{"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/23","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":23,"pages_in_order":43,"rows_per_page":100,"rows":[2201,2300],"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/22","next":"/task/knowledge-distillation/papers/24","papers":[{"url":null,"slug":"reasoningrank-teaching-student-models-to-rank","title":"ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation","date":"2024-10-07","arxiv_id":"2410.05168","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-diffusion-models-with-one-to","title":"Accelerating Diffusion Models with One-to-Many Knowledge Distillation","date":"2024-10-05","arxiv_id":"2410.04191","repositories_listed":0,"syntology":null},{"url":null,"slug":"didots-knowledge-distillation-from-large","title":"DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech","date":"2024-10-05","arxiv_id":"2410.04188","repositories_listed":0,"syntology":null},{"url":null,"slug":"gap-preserving-distillation-by-building","title":"Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher","date":"2024-10-05","arxiv_id":"2410.04140","repositories_listed":0,"syntology":null},{"url":null,"slug":"dockd-knowledge-distillation-from-llms-for","title":"DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models","date":"2024-10-04","arxiv_id":"2410.03061","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-keypoint-detection-with","title":"Self-Supervised Keypoint Detection with Distilled Depth Keypoint Representation","date":"2024-10-04","arxiv_id":"2410.14700","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-medical-radiograph-representation","title":"Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with Multilevel Semantic Granularity","date":"2024-10-01","arxiv_id":"2410.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-recurrent-neural-networks-for","title":"Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging","date":"2024-10-01","arxiv_id":"2410.00948","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-technical-term-translation-a","title":"Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation","date":"2024-10-01","arxiv_id":"2410.00683","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-to-global-self-supervised","title":"Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading","date":"2024-10-01","arxiv_id":"2410.00779","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-updatable-large-language-models-with","title":"Self-Updatable Large Language Models with Parameter Integration","date":"2024-10-01","arxiv_id":"2410.00487","repositories_listed":0,"syntology":null},{"url":null,"slug":"classroom-inspired-multi-mentor-distillation","title":"Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies","date":"2024-09-30","arxiv_id":"2409.20237","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-romanian-offensive-language","title":"Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation","date":"2024-09-30","arxiv_id":"2409.20498","repositories_listed":0,"syntology":null},{"url":null,"slug":"hydra-fl-hybrid-knowledge-distillation-for","title":"HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning","date":"2024-09-30","arxiv_id":"2409.19912","repositories_listed":0,"syntology":null},{"url":null,"slug":"linear-projections-of-teacher-embeddings-for","title":"Linear Projections of Teacher Embeddings for Few-Class Distillation","date":"2024-09-30","arxiv_id":"2409.20449","repositories_listed":0,"syntology":null},{"url":null,"slug":"infantcrynet-a-data-driven-framework-for","title":"InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries","date":"2024-09-29","arxiv_id":"2409.19689","repositories_listed":0,"syntology":null},{"url":null,"slug":"tailored-federated-learning-leveraging","title":"Tailored Federated Learning: Leveraging Direction Regulation & Knowledge Distillation","date":"2024-09-29","arxiv_id":"2409.19741","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-the-gap-promoting-missing-modality-brain","title":"Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment","date":"2024-09-28","arxiv_id":"2409.19366","repositories_listed":0,"syntology":null},{"url":null,"slug":"harmonizing-knowledge-transfer-in-neural","title":"Harmonizing knowledge Transfer in Neural Network with Unified Distillation","date":"2024-09-27","arxiv_id":"2409.18565","repositories_listed":0,"syntology":null},{"url":null,"slug":"minivln-efficient-vision-and-language","title":"MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation","date":"2024-09-27","arxiv_id":"2409.18800","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-cross-domain-self-supervised-pre","title":"Multi-modal Cross-domain Self-supervised Pre-training for fMRI and EEG Fusion","date":"2024-09-27","arxiv_id":"2409.19130","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-bone-marrow-lesion-detection","title":"Semi-Supervised Bone Marrow Lesion Detection from Knee MRI Segmentation Using Mask Inpainting Models","date":"2024-09-27","arxiv_id":"2409.19185","repositories_listed":0,"syntology":null},{"url":null,"slug":"student-oriented-teacher-knowledge-refinement","title":"Student-Oriented Teacher Knowledge Refinement for Knowledge Distillation","date":"2024-09-27","arxiv_id":"2409.18785","repositories_listed":0,"syntology":null},{"url":null,"slug":"kendall-s-t-coefficient-for-logits","title":"Kendall's $τ$ Coefficient for Logits Distillation","date":"2024-09-26","arxiv_id":"2409.17823","repositories_listed":0,"syntology":null},{"url":null,"slug":"weak-to-strong-backdoor-attacks-for-llms-with","title":"Weak-to-Strong Backdoor Attack for Large Language Models","date":"2024-09-26","arxiv_id":"2409.17946","repositories_listed":0,"syntology":null},{"url":null,"slug":"adverse-weather-optical-flow-cumulative","title":"Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptation","date":"2024-09-25","arxiv_id":"2409.17001","repositories_listed":0,"syntology":null},{"url":null,"slug":"mt2kd-towards-a-general-purpose-encoder-for","title":"MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events","date":"2024-09-25","arxiv_id":"2409.17010","repositories_listed":0,"syntology":null},{"url":null,"slug":"selectivekd-a-semi-supervised-framework-for","title":"SelectiveKD: A semi-supervised framework for cancer detection in DBT through Knowledge Distillation and Pseudo-labeling","date":"2024-09-25","arxiv_id":"2409.16581","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-evaluation-benchmarks-for-nlp-models","title":"Privacy Evaluation Benchmarks for NLP Models","date":"2024-09-24","arxiv_id":"2409.15868","repositories_listed":0,"syntology":null},{"url":null,"slug":"twin-network-augmentation-a-novel-training","title":"Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization","date":"2024-09-24","arxiv_id":"2409.15849","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-language-model-and-knowledge","title":"Pre-trained Language Model and Knowledge Distillation for Lightweight Sequential Recommendation","date":"2024-09-23","arxiv_id":"2409.14810","repositories_listed":0,"syntology":null},{"url":null,"slug":"ts-tcd-triplet-level-cross-modal-distillation","title":"TS-HTFA: Advancing Time Series Forecasting via Hierarchical Text-Free Alignment with Large Language Models","date":"2024-09-23","arxiv_id":"2409.14978","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilatequant-accurate-and-efficient-diffusion","title":"DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation","date":"2024-09-22","arxiv_id":"2409.14307","repositories_listed":0,"syntology":null},{"url":null,"slug":"echoatt-attend-copy-then-adjust-for-more","title":"EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models","date":"2024-09-22","arxiv_id":"2409.14595","repositories_listed":0,"syntology":null},{"url":null,"slug":"prior-knowledge-distillation-network-for-face","title":"Prior Knowledge Distillation Network for Face Super-Resolution","date":"2024-09-22","arxiv_id":"2409.14385","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14162","title":"On Importance of Pruning and Distillation for Efficient Low Resource NLP","date":"2024-09-21","arxiv_id":"2409.14162","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-in-birdsong-classification","title":"Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics","date":"2024-09-21","arxiv_id":"2409.15383","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-streaming-transducer-asr-prototyping-via","title":"Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper","date":"2024-09-20","arxiv_id":"2409.13499","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-unsupervised-knowledge-distillation","title":"Simple Unsupervised Knowledge Distillation With Space Similarity","date":"2024-09-20","arxiv_id":"2409.13939","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-optimized-one-step-diffusion-model","title":"Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction","date":"2024-09-19","arxiv_id":"2409.12456","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-knowledge-distillation-empowering","title":"Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights","date":"2024-09-19","arxiv_id":"2409.12586","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-slm-via-chatgpt-and-dataset","title":"Enhancing SLM via ChatGPT and Dataset Augmentation","date":"2024-09-19","arxiv_id":"2409.12599","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-and-enhancing-the-transfer-of","title":"Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models","date":"2024-09-19","arxiv_id":"2409.12512","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cone-beam-ct-image-quality-with","title":"Improving Cone-Beam CT Image Quality with Knowledge Distillation-Enhanced Diffusion Model in Imbalanced Data Settings","date":"2024-09-19","arxiv_id":"2409.12539","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmr-knowledge-distillation-with-a-large","title":"LLMR: Knowledge Distillation with a Large Language Model-Induced Reward","date":"2024-09-19","arxiv_id":"2409.12500","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-models-are-equation-reasoners","title":"Small Language Models are Equation Reasoners","date":"2024-09-19","arxiv_id":"2409.12393","repositories_listed":0,"syntology":null},{"url":null,"slug":"applications-of-knowledge-distillation-in","title":"Applications of Knowledge Distillation in Remote Sensing: A Survey","date":"2024-09-18","arxiv_id":"2409.12111","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-acoustic-scene-classification","title":"Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction","date":"2024-09-18","arxiv_id":"2409.11964","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillation-free-scaling-of-large-ssms-for","title":"StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos","date":"2024-09-18","arxiv_id":"2409.11867","repositories_listed":0,"syntology":null},{"url":null,"slug":"efcm-efficient-fine-tuning-on-compressed","title":"EFCM: Efficient Fine-tuning on Compressed Models for deployment of large models in medical image analysis","date":"2024-09-18","arxiv_id":"2409.11817","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-stage-tts-with-masked-audio-token","title":"Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation","date":"2024-09-17","arxiv_id":"2409.11003","repositories_listed":0,"syntology":null},{"url":null,"slug":"unleashing-the-potential-of-mamba-boosting-a","title":"Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation","date":"2024-09-17","arxiv_id":"2409.11018","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-insights-driven-latent-space-for","title":"Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference","date":"2024-09-16","arxiv_id":"2409.10095","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrated-multi-level-knowledge-distillation","title":"Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification","date":"2024-09-14","arxiv_id":"2409.09389","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-semantic-knowledge-distillation-and","title":"Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility","date":"2024-09-14","arxiv_id":"2409.09357","repositories_listed":0,"syntology":null},{"url":null,"slug":"awf-adaptive-weight-fusion-for-enhanced-class","title":"AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentation","date":"2024-09-13","arxiv_id":"2409.08516","repositories_listed":0,"syntology":null},{"url":null,"slug":"diredi-distillation-and-reverse-distillation","title":"DiReDi: Distillation and Reverse Distillation for AIoT Applications","date":"2024-09-12","arxiv_id":"2409.08308","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-from-balance-rectifying-knowledge","title":"Learn from Balance: Rectifying Knowledge Transfer for Long-Tailed Scenarios","date":"2024-09-12","arxiv_id":"2409.07694","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-continual-and-incremental-learning-approach","title":"A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption","date":"2024-09-11","arxiv_id":"2409.07114","repositories_listed":0,"syntology":null},{"url":null,"slug":"ds-vit-dual-stream-vision-transformer-for","title":"DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis","date":"2024-09-11","arxiv_id":"2409.07584","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-ctc-based-visual-speech-recognition","title":"Enhancing CTC-Based Visual Speech Recognition","date":"2024-09-11","arxiv_id":"2409.07210","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-federated-learning-with-1","title":"Privacy-Preserving Federated Learning with Consistency via Knowledge Distillation Using Conditional Generator","date":"2024-09-11","arxiv_id":"2409.06955","repositories_listed":0,"syntology":null},{"url":null,"slug":"applied-federated-model-personalisation-in","title":"Applied Federated Model Personalisation in the Industrial Domain: A Comparative Study","date":"2024-09-10","arxiv_id":"2409.06904","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-generative-discriminative","title":"Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition","date":"2024-09-10","arxiv_id":"2409.06371","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-redundant-is-the-transformer-stack-in","title":"How Redundant Is the Transformer Stack in Speech Representation Models?","date":"2024-09-10","arxiv_id":"2409.16302","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-via-query-selection","title":"Knowledge Distillation via Query Selection for Detection Transformer","date":"2024-09-10","arxiv_id":"2409.06443","repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-emotion-recognition-system-using","title":"Complex Emotion Recognition System using basic emotions via Facial Expression, EEG, and ECG Signals: a review","date":"2024-09-09","arxiv_id":"2409.07493","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-input-and-output-coordination-for-class","title":"Joint Input and Output Coordination for Class-Incremental Learning","date":"2024-09-09","arxiv_id":"2409.05620","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-one-and-more-distilling-hybrid-order","title":"Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition","date":"2024-09-09","arxiv_id":"2409.05384","repositories_listed":0,"syntology":null},{"url":null,"slug":"loca-logit-calibration-for-knowledge","title":"LoCa: Logit Calibration for Knowledge Distillation","date":"2024-09-07","arxiv_id":"2409.04778","repositories_listed":0,"syntology":null},{"url":null,"slug":"scarf-scalable-continual-learning-framework","title":"SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields","date":"2024-09-06","arxiv_id":"2409.04482","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-distillation-with-degradation","title":"Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration","date":"2024-09-05","arxiv_id":"2409.03455","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimentation-in-content-moderation-using","title":"Experimentation in Content Moderation using RWKV","date":"2024-09-05","arxiv_id":"2409.03939","repositories_listed":0,"syntology":null},{"url":null,"slug":"clda-collaborative-learning-for-enhanced","title":"Collaborative Learning for Enhanced Unsupervised Domain Adaptation","date":"2024-09-04","arxiv_id":"2409.02699","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-image-compression-using-advanced","title":"Efficient Image Compression Using Advanced State Space Models","date":"2024-09-04","arxiv_id":"2409.02743","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resolution-object-recognition-with-cross","title":"Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation","date":"2024-09-04","arxiv_id":"2409.02555","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-target-divergence-hypothesis-toward","title":"Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation","date":"2024-09-04","arxiv_id":"2409.02438","repositories_listed":0,"syntology":null},{"url":"/paper/sorbet-a-neuromorphic-hardware-compatible","slug":"sorbet-a-neuromorphic-hardware-compatible","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","date":"2024-09-04","arxiv_id":"2409.15298","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sorbet-a-neuromorphic-hardware-compatible#ran","syntology_url":"https://syntology.ai/paper/2409.15298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15298"}},"official":null}},{"url":null,"slug":"adaptive-explicit-knowledge-transfer-for","title":"Adaptive Explicit Knowledge Transfer for Knowledge Distillation","date":"2024-09-03","arxiv_id":"2409.01679","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-point-cloud-classification-via","title":"Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique","date":"2024-09-03","arxiv_id":"2409.02020","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-apple-object-detection-with","title":"Improving Apple Object Detection with Occlusion-Enhanced Distillation","date":"2024-09-03","arxiv_id":"2409.01573","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resolution-face-recognition-via-adaptable","title":"Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation","date":"2024-09-03","arxiv_id":"2409.02049","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-vae-based-out-of-distribution","title":"Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment","date":"2024-09-02","arxiv_id":"2409.00880","repositories_listed":0,"syntology":null},{"url":null,"slug":"smaller-weaker-yet-better-training-llm","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","date":"2024-08-29","arxiv_id":"2408.16737","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-kd-knowledge-distillation-from-vlm-for","title":"VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition","date":"2024-08-29","arxiv_id":"2408.16930","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-lossless-speculative-decoding-via","title":"Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation","date":"2024-08-28","arxiv_id":"2408.15562","repositories_listed":0,"syntology":null},{"url":null,"slug":"modalitymirror-improving-audio-classification","title":"ModalityMirror: Improving Audio Classification in Modality Heterogeneity Federated Learning with Multimodal Distillation","date":"2024-08-28","arxiv_id":"2408.15803","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-pre-training-with-long-form-videos","title":"Online pre-training with long-form videos","date":"2024-08-28","arxiv_id":"2408.15651","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-unpacking-the-hidden","title":"Bridging the Gap: Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems","date":"2024-08-26","arxiv_id":"2408.14678","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-video-teaches-you-more-video-to-image","title":"Let Video Teaches You More: Video-to-Image Knowledge Distillation using DEtection TRansformer for Medical Video Lesion Detection","date":"2024-08-26","arxiv_id":"2408.14051","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsak-two-stage-semantic-aware-knowledge","title":"TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines","date":"2024-08-26","arxiv_id":"2408.14146","repositories_listed":0,"syntology":null},{"url":null,"slug":"bring-the-power-of-diffusion-model-to-defect","title":"Bring the Power of Diffusion Model to Defect Detection","date":"2024-08-25","arxiv_id":"2408.13845","repositories_listed":0,"syntology":null},{"url":null,"slug":"condensed-sample-guided-model-inversion-for","title":"Condensed Sample-Guided Model Inversion for Knowledge Distillation","date":"2024-08-25","arxiv_id":"2408.13850","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundational-model-for-electron-micrograph","title":"Foundational Model for Electron Micrograph Analysis: Instruction-Tuning Small-Scale Language-and-Vision Assistant for Enterprise Adoption","date":"2024-08-23","arxiv_id":"2408.13248","repositories_listed":0,"syntology":null},{"url":null,"slug":"growing-deep-neural-network-considering-with","title":"Growing Deep Neural Network Considering with Similarity between Neurons","date":"2024-08-23","arxiv_id":"2408.13291","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-dualchecker-for-mitigating","title":"Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models","date":"2024-08-22","arxiv_id":"2408.12326","repositories_listed":0,"syntology":null},{"url":null,"slug":"rebalancing-multi-label-class-incremental","title":"Rebalancing Multi-Label Class-Incremental Learning","date":"2024-08-22","arxiv_id":"2408.12161","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-detection-of-uncooperative","title":"Vision-Based Detection of Uncooperative Targets and Components on Small Satellites","date":"2024-08-22","arxiv_id":"2408.12084","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-framework-for-continual-learning","title":"A Unified Framework for Continual Learning and Unlearning","date":"2024-08-21","arxiv_id":"2408.11374","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-invariant-progressive-knowledge","title":"Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection","date":"2024-08-21","arxiv_id":"2408.11407","repositories_listed":0,"syntology":null}],"record_sha256":"18c90edd685bbefa66191accba9018038902f959f72c7470bfde36e0200e0523","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}