{"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":"/method/knowledge-distillation/papers/12","list_of":"/method/knowledge-distillation","method":"Knowledge Distillation","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":12,"pages_in_order":31,"rows_per_page":100,"rows":[1101,1200],"of":3071,"counts":{"archive_papers_tagged":3071,"with_a_code_link":1258,"where_syntology_ran_a_sample":320,"not_listed_spam_title":0,"listed":3071,"listed_where_code_ran":320,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":276,"every_run_a_failure_of_syntologys_instrument":44,"listed_with_a_run_with_no_instrument_failure":276,"listed_every_run_a_failure_of_syntologys_instrument":44,"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":"/method/knowledge-distillation","prev":"/method/knowledge-distillation/papers/11","next":"/method/knowledge-distillation/papers/13","papers":[{"paper":"/paper/language-model-knowledge-distillation-for","slug":"language-model-knowledge-distillation-for","title":"Language Model Knowledge Distillation for Efficient Question Answering in Spanish","date":"2023-12-07","arxiv_id":"2312.04193","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["adrianbzg/tinyroberta-distillation-qa-es"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-and-adapting-in-the-clinic-source","slug":"enhancing-and-adapting-in-the-clinic-source","title":"Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement","date":"2023-12-03","arxiv_id":"2312.01338","n_code_links":1,"syntology":null},{"paper":"/paper/dual-teacher-de-biasing-distillation","slug":"dual-teacher-de-biasing-distillation","title":"Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detection","date":"2023-12-02","arxiv_id":"2312.01006","n_code_links":1,"syntology":null},{"paper":null,"slug":"s2p3-self-supervised-polarimetric-pose","title":"S2P3: Self-Supervised Polarimetric Pose Prediction","date":"2023-12-02","arxiv_id":"2312.01105","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-label-efficient-3d-scene-parsing","slug":"generalized-label-efficient-3d-scene-parsing","title":"Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment","date":"2023-12-01","arxiv_id":"2312.00663","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/continual-learning-for-image-segmentation","slug":"continual-learning-for-image-segmentation","title":"Continual Learning for Image Segmentation with Dynamic Query","date":"2023-11-29","arxiv_id":"2311.17450","n_code_links":1,"syntology":null},{"paper":null,"slug":"layercollapse-adaptive-compression-of-neural","title":"LayerCollapse: Adaptive compression of neural networks","date":"2023-11-29","arxiv_id":"2311.17943","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusiontalker-personalization-and","title":"DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser","date":"2023-11-28","arxiv_id":"2311.16565","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/lightgaussian-unbounded-3d-gaussian","slug":"lightgaussian-unbounded-3d-gaussian","title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","date":"2023-11-28","arxiv_id":"2311.17245","n_code_links":1,"syntology":{"ran":17,"of":22,"n_ran_checked":3,"n_instrument":14,"unverified":5,"pointer_only":22,"phrase":"17 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified","official":{"repos":["VITA-Group/LightGaussian"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/pea-diffusion-parameter-efficient-adapter","slug":"pea-diffusion-parameter-efficient-adapter","title":"PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation","date":"2023-11-28","arxiv_id":"2311.17086","n_code_links":1,"syntology":null},{"paper":"/paper/ufin-universal-feature-interaction-network","slug":"ufin-universal-feature-interaction-network","title":"UFIN: Universal Feature Interaction Network for Multi-Domain Click-Through Rate Prediction","date":"2023-11-27","arxiv_id":"2311.15493","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlearning-via-sparse-representations","title":"Unlearning via Sparse Representations","date":"2023-11-26","arxiv_id":"2311.15268","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"maximizing-discrimination-capability-of","title":"Maximizing Discrimination Capability of Knowledge Distillation with Energy Function","date":"2023-11-24","arxiv_id":"2311.14334","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-and-robust-jet-tagging-at-the-lhc","slug":"efficient-and-robust-jet-tagging-at-the-lhc","title":"Efficient and Robust Jet Tagging at the LHC with Knowledge Distillation","date":"2023-11-23","arxiv_id":"2311.14160","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ryanliu30/kd4jets"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knowledge-distillation-based-semantic","title":"Knowledge Distillation Based Semantic Communications For Multiple Users","date":"2023-11-23","arxiv_id":"2311.13789","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-transformer-knowledge-distillation","title":"Efficient Transformer Knowledge Distillation: A Performance Review","date":"2023-11-22","arxiv_id":"2311.13657","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-from-the-dark-side-entropy","title":"EA-KD: Entropy-based Adaptive Knowledge Distillation","date":"2023-11-22","arxiv_id":"2311.13621","n_code_links":0,"syntology":null},{"paper":"/paper/point-segment-and-count-a-generalized","slug":"point-segment-and-count-a-generalized","title":"Point, Segment and Count: A Generalized Framework for Object Counting","date":"2023-11-21","arxiv_id":"2311.12386","n_code_links":1,"syntology":null},{"paper":"/paper/freekd-knowledge-distillation-via-semantic","slug":"freekd-knowledge-distillation-via-semantic","title":"FreeKD: Knowledge Distillation via Semantic Frequency Prompt","date":"2023-11-20","arxiv_id":"2311.12079","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Gumpest/FreeKD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/multistage-collaborative-knowledge","slug":"multistage-collaborative-knowledge","title":"Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation","date":"2023-11-15","arxiv_id":"2311.08640","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["andotalao24/multistage-collaborative-knowledge-distillation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-elastic-language-models","title":"On Elastic Language Models","date":"2023-11-13","arxiv_id":"2311.07204","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/quantized-distillation-optimizing-driver","slug":"quantized-distillation-optimizing-driver","title":"Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environments","date":"2023-11-10","arxiv_id":"2311.05970","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/text-representation-distillation-via","slug":"text-representation-distillation-via","title":"Text Representation Distillation via Information Bottleneck Principle","date":"2023-11-09","arxiv_id":"2311.05472","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/data-exploitation-multi-task-learning-of","slug":"data-exploitation-multi-task-learning-of","title":"Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data","date":"2023-11-07","arxiv_id":"2311.04040","n_code_links":1,"syntology":null},{"paper":"/paper/reducing-spatial-fitting-error-in","slug":"reducing-spatial-fitting-error-in","title":"Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models","date":"2023-11-07","arxiv_id":"2311.03830","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-is-lost-in-knowledge-distillation","title":"What is Lost in Knowledge Distillation?","date":"2023-11-07","arxiv_id":"2311.04142","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":0,"syntology":null},{"paper":"/paper/cross-level-distillation-and-feature","slug":"cross-level-distillation-and-feature","title":"Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification","date":"2023-11-04","arxiv_id":"2311.02392","n_code_links":1,"syntology":null},{"paper":"/paper/comparative-knowledge-distillation","slug":"comparative-knowledge-distillation","title":"Comparative Knowledge Distillation","date":"2023-11-03","arxiv_id":"2311.02253","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-out-of-distribution-robustness-1","slug":"distilling-out-of-distribution-robustness-1","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","date":"2023-11-02","arxiv_id":"2311.01441","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["lapisrocks/DiscreteAdversarialDistillation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/distilwhisper-efficient-distillation-of-multi","slug":"distilwhisper-efficient-distillation-of-multi","title":"Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts","date":"2023-11-02","arxiv_id":"2311.01070","n_code_links":1,"syntology":null},{"paper":"/paper/low-latency-real-time-voice-conversion-on-cpu","slug":"low-latency-real-time-voice-conversion-on-cpu","title":"Low-latency Real-time Voice Conversion on CPU","date":"2023-11-01","arxiv_id":"2311.00873","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/amlnet-adversarial-mutual-learning-neural","slug":"amlnet-adversarial-mutual-learning-neural","title":"AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting","date":"2023-10-30","arxiv_id":"2310.19289","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/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,"n_code_links":0,"syntology":null},{"paper":"/paper/discourse-structures-guided-fine-grained","slug":"discourse-structures-guided-fine-grained","title":"Discourse Structures Guided Fine-grained Propaganda Identification","date":"2023-10-28","arxiv_id":"2310.18544","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/odm3d-alleviating-foreground-sparsity-for","slug":"odm3d-alleviating-foreground-sparsity-for","title":"ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection","date":"2023-10-28","arxiv_id":"2310.18620","n_code_links":1,"syntology":null},{"paper":"/paper/towards-a-unified-conversational","slug":"towards-a-unified-conversational","title":"Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation","date":"2023-10-27","arxiv_id":"2310.18119","n_code_links":1,"syntology":null},{"paper":"/paper/fantastic-gains-and-where-to-find-them-on-the","slug":"fantastic-gains-and-where-to-find-them-on-the","title":"Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model","date":"2023-10-26","arxiv_id":"2310.17653","n_code_links":1,"syntology":null},{"paper":"/paper/torchdistill-meets-hugging-face-libraries-for","slug":"torchdistill-meets-hugging-face-libraries-for","title":"torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP","date":"2023-10-26","arxiv_id":"2310.17644","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-the-effects-of-projectors-in","slug":"understanding-the-effects-of-projectors-in","title":"Understanding the Effects of Projectors in Knowledge Distillation","date":"2023-10-26","arxiv_id":"2310.17183","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/cross-feature-contrastive-loss-for","slug":"cross-feature-contrastive-loss-for","title":"Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data","date":"2023-10-24","arxiv_id":"2310.15890","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-convolutional-neural-networks-as","slug":"dynamic-convolutional-neural-networks-as","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","date":"2023-10-24","arxiv_id":"2310.15648","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/mcc-kd-multi-cot-consistent-knowledge","slug":"mcc-kd-multi-cot-consistent-knowledge","title":"MCC-KD: Multi-CoT Consistent Knowledge Distillation","date":"2023-10-23","arxiv_id":"2310.14747","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["homzer/MCC-KD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/distillcse-distilled-contrastive-learning-for","slug":"distillcse-distilled-contrastive-learning-for","title":"DistillCSE: Distilled Contrastive Learning for Sentence Embeddings","date":"2023-10-20","arxiv_id":"2310.13499","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-abstractiveness-of-summarization","title":"Enhancing Abstractiveness of Summarization Models through Calibrated Distillation","date":"2023-10-20","arxiv_id":"2310.13760","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/monoskd-general-distillation-framework-for","slug":"monoskd-general-distillation-framework-for","title":"MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient","date":"2023-10-17","arxiv_id":"2310.11316","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-knowledge-distillation-for","slug":"leveraging-knowledge-distillation-for","title":"Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments","date":"2023-10-16","arxiv_id":"2310.10170","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/dialogue-chain-of-thought-distillation-for","slug":"dialogue-chain-of-thought-distillation-for","title":"Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents","date":"2023-10-13","arxiv_id":"2310.09343","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["kyle8581/dialoguecot"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"distillspec-improving-speculative-decoding","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","date":"2023-10-12","arxiv_id":"2310.08461","n_code_links":0,"syntology":null},{"paper":"/paper/transport-hub-aware-spatial-temporal-adaptive","slug":"transport-hub-aware-spatial-temporal-adaptive","title":"Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow Prediction","date":"2023-10-12","arxiv_id":"2310.08328","n_code_links":1,"syntology":null},{"paper":"/paper/a-discrepancy-aware-framework-for-robust","slug":"a-discrepancy-aware-framework-for-robust","title":"A Discrepancy Aware Framework for Robust Anomaly Detection","date":"2023-10-11","arxiv_id":"2310.07585","n_code_links":1,"syntology":null},{"paper":"/paper/daspeech-directed-acyclic-transformer-for-1","slug":"daspeech-directed-acyclic-transformer-for-1","title":"DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation","date":"2023-10-11","arxiv_id":"2310.07403","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ictnlp/daspeech"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/online-speculative-decoding","slug":"online-speculative-decoding","title":"Online Speculative Decoding","date":"2023-10-11","arxiv_id":"2310.07177","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liuxiaoxuanpku/osd"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/distillation-improves-visual-place","slug":"distillation-improves-visual-place","title":"Distillation Improves Visual Place Recognition for Low Quality Images","date":"2023-10-10","arxiv_id":"2310.06906","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-anomaly-detection","title":"Knowledge Distillation for Anomaly Detection","date":"2023-10-09","arxiv_id":"2310.06047","n_code_links":0,"syntology":null},{"paper":"/paper/applying-knowledge-distillation-to-improve","slug":"applying-knowledge-distillation-to-improve","title":"Applying Knowledge Distillation to Improve Weed Mapping With Drones","date":"2023-10-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/ded-diagnostic-evidence-distillation-for-acne","slug":"ded-diagnostic-evidence-distillation-for-acne","title":"DED: Diagnostic Evidence Distillation for acne severity grading on face images","date":"2023-10-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/luminet-the-bright-side-of-perceptual","slug":"luminet-the-bright-side-of-perceptual","title":"LumiNet: The Bright Side of Perceptual Knowledge Distillation","date":"2023-10-05","arxiv_id":"2310.03669","n_code_links":1,"syntology":null},{"paper":null,"slug":"heterogeneous-federated-learning-using","title":"Heterogeneous Federated Learning Using Knowledge Codistillation","date":"2023-10-04","arxiv_id":"2310.02549","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/sea-sparse-linear-attention-with-estimated","slug":"sea-sparse-linear-attention-with-estimated","title":"SEA: Sparse Linear Attention with Estimated Attention Mask","date":"2023-10-03","arxiv_id":"2310.01777","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gmlwns2000/sea-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/distilling-influences-to-mitigate-prediction","slug":"distilling-influences-to-mitigate-prediction","title":"Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks","date":"2023-10-02","arxiv_id":"2310.00946","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null}],"record_sha256":"a9f9dae8916b1df763f08489f6cf66efd198dfa5ecb1c624355e95020026d75b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}