{"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/26","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":26,"pages_in_order":43,"rows_per_page":100,"rows":[2501,2600],"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/25","next":"/task/knowledge-distillation/papers/27","papers":[{"url":null,"slug":"do-we-really-need-a-complex-agent-system","title":"Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model","date":"2024-04-06","arxiv_id":"2404.04619","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-happens-when-small-is-made-smaller","title":"What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models","date":"2024-04-06","arxiv_id":"2404.04759","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-small-language-models-help-large-language","title":"Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought","date":"2024-04-04","arxiv_id":"2404.03414","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-affinity-based-generalization-for","title":"Adaptive Affinity-Based Generalization For MRI Imaging Segmentation Across Resource-Limited Settings","date":"2024-04-03","arxiv_id":"2404.02738","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-knowledge-distillation-via-label","title":"Improve Knowledge Distillation via Label Revision and Data Selection","date":"2024-04-03","arxiv_id":"2404.03693","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-with-multi-granularity","title":"Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution","date":"2024-04-03","arxiv_id":"2404.02573","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-incremental-few-shot-event-detection","title":"Class-Incremental Few-Shot Event Detection","date":"2024-04-02","arxiv_id":"2404.01767","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-distillation-a-survey","title":"Federated Distillation: A Survey","date":"2024-04-02","arxiv_id":"2404.08564","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-integration-distillation-for-object","title":"Task Integration Distillation for Object Detectors","date":"2024-04-02","arxiv_id":"2404.01699","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-scalable-efficient-interaction-aware","title":"Towards Scalable & Efficient Interaction-Aware Planning in Autonomous Vehicles using Knowledge Distillation","date":"2024-04-02","arxiv_id":"2404.01746","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-review-of-knowledge","title":"A Comprehensive Review of Knowledge Distillation in Computer Vision","date":"2024-04-01","arxiv_id":"2404.00936","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-radjudge-achieving-radiologist-level","title":"LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation","date":"2024-04-01","arxiv_id":"2404.00998","repositories_listed":0,"syntology":null},{"url":null,"slug":"sugar-pre-training-3d-visual-representations","title":"SUGAR: Pre-training 3D Visual Representations for Robotics","date":"2024-04-01","arxiv_id":"2404.01491","repositories_listed":0,"syntology":null},{"url":null,"slug":"crkd-enhanced-camera-radar-object-detection","title":"CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation","date":"2024-03-28","arxiv_id":"2403.19104","repositories_listed":0,"syntology":null},{"url":null,"slug":"de-confounded-data-free-knowledge","title":"De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts","date":"2024-03-28","arxiv_id":"2403.19539","repositories_listed":0,"syntology":null},{"url":"/paper/gold-generalized-knowledge-distillation-via","slug":"gold-generalized-knowledge-distillation-via","title":"GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation","date":"2024-03-28","arxiv_id":"2403.19754","repositories_listed":0,"syntology":null},{"url":null,"slug":"i2ckd-intra-and-inter-class-knowledge","title":"I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation","date":"2024-03-27","arxiv_id":"2403.18490","repositories_listed":0,"syntology":null},{"url":null,"slug":"md-pk-metaphor-detection-via-prompt-learning","title":"Enhancing Metaphor Detection through Soft Labels and Target Word Prediction","date":"2024-03-27","arxiv_id":"2403.18253","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-compression-a-systematic-approach-to","title":"Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN","date":"2024-03-26","arxiv_id":"2403.17447","repositories_listed":0,"syntology":null},{"url":null,"slug":"oh-we-freeze-improving-quantized-knowledge","title":"Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models","date":"2024-03-26","arxiv_id":"2403.18159","repositories_listed":0,"syntology":null},{"url":"/paper/from-two-stream-to-one-stream-efficient-rgb-t","slug":"from-two-stream-to-one-stream-efficient-rgb-t","title":"From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation","date":"2024-03-25","arxiv_id":"2403.16834","repositories_listed":0,"syntology":null},{"url":null,"slug":"configurable-learned-holography","title":"Configurable Holography: Towards Display and Scene Adaptation","date":"2024-03-24","arxiv_id":"2405.01558","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-project-for-cross-task-knowledge","title":"Learning to Project for Cross-Task Knowledge Distillation","date":"2024-03-21","arxiv_id":"2403.14494","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformmix-learning-transformation-and","title":"TransformMix: Learning Transformation and Mixing Strategies from Data","date":"2024-03-19","arxiv_id":"2403.12429","repositories_listed":0,"syntology":null},{"url":null,"slug":"knfu-effective-knowledge-fusion","title":"KnFu: Effective Knowledge Fusion","date":"2024-03-18","arxiv_id":"2403.11892","repositories_listed":0,"syntology":null},{"url":null,"slug":"ttt-kd-test-time-training-for-3d-semantic","title":"TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models","date":"2024-03-18","arxiv_id":"2403.11691","repositories_listed":0,"syntology":null},{"url":null,"slug":"flykd-graph-knowledge-distillation-on-the-fly","title":"FlyKD: Graph Knowledge Distillation on the Fly with Curriculum Learning","date":"2024-03-16","arxiv_id":"2403.10807","repositories_listed":0,"syntology":null},{"url":null,"slug":"lookalike-human-mimicry-based-collaborative","title":"LookALike: Human Mimicry based collaborative decision making","date":"2024-03-16","arxiv_id":"2403.10824","repositories_listed":0,"syntology":null},{"url":null,"slug":"group-mix-sam-lightweight-solution-for","title":"Group-Mix SAM: Lightweight Solution for Industrial Assembly Line Applications","date":"2024-03-15","arxiv_id":"2403.10053","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-oc20-trained-equiformerv2-models-for","title":"Adapting OC20-trained EquiformerV2 Models for High-Entropy Materials","date":"2024-03-14","arxiv_id":"2403.09811","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-with-meta","title":"Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization","date":"2024-03-14","arxiv_id":"2403.09433","repositories_listed":0,"syntology":null},{"url":null,"slug":"select-and-distill-selective-dual-teacher","title":"Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models","date":"2024-03-14","arxiv_id":"2403.09296","repositories_listed":0,"syntology":null},{"url":null,"slug":"coronetgan-controlled-pruning-of-gans-via","title":"CoroNetGAN: Controlled Pruning of GANs via Hypernetworks","date":"2024-03-13","arxiv_id":"2403.08261","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-named-entity-recognition-models","title":"Distilling Named Entity Recognition Models for Endangered Species from Large Language Models","date":"2024-03-13","arxiv_id":"2403.15430","repositories_listed":0,"syntology":null},{"url":null,"slug":"lix-implicitly-infusing-spatial-geometric","title":"LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving","date":"2024-03-13","arxiv_id":"2403.08215","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-self-localization-models-for-unseen","title":"Training Self-localization Models for Unseen Unfamiliar Places via Teacher-to-Student Data-Free Knowledge Transfer","date":"2024-03-13","arxiv_id":"2403.10552","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-the-knowledge-in-data-pruning","title":"Distilling the Knowledge in Data Pruning","date":"2024-03-12","arxiv_id":"2403.07854","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-sparsification-via-stimulative","title":"Enhanced Sparsification via Stimulative Training","date":"2024-03-11","arxiv_id":"2403.06417","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-adversarial-training-with-prior","title":"Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression","date":"2024-03-11","arxiv_id":"2403.06700","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-knowledge-distillation-with-large","title":"Evolving Knowledge Distillation with Large Language Models and Active Learning","date":"2024-03-11","arxiv_id":"2403.06414","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-category-one-prompt-dataset-distillation","title":"One Category One Prompt: Dataset Distillation using Diffusion Models","date":"2024-03-11","arxiv_id":"2403.07142","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-is-all-you-need-for-boosting-graph","title":"Attention is all you need for boosting graph convolutional neural network","date":"2024-03-10","arxiv_id":"2403.15419","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-of-convolutional","title":"Knowledge Distillation of Convolutional Neural Networks through Feature Map Transformation using Decision Trees","date":"2024-03-10","arxiv_id":"2403.06089","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-sparse-teacher-defense-against","title":"Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples","date":"2024-03-08","arxiv_id":"2403.05181","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-guided-feature-distillation-for","title":"Attention-guided Feature Distillation for Semantic Segmentation","date":"2024-03-08","arxiv_id":"2403.05451","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-a-multiple-instance-learning","title":"Fine-tuning a Multiple Instance Learning Feature Extractor with Masked Context Modelling and Knowledge Distillation","date":"2024-03-08","arxiv_id":"2403.05325","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graph-aided-radiology-report-generation","title":"Scene Graph Aided Radiology Report Generation","date":"2024-03-08","arxiv_id":"2403.05687","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-small-language-models-be-good-reasoners","title":"Can Small Language Models be Good Reasoners for Sequential Recommendation?","date":"2024-03-07","arxiv_id":"2403.04260","repositories_listed":0,"syntology":null},{"url":null,"slug":"mkf-ads-a-multi-knowledge-fused-anomaly","title":"MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network","date":"2024-03-07","arxiv_id":"2403.04293","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-fine-tuning-of-large","title":"Privacy-preserving Fine-tuning of Large Language Models through Flatness","date":"2024-03-07","arxiv_id":"2403.04124","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilled-chatgpt-topic-sentiment-modeling","title":"Distilled ChatGPT Topic & Sentiment Modeling with Applications in Finance","date":"2024-03-04","arxiv_id":"2403.02185","repositories_listed":0,"syntology":null},{"url":null,"slug":"jep-kd-joint-embedding-predictive","title":"JEP-KD: Joint-Embedding Predictive Architecture Based Knowledge Distillation for Visual Speech Recognition","date":"2024-03-04","arxiv_id":"2403.18843","repositories_listed":0,"syntology":null},{"url":null,"slug":"ub-finenet-urban-building-fine-grained","title":"UB-FineNet: Urban Building Fine-grained Classification Network for Open-access Satellite Images","date":"2024-03-04","arxiv_id":"2403.02132","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-wav2vec2-embeddings-for-on","title":"A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement","date":"2024-03-03","arxiv_id":"2403.01369","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperspectral-image-analysis-in-single-modal","title":"Hyperspectral Image Analysis in Single-Modal and Multimodal setting using Deep Learning Techniques","date":"2024-03-03","arxiv_id":"2403.01546","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-text-style-transfer-with-self","title":"Distilling Text Style Transfer With Self-Explanation From LLMs","date":"2024-03-02","arxiv_id":"2403.01106","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-mlp-more-graph-information-a-three","title":"Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework","date":"2024-03-02","arxiv_id":"2403.01079","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-event-camera-pre-training-via","title":"Data-efficient Event Camera Pre-training via Disentangled Masked Modeling","date":"2024-03-01","arxiv_id":"2403.00416","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-alignment-of-draft-model-for","title":"Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs","date":"2024-02-29","arxiv_id":"2403.00858","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-monocular-3d-detection-with","title":"Weakly Supervised Monocular 3D Detection with a Single-View Image","date":"2024-02-29","arxiv_id":"2402.19144","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lightweight-low-light-image-enhancement","title":"A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correction","date":"2024-02-28","arxiv_id":"2402.18147","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-reweighting-towards-imbalanced-class","title":"Gradient Reweighting: Towards Imbalanced Class-Incremental Learning","date":"2024-02-28","arxiv_id":"2402.18528","repositories_listed":0,"syntology":null},{"url":null,"slug":"miko-multimodal-intention-knowledge","title":"MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery","date":"2024-02-28","arxiv_id":"2402.18169","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcf-vc-mitigate-catastrophic-forgetting-in","title":"MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning","date":"2024-02-27","arxiv_id":"2402.17680","repositories_listed":0,"syntology":null},{"url":null,"slug":"sddgr-stable-diffusion-based-deep-generative","title":"SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection","date":"2024-02-27","arxiv_id":"2402.17323","repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-teacher-student-normality-learning","title":"Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localization","date":"2024-02-27","arxiv_id":"2402.17091","repositories_listed":0,"syntology":null},{"url":null,"slug":"dtcm-deep-transformer-capsule-mutual","title":"DTCM: Deep Transformer Capsule Mutual Distillation for Multivariate Time Series Classification","date":"2024-02-26","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-privacy-data-augmentation-guided-by","title":"LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification","date":"2024-02-26","arxiv_id":"2402.16515","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-similarity-aware-knowledge-distillation","title":"SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning","date":"2024-02-26","arxiv_id":"2402.16830","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-adversarial-robustness-using","title":"Distilling Adversarial Robustness Using Heterogeneous Teachers","date":"2024-02-23","arxiv_id":"2402.15586","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-systematic-decompositional-natural","title":"Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic","date":"2024-02-22","arxiv_id":"2402.14798","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-insights-into-knowledge","title":"Practical Insights into Knowledge Distillation for Pre-Trained Models","date":"2024-02-22","arxiv_id":"2402.14922","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-invariance-regularization-in","title":"Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off","date":"2024-02-22","arxiv_id":"2402.14648","repositories_listed":0,"syntology":null},{"url":null,"slug":"push-quantization-aware-training-toward-full","title":"In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training","date":"2024-02-21","arxiv_id":"2402.13497","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-text-style-transfer-via-llms-and","title":"Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions","date":"2024-02-21","arxiv_id":"2402.13647","repositories_listed":0,"syntology":null},{"url":null,"slug":"wisdom-of-committee-distilling-from","title":"Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model","date":"2024-02-21","arxiv_id":"2402.14035","repositories_listed":0,"syntology":null},{"url":null,"slug":"elad-explanation-guided-large-language-models","title":"ELAD: Explanation-Guided Large Language Models Active Distillation","date":"2024-02-20","arxiv_id":"2402.13098","repositories_listed":0,"syntology":null},{"url":null,"slug":"fgad-self-boosted-knowledge-distillation-for","title":"FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework","date":"2024-02-20","arxiv_id":"2402.12761","repositories_listed":0,"syntology":null},{"url":null,"slug":"pirb-a-comprehensive-benchmark-of-polish","title":"PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods","date":"2024-02-20","arxiv_id":"2402.13350","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-good-practices-for-task-specific","title":"On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models","date":"2024-02-17","arxiv_id":"2402.11305","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedd2s-personalized-data-free-federated","title":"FedD2S: Personalized Data-Free Federated Knowledge Distillation","date":"2024-02-16","arxiv_id":"2402.10846","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-cultural-commonsense-knowledge","title":"Cultural Commonsense Knowledge for Intercultural Dialogues","date":"2024-02-16","arxiv_id":"2402.10689","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-and-efficient-inference-for","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","date":"2024-02-15","arxiv_id":"2402.09748","repositories_listed":0,"syntology":null},{"url":null,"slug":"walsh-domain-neural-network-for-power","title":"Walsh-domain Neural Network for Power Amplifier Behavioral Modelling and Digital Predistortion","date":"2024-02-15","arxiv_id":"2402.09964","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-chatgpt-into-secure-hospital","title":"Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis","date":"2024-02-14","arxiv_id":"2402.09358","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-models-for-enhanced-1","title":"Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies","date":"2024-02-14","arxiv_id":"2402.09282","repositories_listed":0,"syntology":null},{"url":null,"slug":"apalu-a-trainable-adaptive-activation","title":"APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks","date":"2024-02-13","arxiv_id":"2402.08244","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stage-multi-task-self-supervised-learning","title":"Two-Stage Multi-task Self-Supervised Learning for Medical Image Segmentation","date":"2024-02-11","arxiv_id":"2402.07119","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-compression-for-teacher-to-student","title":"Embedding Compression for Teacher-to-Student Knowledge Transfer","date":"2024-02-09","arxiv_id":"2402.06761","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-meets-graph-neural","title":"Large Language Model Meets Graph Neural Network in Knowledge Distillation","date":"2024-02-08","arxiv_id":"2402.05894","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-road-detection","title":"Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning","date":"2024-02-07","arxiv_id":"2402.05305","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-transformer-compression","title":"A Survey on Transformer Compression","date":"2024-02-05","arxiv_id":"2402.05964","repositories_listed":0,"syntology":null},{"url":"/paper/dual-knowledge-distillation-for-efficient","slug":"dual-knowledge-distillation-for-efficient","title":"Dual Knowledge Distillation for Efficient Sound Event Detection","date":"2024-02-05","arxiv_id":"2402.02781","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-cryptonets-leveraging-different-level","title":"Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inference","date":"2024-02-02","arxiv_id":"2402.01296","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-inference-of-integer-swin-transformer","title":"Faster Inference of Integer SWIN Transformer by Removing the GELU Activation","date":"2024-02-02","arxiv_id":"2402.01169","repositories_listed":0,"syntology":null},{"url":null,"slug":"spiking-centernet-a-distillation-boosted","title":"Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection","date":"2024-02-02","arxiv_id":"2402.01287","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-bias-through-ensemble-learning-and","title":"Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning","date":"2024-02-01","arxiv_id":"2402.00910","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-conditional-diffusion-models-for","title":"Augmenting Offline Reinforcement Learning with State-only Interactions","date":"2024-02-01","arxiv_id":"2402.00807","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-student-knowledge-distillation-networks","title":"Dual-Student Knowledge Distillation Networks for Unsupervised Anomaly Detection","date":"2024-02-01","arxiv_id":"2402.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"epsd-early-pruning-with-self-distillation-for","title":"EPSD: Early Pruning with Self-Distillation for Efficient Model Compression","date":"2024-01-31","arxiv_id":"2402.00084","repositories_listed":0,"syntology":null}],"record_sha256":"ae8668101988b89a2312929faaf676d3ea4522a018d55a6d539d42aaf715755c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}