{"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/32","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":32,"pages_in_order":43,"rows_per_page":100,"rows":[3101,3200],"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/31","next":"/task/knowledge-distillation/papers/33","papers":[{"url":null,"slug":"smoc-net-leveraging-camera-pose-for-self","title":"SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tiny-updater-towards-efficient-neural-network","title":"Tiny Updater: Towards Efficient Neural Network-Driven Software Updating","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"triple-revisiting-pretrained-model-reuse-and","title":"TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unikd-universal-knowledge-distillation-for","title":"UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/x3kd-knowledge-distillation-across-modalities","slug":"x3kd-knowledge-distillation-across-modalities","title":"X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"you-do-not-need-additional-priors-or","title":"You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bd-kd-balancing-the-divergences-for-online","title":"BD-KD: Balancing the Divergences for Online Knowledge Distillation","date":"2022-12-25","arxiv_id":"2212.12965","repositories_listed":0,"syntology":null},{"url":null,"slug":"camembert-cascading-assistant-mediated","title":"CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT","date":"2022-12-22","arxiv_id":"2212.11456","repositories_listed":0,"syntology":null},{"url":null,"slug":"adam-dense-retrieval-distillation-with","title":"Adam: Dense Retrieval Distillation with Adaptive Dark Examples","date":"2022-12-20","arxiv_id":"2212.10192","repositories_listed":0,"syntology":null},{"url":null,"slug":"diff-glat-diffusion-glancing-transformer-for","title":"Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning","date":"2022-12-20","arxiv_id":"2212.10240","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-distillation-for-long-document","title":"Fine-Grained Distillation for Long Document Retrieval","date":"2022-12-20","arxiv_id":"2212.10423","repositories_listed":0,"syntology":null},{"url":null,"slug":"i2d2-inductive-knowledge-distillation-with","title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation","date":"2022-12-19","arxiv_id":"2212.09246","repositories_listed":0,"syntology":null},{"url":null,"slug":"knife-knowledge-distillation-with-free-text","title":"KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales","date":"2022-12-19","arxiv_id":"2212.09721","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-knowledge-distillation-from-crowd","title":"Multi-View Knowledge Distillation from Crowd Annotations for Out-of-Domain Generalization","date":"2022-12-19","arxiv_id":"2212.09409","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-point-cloud-pre-training-with-knowledge","title":"3D Point Cloud Pre-training with Knowledge Distillation from 2D Images","date":"2022-12-17","arxiv_id":"2212.08974","repositories_listed":0,"syntology":null},{"url":null,"slug":"swing-distillation-a-privacy-preserving","title":"Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework","date":"2022-12-16","arxiv_id":"2212.08349","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-small-language-models-to-reason","title":"Teaching Small Language Models to Reason","date":"2022-12-16","arxiv_id":"2212.08410","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-paradigm-based-brain-computer","title":"Hybrid Paradigm-based Brain-Computer Interface for Robotic Arm Control","date":"2022-12-14","arxiv_id":"2212.08122","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-for-dense-retrieval-through","title":"Domain Adaptation for Dense Retrieval through Self-Supervision by Pseudo-Relevance Labeling","date":"2022-12-13","arxiv_id":"2212.06552","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuation-kd-improved-knowledge","title":"Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization","date":"2022-12-12","arxiv_id":"2212.05998","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-generalization-of-pre-trained","title":"Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging","date":"2022-12-12","arxiv_id":"2212.05956","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmnet-multi-modal-fusion-with-mutual-learning","title":"Multimodal Matching-aware Co-attention Networks with Mutual Knowledge Distillation for Fake News Detection","date":"2022-12-12","arxiv_id":"2212.05699","repositories_listed":0,"syntology":null},{"url":null,"slug":"siamese-sleep-transformer-for-robust-sleep","title":"Siamese Sleep Transformer For Robust Sleep Stage Scoring With Self-knowledge Distillation and Selective Batch Sampling","date":"2022-12-12","arxiv_id":"2212.13919","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-what-you-should-learn","title":"Teaching What You Should Teach: A Data-Based Distillation Method","date":"2022-12-11","arxiv_id":"2212.05422","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-adversarial-faster-rcnn-with-paradigm","title":"Multi-adversarial Faster-RCNN with Paradigm Teacher for Unrestricted Object Detection","date":"2022-12-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complete-to-partial-4d-distillation-for-self","title":"Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning","date":"2022-12-10","arxiv_id":"2212.05330","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-applied-to-optical","title":"Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection","date":"2022-12-08","arxiv_id":"2212.04569","repositories_listed":0,"syntology":null},{"url":null,"slug":"occlusion-robust-fau-recognition-by-mining","title":"Occlusion-Robust FAU Recognition by Mining Latent Space of Masked Autoencoders","date":"2022-12-08","arxiv_id":"2212.04029","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-different-learning-styles-for","title":"Leveraging Different Learning Styles for Improved Knowledge Distillation in Biomedical Imaging","date":"2022-12-06","arxiv_id":"2212.02931","repositories_listed":0,"syntology":null},{"url":null,"slug":"life-long-learning-for-multilingual-neural","title":"Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation","date":"2022-12-06","arxiv_id":"2212.02800","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-world-detr-transformer-based-open-world","title":"Open World DETR: Transformer based Open World Object Detection","date":"2022-12-06","arxiv_id":"2212.02969","repositories_listed":0,"syntology":null},{"url":null,"slug":"da-cil-towards-domain-adaptive-class","title":"DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection","date":"2022-12-05","arxiv_id":"2212.02057","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-image-calibration-using-knowledge","title":"Single image calibration using knowledge distillation approaches","date":"2022-12-05","arxiv_id":"2212.02379","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-royalflush-system-for-the-wmt-2022","title":"The RoyalFlush System for the WMT 2022 Efficiency Task","date":"2022-12-03","arxiv_id":"2212.01543","repositories_listed":0,"syntology":null},{"url":null,"slug":"injecting-spatial-information-for-monaural","title":"Injecting Spatial Information for Monaural Speech Enhancement via Knowledge Distillation","date":"2022-12-02","arxiv_id":"2212.01012","repositories_listed":0,"syntology":null},{"url":null,"slug":"structvpr-distill-structural-knowledge-with","title":"StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition","date":"2022-12-02","arxiv_id":"2212.00937","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-depth-distillation-with-3d","title":"Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection","date":"2022-11-30","arxiv_id":"2211.16779","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordinating-cross-modal-distillation-for","title":"Coordinating Cross-modal Distillation for Molecular Property Prediction","date":"2022-11-30","arxiv_id":"2211.16712","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-knowledge-transfer-for-weakly","title":"Explicit Knowledge Transfer for Weakly-Supervised Code Generation","date":"2022-11-30","arxiv_id":"2211.16740","repositories_listed":0,"syntology":null},{"url":null,"slug":"heat-hardware-efficient-automatic-tensor","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","date":"2022-11-30","arxiv_id":"2211.16749","repositories_listed":0,"syntology":null},{"url":null,"slug":"hint-dynamic-knowledge-distillation","title":"Hint-dynamic Knowledge Distillation","date":"2022-11-30","arxiv_id":"2211.17059","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-copolymer-inverse-design-system","title":"Random Copolymer inverse design system orienting on Accurate discovering of Antimicrobial peptide-mimetic copolymers","date":"2022-11-30","arxiv_id":"2212.00023","repositories_listed":0,"syntology":null},{"url":"/paper/feature-based-adaptive-contrastive","slug":"feature-based-adaptive-contrastive","title":"Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution","date":"2022-11-29","arxiv_id":"2211.15951","repositories_listed":0,"syntology":null},{"url":null,"slug":"bjtu-wechat-s-systems-for-the-wmt22-chat","title":"BJTU-WeChat's Systems for the WMT22 Chat Translation Task","date":"2022-11-28","arxiv_id":"2211.15009","repositories_listed":0,"syntology":null},{"url":null,"slug":"inter-kd-intermediate-knowledge-distillation","title":"Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition","date":"2022-11-28","arxiv_id":"2211.15075","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-aware-information-for-logit-based","title":"Class-aware Information for Logit-based Knowledge Distillation","date":"2022-11-27","arxiv_id":"2211.14773","repositories_listed":0,"syntology":null},{"url":null,"slug":"epik-eliminating-multi-model-pipelines-with","title":"EPIK: Eliminating multi-model Pipelines with Knowledge-distillation","date":"2022-11-27","arxiv_id":"2211.14920","repositories_listed":0,"syntology":null},{"url":null,"slug":"skdbert-compressing-bert-via-stochastic","title":"SKDBERT: Compressing BERT via Stochastic Knowledge Distillation","date":"2022-11-26","arxiv_id":"2211.14466","repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-knowledge-distillation-for-object","title":"Structural Knowledge Distillation for Object Detection","date":"2022-11-23","arxiv_id":"2211.13133","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-kd-adversarial-learning-and-implicit","title":"AI-KD: Adversarial learning and Implicit regularization for self-Knowledge Distillation","date":"2022-11-20","arxiv_id":"2211.10938","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-collaborative-learning-via","title":"Scalable Collaborative Learning via Representation Sharing","date":"2022-11-20","arxiv_id":"2211.10943","repositories_listed":0,"syntology":null},{"url":null,"slug":"dasecount-domain-agnostic-sample-efficient","title":"DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-shot Learning","date":"2022-11-18","arxiv_id":"2211.10040","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-3-etr-decoder-distillation-for-detection","title":"D$^3$ETR: Decoder Distillation for Detection Transformer","date":"2022-11-17","arxiv_id":"2211.09768","repositories_listed":0,"syntology":null},{"url":null,"slug":"detrdistill-a-universal-knowledge","title":"DETRDistill: A Universal Knowledge Distillation Framework for DETR-families","date":"2022-11-17","arxiv_id":"2211.10156","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-fast-and-accurate","title":"Knowledge distillation for fast and accurate DNA sequence correction","date":"2022-11-17","arxiv_id":"2211.09862","repositories_listed":0,"syntology":null},{"url":null,"slug":"sub-graph-learning-for-spatiotemporal","title":"Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge Distillation","date":"2022-11-17","arxiv_id":"2211.09740","repositories_listed":0,"syntology":null},{"url":null,"slug":"yield-evaluation-of-citrus-fruits-based-on","title":"Yield Evaluation of Citrus Fruits based on the YoloV5 compressed by Knowledge Distillation","date":"2022-11-16","arxiv_id":"2211.08743","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-active-learning-pipeline-for","title":"An Efficient Active Learning Pipeline for Legal Text Classification","date":"2022-11-15","arxiv_id":"2211.08112","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-aware-model-ensemble-with","title":"Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation","date":"2022-11-15","arxiv_id":"2211.08106","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-interpretable-neuron-embedding-for-static","title":"An Interpretable Neuron Embedding for Static Knowledge Distillation","date":"2022-11-14","arxiv_id":"2211.07647","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-correlation-guided-knowledge-transfer","title":"Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning","date":"2022-11-14","arxiv_id":"2211.07364","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-knowledge-distillation-towards","title":"Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection","date":"2022-11-14","arxiv_id":"2211.08398","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-range-zero-shot-generative-deep-network","title":"Long-Range Zero-Shot Generative Deep Network Quantization","date":"2022-11-13","arxiv_id":"2211.06816","repositories_listed":0,"syntology":null},{"url":null,"slug":"fan-trans-online-knowledge-distillation-for","title":"FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection","date":"2022-11-11","arxiv_id":"2211.06143","repositories_listed":0,"syntology":null},{"url":null,"slug":"pile-pairwise-iterative-logits-ensemble-for","title":"PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation","date":"2022-11-11","arxiv_id":"2211.06059","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-federated-learning","title":"Knowledge Distillation for Federated Learning: a Practical Guide","date":"2022-11-09","arxiv_id":"2211.04742","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-fairness-and-environmental","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","date":"2022-11-08","arxiv_id":"2211.04256","repositories_listed":0,"syntology":null},{"url":null,"slug":"closing-the-gap-between-client-and-global","title":"Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning","date":"2022-11-07","arxiv_id":"2211.03457","repositories_listed":0,"syntology":null},{"url":null,"slug":"peak-first-ctc-reducing-the-peak-latency-of","title":"Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization","date":"2022-11-07","arxiv_id":"2211.03284","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-trade-off-in-personalized-speech","title":"Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation","date":"2022-11-05","arxiv_id":"2211.02944","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightvessel-exploring-lightweight-coronary","title":"LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation","date":"2022-11-02","arxiv_id":"2211.00899","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-distillation-of-semantic","title":"Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model","date":"2022-11-02","arxiv_id":"2211.01200","repositories_listed":0,"syntology":null},{"url":null,"slug":"ardir-improving-robustness-using-knowledge","title":"ARDIR: Improving Robustness using Knowledge Distillation of Internal Representation","date":"2022-11-01","arxiv_id":"2211.00239","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-chinese-multi-label-text","title":"Enhancing Chinese Multi-Label Text Classification Performance with Response-based Knowledge Distillation","date":"2022-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-sound-event-detection-model-with","title":"Lightweight Sound Event Detection Model with RepVGG Architecture","date":"2022-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-likelihood-distillation-for-robust","title":"Maximum Likelihood Distillation for Robust Modulation Classification","date":"2022-11-01","arxiv_id":"2211.00748","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-negative-text-replay-for-continual","title":"Generative Negative Text Replay for Continual Vision-Language Pretraining","date":"2022-10-31","arxiv_id":"2210.17322","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-neural-network-with-knowledge","title":"Lightweight Neural Network with Knowledge Distillation for CSI Feedback","date":"2022-10-31","arxiv_id":"2210.17113","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-knowledge-distillation-to","title":"Application of Knowledge Distillation to Multi-task Speech Representation Learning","date":"2022-10-29","arxiv_id":"2210.16611","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-current-explainability-help-provide","title":"Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes?","date":"2022-10-28","arxiv_id":"2210.15882","repositories_listed":0,"syntology":null},{"url":null,"slug":"completely-heterogeneous-federated-learning","title":"Completely Heterogeneous Federated Learning","date":"2022-10-28","arxiv_id":"2210.15865","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-uformer-semi-supervised-uncertainty","title":"Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing","date":"2022-10-28","arxiv_id":"2210.16057","repositories_listed":0,"syntology":null},{"url":null,"slug":"teacher-student-architecture-for-knowledge","title":"Teacher-Student Architecture for Knowledge Learning: A Survey","date":"2022-10-28","arxiv_id":"2210.17332","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-multi-teacher-knowledge","title":"Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks","date":"2022-10-27","arxiv_id":"2210.16103","repositories_listed":0,"syntology":null},{"url":null,"slug":"li3detr-a-lidar-based-3d-detection","title":"Li3DeTr: A LiDAR based 3D Detection Transformer","date":"2022-10-27","arxiv_id":"2210.15365","repositories_listed":0,"syntology":null},{"url":null,"slug":"quill-query-intent-with-large-language-models","title":"QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation","date":"2022-10-27","arxiv_id":"2210.15718","repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-averaging-a-simple-yet-effective","title":"Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition","date":"2022-10-27","arxiv_id":"2210.15282","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-tailed-food-classification","title":"Long-tailed Food Classification","date":"2022-10-26","arxiv_id":"2210.14748","repositories_listed":0,"syntology":null},{"url":"/paper/an-effective-deep-network-for-head-pose","slug":"an-effective-deep-network-for-head-pose","title":"An Effective Deep Network for Head Pose Estimation without Keypoints","date":"2022-10-25","arxiv_id":"2210.13705","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-cross-layer-knowledge-distillation-on","title":"Online Cross-Layer Knowledge Distillation on Graph Neural Networks with Deep Supervision","date":"2022-10-25","arxiv_id":"2210.13743","repositories_listed":0,"syntology":null},{"url":null,"slug":"referee-reference-free-sentence-summarization","title":"Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation","date":"2022-10-25","arxiv_id":"2210.13800","repositories_listed":0,"syntology":null},{"url":null,"slug":"legal-tech-open-diaries-lesson-learned-on-how","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","date":"2022-10-24","arxiv_id":"2210.13086","repositories_listed":0,"syntology":null},{"url":null,"slug":"respecting-transfer-gap-in-knowledge","title":"Respecting Transfer Gap in Knowledge Distillation","date":"2022-10-23","arxiv_id":"2210.12787","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-label-smoothing-with-self-knowledge-1","title":"Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation","date":"2022-10-22","arxiv_id":"2210.13459","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-gate-knowledge-distillation-leverage","title":"Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model","date":"2022-10-22","arxiv_id":"2210.12427","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-efficiency-trade-offs-in-adapting","title":"Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks","date":"2022-10-21","arxiv_id":"2210.12022","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-object-detection-based-on","title":"Semi-supervised object detection based on single-stage detector for thighbone fracture localization","date":"2022-10-20","arxiv_id":"2210.10998","repositories_listed":0,"syntology":null},{"url":null,"slug":"similarity-of-neural-architectures-based-on","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","date":"2022-10-20","arxiv_id":"2210.11407","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-multiple-specialty-learners-for","title":"Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge Distillation","date":"2022-10-20","arxiv_id":"2210.11094","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-baseline-revisited-pushing-the-limits-of","title":"A baseline revisited: Pushing the limits of multi-segment models for context-aware translation","date":"2022-10-19","arxiv_id":"2210.10906","repositories_listed":0,"syntology":null}],"record_sha256":"3e09a09e068f071658cf49163b14bf81050bd3c790542e12c0cc3fb38b03ff46","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}