{"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/multi-head-attention/papers/146","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","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":146,"pages_in_order":249,"rows_per_page":100,"rows":[14501,14600],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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/multi-head-attention","prev":"/method/multi-head-attention/papers/145","next":"/method/multi-head-attention/papers/147","papers":[{"paper":"/paper/a-convolutional-vision-transformer-for","slug":"a-convolutional-vision-transformer-for","title":"A Convolutional Vision Transformer for Semantic Segmentation of Side-Scan Sonar Data","date":"2023-02-24","arxiv_id":"2302.12416","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-neural-network-based-reverse-radio","title":"A Deep Neural Network Based Reverse Radio Spectrogram Search Algorithm","date":"2023-02-24","arxiv_id":"2302.13854","n_code_links":0,"syntology":null},{"paper":"/paper/hulat-at-semeval-2023-task-10-data","slug":"hulat-at-semeval-2023-task-10-data","title":"HULAT at SemEval-2023 Task 10: Data augmentation for pre-trained transformers applied to the detection of sexism in social media","date":"2023-02-24","arxiv_id":"2302.12840","n_code_links":1,"syntology":null},{"paper":"/paper/mux-plms-pre-training-language-models-with","slug":"mux-plms-pre-training-language-models-with","title":"MUX-PLMs: Data Multiplexing for High-throughput Language Models","date":"2023-02-24","arxiv_id":"2302.12441","n_code_links":1,"syntology":null},{"paper":"/paper/retrieved-sequence-augmentation-for-protein","slug":"retrieved-sequence-augmentation-for-protein","title":"Retrieved Sequence Augmentation for Protein Representation Learning","date":"2023-02-24","arxiv_id":"2302.12563","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hkunlp/rsa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"spanish-built-factual-freectianary-spanish","title":"Spanish Built Factual Freectianary (Spanish-BFF): the first AI-generated free dictionary","date":"2023-02-24","arxiv_id":"2302.12746","n_code_links":0,"syntology":null},{"paper":"/paper/trafformer-a-transformer-model-for-prediction","slug":"trafformer-a-transformer-model-for-prediction","title":"TrafFormer: A Transformer Model for Predicting Long-term Traffic","date":"2023-02-24","arxiv_id":"2302.12388","n_code_links":1,"syntology":null},{"paper":"/paper/window-transformer-for-dialogue-document-a","slug":"window-transformer-for-dialogue-document-a","title":"Window transformer for dialogue document: a joint framework for causal emotion entailment","date":"2023-02-24","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/does-deep-learning-learn-to-abstract-a","slug":"does-deep-learning-learn-to-abstract-a","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","date":"2023-02-23","arxiv_id":"2302.11978","n_code_links":1,"syntology":null},{"paper":"/paper/lightcts-a-lightweight-framework-for","slug":"lightcts-a-lightweight-framework-for","title":"LightCTS: A Lightweight Framework for Correlated Time Series Forecasting","date":"2023-02-23","arxiv_id":"2302.11974","n_code_links":1,"syntology":null},{"paper":"/paper/mossformer-pushing-the-performance-limit-of","slug":"mossformer-pushing-the-performance-limit-of","title":"MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions","date":"2023-02-23","arxiv_id":"2302.11824","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["modelscope/ClearerVoice-Studio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-the-generalization-ability-of-retrieval","title":"On the Generalization Ability of Retrieval-Enhanced Transformers","date":"2023-02-23","arxiv_id":"2302.12128","n_code_links":0,"syntology":null},{"paper":null,"slug":"patch-network-for-medical-image-segmentation","title":"Patch Network for medical image Segmentation","date":"2023-02-23","arxiv_id":"2302.11802","n_code_links":0,"syntology":null},{"paper":"/paper/power-time-series-forecasting-by-pretrained","slug":"power-time-series-forecasting-by-pretrained","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","date":"2023-02-23","arxiv_id":"2302.11939","n_code_links":3,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","official":{"repos":["damo-di-ml/one_fits_all"],"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":["listed","official"]}}},{"paper":null,"slug":"studyformer-attention-based-and-dynamic-multi","title":"StudyFormer : Attention-Based and Dynamic Multi View Classifier for X-ray images","date":"2023-02-23","arxiv_id":"2302.11840","n_code_links":0,"syntology":null},{"paper":"/paper/teacher-intervention-improving-convergence-of","slug":"teacher-intervention-improving-convergence-of","title":"Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers","date":"2023-02-23","arxiv_id":"2302.11812","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["marsjacobs/ti-kd-qat"],"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":["unlocated"]}}},{"paper":null,"slug":"testing-ai-performance-on-less-frequent","title":"Testing AI on language comprehension tasks reveals insensitivity to underlying meaning","date":"2023-02-23","arxiv_id":"2302.12313","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-in-single-object-tracking-an","title":"Transformers in Single Object Tracking: An Experimental Survey","date":"2023-02-23","arxiv_id":"2302.11867","n_code_links":0,"syntology":null},{"paper":"/paper/vlsp-2022-evjvqa-challenge-multilingual","slug":"vlsp-2022-evjvqa-challenge-multilingual","title":"EVJVQA Challenge: Multilingual Visual Question Answering","date":"2023-02-23","arxiv_id":"2302.11752","n_code_links":0,"syntology":null},{"paper":"/paper/what-makes-a-language-easy-to-deep-learn","slug":"what-makes-a-language-easy-to-deep-learn","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","date":"2023-02-23","arxiv_id":"2302.12239","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lgalke/easy2deeplearn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/zoedepth-zero-shot-transfer-by-combining","slug":"zoedepth-zero-shot-transfer-by-combining","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","date":"2023-02-23","arxiv_id":"2302.12288","n_code_links":6,"syntology":{"ran":12,"of":16,"n_ran_checked":5,"n_instrument":7,"unverified":4,"pointer_only":10,"phrase":"12 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; 7 where Syntology's instrument failed) · 4 unverified","official":{"repos":["isl-org/ZoeDepth"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/a-residual-dense-vision-transformer-for","slug":"a-residual-dense-vision-transformer-for","title":"A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuning","date":"2023-02-22","arxiv_id":"2302.11184","n_code_links":1,"syntology":null},{"paper":null,"slug":"bb-gcn-a-bi-modal-bridged-graph-convolutional","title":"BB-GCN: A Bi-modal Bridged Graph Convolutional Network for Multi-label Chest X-Ray Recognition","date":"2023-02-22","arxiv_id":"2302.11082","n_code_links":0,"syntology":null},{"paper":"/paper/cross-modal-audio-visual-co-learning-for-text","slug":"cross-modal-audio-visual-co-learning-for-text","title":"Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification","date":"2023-02-22","arxiv_id":"2302.11254","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-active-learning-in-the-presence-of-label","title":"Deep Active Learning in the Presence of Label Noise: A Survey","date":"2023-02-22","arxiv_id":"2302.11075","n_code_links":0,"syntology":null},{"paper":"/paper/hinormer-representation-learning-on","slug":"hinormer-representation-learning-on","title":"HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer","date":"2023-02-22","arxiv_id":"2302.11329","n_code_links":1,"syntology":null},{"paper":"/paper/ks-detr-knowledge-sharing-in-attention","slug":"ks-detr-knowledge-sharing-in-attention","title":"KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer","date":"2023-02-22","arxiv_id":"2302.11208","n_code_links":1,"syntology":null},{"paper":null,"slug":"solution-for-the-epo-codefest-on-green","title":"Solution for the EPO CodeFest on Green Plastics: Hierarchical multi-label classification of patents relating to green plastics using deep learning","date":"2023-02-22","arxiv_id":"2302.13784","n_code_links":0,"syntology":null},{"paper":"/paper/video-swinunet-spatio-temporal-deep-learning","slug":"video-swinunet-spatio-temporal-deep-learning","title":"Video-SwinUNet: Spatio-temporal Deep Learning Framework for VFSS Instance Segmentation","date":"2023-02-22","arxiv_id":"2302.11325","n_code_links":2,"syntology":null},{"paper":null,"slug":"bokeh-rendering-based-on-adaptive-depth","title":"Bokeh Rendering Based on Adaptive Depth Calibration Network","date":"2023-02-21","arxiv_id":"2302.10808","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-jack-of-all-trades-master-of-none","slug":"chatgpt-jack-of-all-trades-master-of-none","title":"ChatGPT: Jack of all trades, master of none","date":"2023-02-21","arxiv_id":"2302.10724","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["clarin-pl/chatgpt-evaluation-01-2023"],"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":"/paper/co-driven-recognition-of-semantic-consistency","slug":"co-driven-recognition-of-semantic-consistency","title":"Co-Driven Recognition of Semantic Consistency via the Fusion of Transformer and HowNet Sememes Knowledge","date":"2023-02-21","arxiv_id":"2302.10570","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-models-and-semi-supervised-learners-1","slug":"diffusion-models-and-semi-supervised-learners-1","title":"Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels","date":"2023-02-21","arxiv_id":"2302.10586","n_code_links":3,"syntology":{"ran":18,"of":22,"n_ran_checked":10,"n_instrument":8,"unverified":4,"pointer_only":9,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ml-gsai/dpt","baofff/U-ViT"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/edgeformers-graph-empowered-transformers-for","slug":"edgeformers-graph-empowered-transformers-for","title":"Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks","date":"2023-02-21","arxiv_id":"2302.11050","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["petergriffinjin/edgeformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/hyena-hierarchy-towards-larger-convolutional","slug":"hyena-hierarchy-towards-larger-convolutional","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","date":"2023-02-21","arxiv_id":"2302.10866","n_code_links":7,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":4,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hazyresearch/safari"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"k-nn-adapter-efficient-domain-adaptation-for","title":"$k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models","date":"2023-02-21","arxiv_id":"2302.10879","n_code_links":0,"syntology":null},{"paper":"/paper/label-information-enhanced-fraud-detection","slug":"label-information-enhanced-fraud-detection","title":"Label Information Enhanced Fraud Detection against Low Homophily in Graphs","date":"2023-02-21","arxiv_id":"2302.10407","n_code_links":1,"syntology":null},{"paper":"/paper/lightweight-real-time-semantic-segmentation","slug":"lightweight-real-time-semantic-segmentation","title":"Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN","date":"2023-02-21","arxiv_id":"2302.10484","n_code_links":1,"syntology":null},{"paper":"/paper/memory-augmented-online-video-anomaly","slug":"memory-augmented-online-video-anomaly","title":"Memory-augmented Online Video Anomaly Detection","date":"2023-02-21","arxiv_id":"2302.10719","n_code_links":1,"syntology":null},{"paper":null,"slug":"mulgt-multi-task-graph-transformer-with-task","title":"MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis","date":"2023-02-21","arxiv_id":"2302.10574","n_code_links":0,"syntology":null},{"paper":"/paper/mvmtnet-a-multi-variate-multi-modal","slug":"mvmtnet-a-multi-variate-multi-modal","title":"MVMTnet: A Multi-variate Multi-modal Transformer for Multi-class Classification of Cardiac Irregularities Using ECG Waveforms and Clinical Notes","date":"2023-02-21","arxiv_id":"2302.11021","n_code_links":1,"syntology":null},{"paper":"/paper/sf2former-amyotrophic-lateral-sclerosis","slug":"sf2former-amyotrophic-lateral-sclerosis","title":"SF2Former: Amyotrophic Lateral Sclerosis Identification From Multi-center MRI Data Using Spatial and Frequency Fusion Transformer","date":"2023-02-21","arxiv_id":"2302.10859","n_code_links":1,"syntology":null},{"paper":null,"slug":"time-to-embrace-natural-language-processing","title":"Time to Embrace Natural Language Processing (NLP)-based Digital Pathology: Benchmarking NLP- and Convolutional Neural Network-based Deep Learning Pipelines","date":"2023-02-21","arxiv_id":"2302.10406","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-classification-reliability-of-nlp","title":"Boosting classification reliability of NLP transformer models in the long run","date":"2023-02-20","arxiv_id":"2302.10016","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-advantages-of-transformers-for","slug":"exploring-the-advantages-of-transformers-for","title":"Exploring the Advantages of Transformers for High-Frequency Trading","date":"2023-02-20","arxiv_id":"2302.13850","n_code_links":1,"syntology":null},{"paper":"/paper/friend-recall-in-online-games-via-pre","slug":"friend-recall-in-online-games-via-pre","title":"Friend Ranking in Online Games via Pre-training Edge Transformers","date":"2023-02-20","arxiv_id":"2302.10043","n_code_links":2,"syntology":null},{"paper":null,"slug":"glocalfuse-depth-fusing-transformers-and-cnns","title":"GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation","date":"2023-02-20","arxiv_id":"2302.09884","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-multi-modal-pre-trained-models-a","slug":"large-scale-multi-modal-pre-trained-models-a","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","date":"2023-02-20","arxiv_id":"2302.10035","n_code_links":1,"syntology":null},{"paper":null,"slug":"optical-transformers","title":"Optical Transformers","date":"2023-02-20","arxiv_id":"2302.10360","n_code_links":0,"syntology":null},{"paper":"/paper/stb-vmm-swin-transformer-based-video-motion","slug":"stb-vmm-swin-transformer-based-video-motion","title":"STB-VMM: Swin Transformer Based Video Motion Magnification","date":"2023-02-20","arxiv_id":"2302.10001","n_code_links":1,"syntology":null},{"paper":"/paper/zero-shot-information-extraction-via-chatting","slug":"zero-shot-information-extraction-via-chatting","title":"ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT","date":"2023-02-20","arxiv_id":"2302.10205","n_code_links":1,"syntology":null},{"paper":"/paper/can-chatgpt-understand-too-a-comparative","slug":"can-chatgpt-understand-too-a-comparative","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","date":"2023-02-19","arxiv_id":"2302.10198","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-effectiveness-of-pre-trained","slug":"evaluating-the-effectiveness-of-pre-trained","title":"Evaluating the Effectiveness of Pre-trained Language Models in Predicting the Helpfulness of Online Product Reviews","date":"2023-02-19","arxiv_id":"2302.10199","n_code_links":1,"syntology":null},{"paper":"/paper/medvit-a-robust-vision-transformer-for","slug":"medvit-a-robust-vision-transformer-for","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","date":"2023-02-19","arxiv_id":"2302.09462","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":["Omid-Nejati/MedViT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mixed-hierarchy-network-for-image-restoration","slug":"mixed-hierarchy-network-for-image-restoration","title":"Mixed Hierarchy Network for Image Restoration","date":"2023-02-19","arxiv_id":"2302.09554","n_code_links":1,"syntology":null},{"paper":"/paper/text-classification-in-the-wild-a-large-scale","slug":"text-classification-in-the-wild-a-large-scale","title":"Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset","date":"2023-02-19","arxiv_id":"2302.09509","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-survey-on-pretrained","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","date":"2023-02-18","arxiv_id":"2302.09419","n_code_links":0,"syntology":null},{"paper":null,"slug":"bag-of-tricks-for-effective-language-model","title":"Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE","date":"2023-02-18","arxiv_id":"2302.09268","n_code_links":0,"syntology":null},{"paper":"/paper/bbt-fin-comprehensive-construction-of-chinese","slug":"bbt-fin-comprehensive-construction-of-chinese","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","date":"2023-02-18","arxiv_id":"2302.09432","n_code_links":2,"syntology":null},{"paper":"/paper/how-good-are-gpt-models-at-machine","slug":"how-good-are-gpt-models-at-machine","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","date":"2023-02-18","arxiv_id":"2302.09210","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/gpt-mt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hyneter-hybrid-network-transformer-for-object","title":"Hyneter: Hybrid Network Transformer for Object Detection","date":"2023-02-18","arxiv_id":"2302.09365","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-attention-memory","title":"Neural Attention Memory","date":"2023-02-18","arxiv_id":"2302.09422","n_code_links":0,"syntology":null},{"paper":null,"slug":"vital-vision-transformer-neural-networks-for","title":"VITAL: Vision Transformer Neural Networks for Accurate Smartphone Heterogeneity Resilient Indoor Localization","date":"2023-02-18","arxiv_id":"2302.09443","n_code_links":0,"syntology":null},{"paper":"/paper/bounding-the-capabilities-of-large-language","slug":"bounding-the-capabilities-of-large-language","title":"Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints","date":"2023-02-17","arxiv_id":"2302.09185","n_code_links":1,"syntology":null},{"paper":"/paper/conveying-the-predicted-future-to-users-a","slug":"conveying-the-predicted-future-to-users-a","title":"Conveying the Predicted Future to Users: A Case Study of Story Plot Prediction","date":"2023-02-17","arxiv_id":"2302.09122","n_code_links":1,"syntology":null},{"paper":"/paper/dtaad-dual-tcn-attention-networks-for-anomaly","slug":"dtaad-dual-tcn-attention-networks-for-anomaly","title":"DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data","date":"2023-02-17","arxiv_id":"2302.10753","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt4mia-utilizing-geneative-pre-trained","title":"GPT4MIA: Utilizing Generative Pre-trained Transformer (GPT-3) as A Plug-and-Play Transductive Model for Medical Image Analysis","date":"2023-02-17","arxiv_id":"2302.08722","n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-language-detection-2","title":"Hate Speech and Offensive Language Detection using an Emotion-aware Shared Encoder","date":"2023-02-17","arxiv_id":"2302.08777","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-transformer-based-networks-with","title":"Improving Transformer-based Networks With Locality For Automatic Speaker Verification","date":"2023-02-17","arxiv_id":"2302.08639","n_code_links":0,"syntology":null},{"paper":"/paper/like-a-good-nearest-neighbor-practical","slug":"like-a-good-nearest-neighbor-practical","title":"Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification","date":"2023-02-17","arxiv_id":"2302.08957","n_code_links":1,"syntology":null},{"paper":null,"slug":"mcae-masked-contrastive-autoencoder-for-face","title":"EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-spoofing","date":"2023-02-17","arxiv_id":"2302.08674","n_code_links":0,"syntology":null},{"paper":"/paper/multiresolution-graph-transformers-and","slug":"multiresolution-graph-transformers-and","title":"Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures","date":"2023-02-17","arxiv_id":"2302.08647","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hysonlab/multires-graph-transformer","vijaydwivedi75/lrgb"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/pac-prediction-sets-for-large-language-models","slug":"pac-prediction-sets-for-large-language-models","title":"PAC Prediction Sets for Large Language Models of Code","date":"2023-02-17","arxiv_id":"2302.08703","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompting-large-language-models-with-the","title":"Prompting Large Language Models With the Socratic Method","date":"2023-02-17","arxiv_id":"2303.08769","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-generative-adversarial-1","title":"Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey","date":"2023-02-17","arxiv_id":"2302.08641","n_code_links":0,"syntology":null},{"paper":null,"slug":"vita-a-vision-transformer-inference","title":"ViTA: A Vision Transformer Inference Accelerator for Edge Applications","date":"2023-02-17","arxiv_id":"2302.09108","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-based-deep-learning-algorithm","title":"A Transformer-based Deep Learning Algorithm to Auto-record Undocumented Clinical One-Lung Ventilation Events","date":"2023-02-16","arxiv_id":"2302.12713","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-flattening-beyond-concatenating","title":"Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation","date":"2023-02-16","arxiv_id":"2302.08079","n_code_links":0,"syntology":null},{"paper":"/paper/efficiency-360-efficient-vision-transformers","slug":"efficiency-360-efficient-vision-transformers","title":"Efficiency 360: Efficient Vision Transformers","date":"2023-02-16","arxiv_id":"2302.08374","n_code_links":1,"syntology":null},{"paper":null,"slug":"foundation-models-for-natural-language","title":"Foundation Models for Natural Language Processing -- Pre-trained Language Models Integrating Media","date":"2023-02-16","arxiv_id":"2302.08575","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-cross-modal-transformer-for-rgb","title":"Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection","date":"2023-02-16","arxiv_id":"2302.08052","n_code_links":0,"syntology":null},{"paper":"/paper/keep-it-neutral-using-natural-language","slug":"keep-it-neutral-using-natural-language","title":"For Generated Text, Is NLI-Neutral Text the Best Text?","date":"2023-02-16","arxiv_id":"2302.08577","n_code_links":1,"syntology":null},{"paper":"/paper/learning-non-local-spatial-angular","slug":"learning-non-local-spatial-angular","title":"Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution","date":"2023-02-16","arxiv_id":"2302.08058","n_code_links":1,"syntology":null},{"paper":"/paper/marich-a-query-efficient-distributionally","slug":"marich-a-query-efficient-distributionally","title":"Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data","date":"2023-02-16","arxiv_id":"2302.08466","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":2,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["debabrota-basu/marich"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"prompt-tuning-of-deep-neural-networks-for","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","date":"2023-02-16","arxiv_id":"2302.08102","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-image-captioning","slug":"retrieval-augmented-image-captioning","title":"Retrieval-augmented Image Captioning","date":"2023-02-16","arxiv_id":"2302.08268","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-human-motion-forecasting-using","title":"Robust Human Motion Forecasting using Transformer-based Model","date":"2023-02-16","arxiv_id":"2302.08274","n_code_links":0,"syntology":null},{"paper":"/paper/search-engine-augmented-dialogue-response","slug":"search-engine-augmented-dialogue-response","title":"Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production","date":"2023-02-16","arxiv_id":"2302.09300","n_code_links":1,"syntology":null},{"paper":null,"slug":"short-term-and-long-term-memory-self","title":"Short-term and long-term memory self-attention network for segmentation of tumours in 3D medical images","date":"2023-02-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speaker-change-detection-for-transformer","title":"Speaker Change Detection for Transformer Transducer ASR","date":"2023-02-16","arxiv_id":"2302.08549","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntactic-structure-processing-in-the-brain","title":"Syntactic Structure Processing in the Brain while Listening","date":"2023-02-16","arxiv_id":"2302.08589","n_code_links":0,"syntology":null},{"paper":null,"slug":"tcgan-semantic-aware-and-structure-preserved","title":"TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation","date":"2023-02-16","arxiv_id":"2302.08047","n_code_links":0,"syntology":null},{"paper":"/paper/urcdc-depth-uncertainty-rectified-cross","slug":"urcdc-depth-uncertainty-rectified-cross","title":"URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation","date":"2023-02-16","arxiv_id":"2302.08149","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":5,"n_instrument":2,"unverified":4,"pointer_only":5,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shuweishao/urcdc-depth"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"commonsense-reasoning-for-conversational-ai-a","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","date":"2023-02-15","arxiv_id":"2302.07926","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-score-based-speaker-adaptation-of","slug":"confidence-score-based-speaker-adaptation-of","title":"Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems","date":"2023-02-15","arxiv_id":"2302.07521","n_code_links":1,"syntology":null},{"paper":"/paper/learning-performance-improving-code-edits","slug":"learning-performance-improving-code-edits","title":"Learning Performance-Improving Code Edits","date":"2023-02-15","arxiv_id":"2302.07867","n_code_links":2,"syntology":{"ran":8,"of":19,"n_ran_checked":3,"n_instrument":5,"unverified":11,"pointer_only":19,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","official":{"repos":["madaan/pie-perf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pose-oriented-transformer-with-uncertainty","title":"Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation","date":"2023-02-15","arxiv_id":"2302.07408","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-learning-for-modeling-gamma","title":"Self-Supervised Learning for Modeling Gamma-ray Variability in Blazars","date":"2023-02-15","arxiv_id":"2302.07700","n_code_links":0,"syntology":null},{"paper":"/paper/speculative-decoding-with-big-little-decoder-1","slug":"speculative-decoding-with-big-little-decoder-1","title":"Speculative Decoding with Big Little Decoder","date":"2023-02-15","arxiv_id":"2302.07863","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["kssteven418/biglittledecoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tformer-a-transmission-friendly-vit-model-for","title":"TFormer: A Transmission-Friendly ViT Model for IoT Devices","date":"2023-02-15","arxiv_id":"2302.07734","n_code_links":0,"syntology":null}],"record_sha256":"f65dcca1f08249e4b19df8f650639a20981ce92ef0e9a1e552064b07a95deb8e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}