","repositories_listed":0,"syntology":null},{"url":null,"slug":"donut-hole-donut-sparsification-by-harnessing","title":"DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency","date":"2023-11-09","arxiv_id":"2311.05778","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-cross-modal-feature","title":"Object-centric Cross-modal Feature Distillation for Event-based Object Detection","date":"2023-11-09","arxiv_id":"2311.05494","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-knowledge-transfer","title":"Supervised domain adaptation for building extraction from off-nadir aerial images","date":"2023-11-07","arxiv_id":"2311.03867","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-lost-in-knowledge-distillation","title":"What is Lost in Knowledge Distillation?","date":"2023-11-07","arxiv_id":"2311.04142","repositories_listed":0,"syntology":null},{"url":"/paper/asymmetric-masked-distillation-for-pre","slug":"asymmetric-masked-distillation-for-pre","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","date":"2023-11-06","arxiv_id":"2311.03149","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-training-and-co-distillation-for-quality","title":"Co-training and Co-distillation for Quality Improvement and Compression of Language Models","date":"2023-11-06","arxiv_id":"2311.02849","repositories_listed":0,"syntology":null},{"url":null,"slug":"after-stroke-arm-paresis-detection-using","title":"After-Stroke Arm Paresis Detection using Kinematic Data","date":"2023-11-03","arxiv_id":"2311.16138","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-distillation-of-language-model-by","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","date":"2023-11-03","arxiv_id":"2311.01689","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-detection-and-control-system-for","title":"An Efficient Detection and Control System for Underwater Docking using Machine Learning and Realistic Simulation: A Comprehensive Approach","date":"2023-11-02","arxiv_id":"2311.01522","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-knowledge-from-cnn-transformer","title":"Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition","date":"2023-11-02","arxiv_id":"2311.01283","repositories_listed":0,"syntology":null},{"url":null,"slug":"group-distributionally-robust-knowledge","title":"Group Distributionally Robust Knowledge Distillation","date":"2023-11-01","arxiv_id":"2311.00476","repositories_listed":0,"syntology":null},{"url":null,"slug":"neo-kd-knowledge-distillation-based","title":"NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks","date":"2023-11-01","arxiv_id":"2311.00428","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-multi-fidelity-learning-for-cost","title":"Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision","date":"2023-10-31","arxiv_id":"2310.20153","repositories_listed":0,"syntology":null},{"url":null,"slug":"must-a-multilingual-student-teacher-learning","title":"MUST: A Multilingual Student-Teacher Learning approach for low-resource speech recognition","date":"2023-10-29","arxiv_id":"2310.18865","repositories_listed":0,"syntology":null},{"url":"/paper/rckd-response-based-cross-task-knowledge","slug":"rckd-response-based-cross-task-knowledge","title":"RCKD: Response-Based Cross-Task Knowledge Distillation for Pathological Image Analysis","date":"2023-10-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-object-detection-in-optical-remote","title":"Efficient Object Detection in Optical Remote Sensing Imagery via Attention-based Feature Distillation","date":"2023-10-28","arxiv_id":"2310.18676","repositories_listed":0,"syntology":null},{"url":"/paper/multi-label-emotion-analysis-in-conversation","slug":"multi-label-emotion-analysis-in-conversation","title":"Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation","date":"2023-10-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sonosam-segment-anything-on-ultrasound-images","title":"SonoSAMTrack -- Segment and Track Anything on Ultrasound Images","date":"2023-10-25","arxiv_id":"2310.16872","repositories_listed":0,"syntology":null},{"url":null,"slug":"abkd-graph-neural-network-compression-with","title":"ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation","date":"2023-10-24","arxiv_id":"2310.15938","repositories_listed":0,"syntology":null},{"url":null,"slug":"wakening-past-concepts-without-past-data-1","title":"Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos","date":"2023-10-24","arxiv_id":"2310.16115","repositories_listed":0,"syntology":null},{"url":null,"slug":"ophthalmic-biomarker-detection-using","title":"Leveraging Complementary Attention maps in vision transformers for OCT image analysis","date":"2023-10-21","arxiv_id":"2310.14005","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-knowledge-distillation-using","title":"Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images","date":"2023-10-20","arxiv_id":"2310.13782","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-abstractiveness-of-summarization","title":"Enhancing Abstractiveness of Summarization Models through Calibrated Distillation","date":"2023-10-20","arxiv_id":"2310.13760","repositories_listed":0,"syntology":null},{"url":null,"slug":"gendistiller-distilling-pre-trained-language","title":"GenDistiller: Distilling Pre-trained Language Models based on Generative Models","date":"2023-10-20","arxiv_id":"2310.13418","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-analysis-of-task-agnostic","title":"A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models","date":"2023-10-13","arxiv_id":"2310.08797","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-multi-modal-3d-semantic","title":"Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving","date":"2023-10-13","arxiv_id":"2310.08826","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillspec-improving-speculative-decoding","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","date":"2023-10-12","arxiv_id":"2310.08461","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-efficient-vision-transformers-from","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","date":"2023-10-11","arxiv_id":"2310.07265","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-anomaly-detection","title":"Knowledge Distillation for Anomaly Detection","date":"2023-10-09","arxiv_id":"2310.06047","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-larger-image-classifiers-memorise","title":"What do larger image classifiers memorise?","date":"2023-10-09","arxiv_id":"2310.05337","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-feature-importance-scores-for","title":"Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates","date":"2023-10-06","arxiv_id":"2310.04352","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-federated-learning-using","title":"Heterogeneous Federated Learning Using Knowledge Codistillation","date":"2023-10-04","arxiv_id":"2310.02549","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-2-kd-slu-an-intra-inter-knowledge","title":"I$^2$KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding","date":"2023-10-04","arxiv_id":"2310.02594","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-knowledge-distillation-with-teacher","title":"Improving Knowledge Distillation with Teacher's Explanation","date":"2023-10-04","arxiv_id":"2310.02572","repositories_listed":0,"syntology":null},{"url":null,"slug":"talking-models-distill-pre-trained-knowledge","title":"Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication","date":"2023-10-04","arxiv_id":"2310.03188","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-a-student-large-language-model-perform-as","title":"Can a student Large Language Model perform as well as it's teacher?","date":"2023-10-03","arxiv_id":"2310.02421","repositories_listed":0,"syntology":null},{"url":null,"slug":"kgex-explaining-knowledge-graph-embeddings","title":"KGEx: Explaining Knowledge Graph Embeddings via Subgraph Sampling and Knowledge Distillation","date":"2023-10-02","arxiv_id":"2310.01065","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-cross-modal-knowledge-distillation","title":"Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality","date":"2023-10-02","arxiv_id":"2310.01035","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fixing-clever-hans-predictors-with","title":"Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation","date":"2023-10-02","arxiv_id":"2310.01011","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-logiglue-a-brief-survey-and-a","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","date":"2023-10-02","arxiv_id":"2310.00836","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-inductive-bias-knowledge","title":"Distilling Inductive Bias: Knowledge Distillation Beyond Model Compression","date":"2023-09-30","arxiv_id":"2310.00369","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-few-call-model-stealing-via-active","title":"Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation","date":"2023-09-29","arxiv_id":"2310.00096","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-low-resolution-image-recognition","title":"An Enhanced Low-Resolution Image Recognition Method for Traffic Environments","date":"2023-09-28","arxiv_id":"2309.16390","repositories_listed":0,"syntology":null},{"url":null,"slug":"distill-to-delete-unlearning-in-graph","title":"Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation","date":"2023-09-28","arxiv_id":"2309.16173","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-ode-solvers-of-diffusion-models","title":"Distilling ODE Solvers of Diffusion Models into Smaller Steps","date":"2023-09-28","arxiv_id":"2309.16421","repositories_listed":0,"syntology":null},{"url":null,"slug":"cold-warm-net-addressing-cold-start-users-in","title":"Cold & Warm Net: Addressing Cold-Start Users in Recommender Systems","date":"2023-09-27","arxiv_id":"2309.15646","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualvc-2-dynamic-masked-convolution-for","title":"DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion","date":"2023-09-27","arxiv_id":"2309.15496","repositories_listed":0,"syntology":null},{"url":null,"slug":"inherit-with-distillation-and-evolve-with","title":"Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory","date":"2023-09-27","arxiv_id":"2309.15413","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoadviser-video-knowledge-distillation-for","title":"VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning","date":"2023-09-27","arxiv_id":"2309.15494","repositories_listed":0,"syntology":null},{"url":null,"slug":"adu-depth-attention-based-distillation-with","title":"ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation","date":"2023-09-26","arxiv_id":"2309.14744","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-continual-multi-view-clustering","title":"Contrastive Continual Multi-view Clustering with Filtered Structural Fusion","date":"2023-09-26","arxiv_id":"2309.15135","repositories_listed":0,"syntology":null},{"url":null,"slug":"donnav2-lightweight-neural-architecture","title":"DONNAv2 -- Lightweight Neural Architecture Search for Vision tasks","date":"2023-09-26","arxiv_id":"2309.14670","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-using-generated-privileged","title":"Learning Using Generated Privileged Information by Text-to-Image Diffusion Models","date":"2023-09-26","arxiv_id":"2309.15238","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-tolerant-unsupervised-adapter-for","title":"Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models","date":"2023-09-26","arxiv_id":"2309.14928","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-3d-perception-with-2d-vision","title":"Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving","date":"2023-09-25","arxiv_id":"2309.14491","repositories_listed":0,"syntology":null},{"url":null,"slug":"dfrd-data-free-robustness-distillation-for","title":"DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning","date":"2023-09-24","arxiv_id":"2309.13546","repositories_listed":0,"syntology":null},{"url":null,"slug":"multivariate-prototype-representation-for","title":"Multivariate Prototype Representation for Domain-Generalized Incremental Learning","date":"2023-09-24","arxiv_id":"2309.13563","repositories_listed":0,"syntology":null},{"url":null,"slug":"poster-self-supervised-quantization-aware","title":"Poster: Self-Supervised Quantization-Aware Knowledge Distillation","date":"2023-09-22","arxiv_id":"2309.13220","repositories_listed":0,"syntology":null},{"url":null,"slug":"triple-view-knowledge-distillation-for-semi","title":"Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation","date":"2023-09-22","arxiv_id":"2309.12557","repositories_listed":0,"syntology":null},{"url":null,"slug":"vic-kd-variance-invariance-covariance","title":"VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks","date":"2023-09-22","arxiv_id":"2309.12914","repositories_listed":0,"syntology":null},{"url":null,"slug":"defending-against-data-free-model-extraction","title":"Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training","date":"2023-09-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"defending-against-data-free-model-extraction-1","title":"Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training","date":"2023-09-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/language-oriented-communication-with-semantic","slug":"language-oriented-communication-with-semantic","title":"Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation","date":"2023-09-20","arxiv_id":"2309.11127","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-clip-robustness-with-knowledge","title":"Improving CLIP Robustness with Knowledge Distillation and Self-Training","date":"2023-09-19","arxiv_id":"2309.10361","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-ultrasound-tongue-images-for-1","title":"Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement","date":"2023-09-19","arxiv_id":"2309.10455","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-hubert-with-lstms-via-decoupled","title":"Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation","date":"2023-09-18","arxiv_id":"2309.09920","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-generative-knowledge","title":"Heterogeneous Generative Knowledge Distillation with Masked Image Modeling","date":"2023-09-18","arxiv_id":"2309.09571","repositories_listed":0,"syntology":null},{"url":null,"slug":"unideal-curriculum-knowledge-distillation","title":"UNIDEAL: Curriculum Knowledge Distillation Federated Learning","date":"2023-09-16","arxiv_id":"2309.08961","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-knowledge-distillation-via-flow","title":"Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech","date":"2023-09-15","arxiv_id":"2309.08255","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-class-knowledge-distillation-for-spoofing","title":"One-Class Knowledge Distillation for Spoofing Speech Detection","date":"2023-09-15","arxiv_id":"2309.08285","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-early-detection-of","title":"Privacy-preserving Early Detection of Epileptic Seizures in Videos","date":"2023-09-15","arxiv_id":"2309.08794","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-step-knowledge-distillation-for-tiny","title":"Two-Step Knowledge Distillation for Tiny Speech Enhancement","date":"2023-09-15","arxiv_id":"2309.08144","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-local-global-feature-fusion-framework","title":"A Novel Local-Global Feature Fusion Framework for Body-weight Exercise Recognition with Pressure Mapping Sensors","date":"2023-09-14","arxiv_id":"2309.07888","repositories_listed":0,"syntology":null},{"url":null,"slug":"colld-contrastive-layer-to-layer-distillation","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","date":"2023-09-14","arxiv_id":"2309.07707","repositories_listed":0,"syntology":null},{"url":null,"slug":"corf-colorizing-radiance-fields-using","title":"ChromaDistill: Colorizing Monochrome Radiance Fields with Knowledge Distillation","date":"2023-09-14","arxiv_id":"2309.07668","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-with-dirichlet-generative","title":"Continual Learning with Dirichlet Generative-based Rehearsal","date":"2023-09-13","arxiv_id":"2309.06917","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-training-and-multi-task-learning-for","title":"Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detection","date":"2023-09-12","arxiv_id":"2309.06288","repositories_listed":0,"syntology":null},{"url":null,"slug":"kd-fixmatch-knowledge-distillation-siamese","title":"KD-FixMatch: Knowledge Distillation Siamese Neural Networks","date":"2023-09-11","arxiv_id":"2309.05826","repositories_listed":0,"syntology":null},{"url":null,"slug":"devit-decomposing-vision-transformers-for","title":"DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices","date":"2023-09-10","arxiv_id":"2309.05015","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-emotion-recognition-with-distilled","title":"Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations","date":"2023-09-09","arxiv_id":"2309.04849","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-denoisers-are-good-2d-teachers-molecular","title":"3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation","date":"2023-09-08","arxiv_id":"2309.04062","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-empowered-digital-twin","title":"Knowledge Distillation-Empowered Digital Twin for Anomaly Detection","date":"2023-09-08","arxiv_id":"2309.04616","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-comparable-knowledge-distillation-in","title":"Towards Comparable Knowledge Distillation in Semantic Image Segmentation","date":"2023-09-07","arxiv_id":"2309.03659","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-natural-language-inference-predictor","title":"A deep Natural Language Inference predictor without language-specific training data","date":"2023-09-06","arxiv_id":"2309.02887","repositories_listed":0,"syntology":null},{"url":null,"slug":"dmkd-improving-feature-based-knowledge","title":"DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation","date":"2023-09-06","arxiv_id":"2309.02719","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-asr-pretrained-conformers-for","title":"Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation","date":"2023-09-06","arxiv_id":"2309.03019","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-efficient-vision-transformers","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","date":"2023-09-05","arxiv_id":"2309.02031","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-high-performance-learned-image","title":"Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation","date":"2023-09-05","arxiv_id":"2309.02529","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-self-supervised-learning-via","title":"Probabilistic Self-supervised Learning via Scoring Rules Minimization","date":"2023-09-05","arxiv_id":"2309.02048","repositories_listed":0,"syntology":null},{"url":null,"slug":"todm-train-once-deploy-many-efficient","title":"TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models","date":"2023-09-05","arxiv_id":"2309.01947","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-query-strategies-for-efficient-online","title":"On the Query Strategies for Efficient Online Active Distillation","date":"2023-09-04","arxiv_id":"2309.01612","repositories_listed":0,"syntology":null},{"url":null,"slug":"prior-knowledge-guided-network-for-video","title":"Prior Knowledge Guided Network for Video Anomaly Detection","date":"2023-09-04","arxiv_id":"2309.01682","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-finetuning-with-latent","title":"Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff","date":"2023-08-31","arxiv_id":"2308.16454","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-from-non-streaming-to","title":"Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer","date":"2023-08-31","arxiv_id":"2308.16415","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-long-tailed-recognition-for-graph","title":"Towards Long-Tailed Recognition for Graph Classification via Collaborative Experts","date":"2023-08-31","arxiv_id":"2308.16609","repositories_listed":0,"syntology":null}],"record_sha256":"ad6bc07f716b1b3724cc86afa405730ebb6ab9d635151ab157a7b5c6a117f20f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}