{"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/129","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":129,"pages_in_order":249,"rows_per_page":100,"rows":[12801,12900],"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/128","next":"/method/multi-head-attention/papers/130","papers":[{"paper":null,"slug":"thrilled-by-your-progress-large-language","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","date":"2023-06-15","arxiv_id":"2306.10073","n_code_links":0,"syntology":null},{"paper":null,"slug":"tighter-prediction-intervals-for-causal","title":"Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding","date":"2023-06-15","arxiv_id":"2306.09520","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-diffusion-classifiers-with-denoising","title":"DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers","date":"2023-06-15","arxiv_id":"2306.09192","n_code_links":0,"syntology":null},{"paper":"/paper/vip-a-differentially-private-foundation-model","slug":"vip-a-differentially-private-foundation-model","title":"ViP: A Differentially Private Foundation Model for Computer Vision","date":"2023-06-15","arxiv_id":"2306.08842","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["facebookresearch/vip-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/a-semantically-enhanced-dual-encoder-for","slug":"a-semantically-enhanced-dual-encoder-for","title":"A semantically enhanced dual encoder for aspect sentiment triplet extraction","date":"2023-06-14","arxiv_id":"2306.08373","n_code_links":1,"syntology":null},{"paper":"/paper/assessing-the-effectiveness-of-gpt-3-in","slug":"assessing-the-effectiveness-of-gpt-3-in","title":"Assessing the Effectiveness of GPT-3 in Detecting False Political Statements: A Case Study on the LIAR Dataset","date":"2023-06-14","arxiv_id":"2306.08190","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-a-corpus-for-biomedical-relation","title":"Building a Corpus for Biomedical Relation Extraction of Species Mentions","date":"2023-06-14","arxiv_id":"2306.08403","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-not-naysayers-an-analysis","slug":"language-models-are-not-naysayers-an-analysis","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","date":"2023-06-14","arxiv_id":"2306.08189","n_code_links":1,"syntology":null},{"paper":null,"slug":"m-2unet-metaformer-multi-scale-upsampling","title":"M^2UNet: MetaFormer Multi-scale Upsampling Network for Polyp Segmentation","date":"2023-06-14","arxiv_id":"2306.08600","n_code_links":0,"syntology":null},{"paper":null,"slug":"mcr-data2vec-2-0-improving-self-supervised","title":"MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization","date":"2023-06-14","arxiv_id":"2306.08463","n_code_links":0,"syntology":null},{"paper":"/paper/muben-benchmarking-the-uncertainty-of-pre","slug":"muben-benchmarking-the-uncertainty-of-pre","title":"MUBen: Benchmarking the Uncertainty of Molecular Representation Models","date":"2023-06-14","arxiv_id":"2306.10060","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"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":["Yinghao-Li/UncertaintyBenchmark","yinghao-li/muben"],"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/multimodal-optimal-transport-based-co","slug":"multimodal-optimal-transport-based-co","title":"Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction","date":"2023-06-14","arxiv_id":"2306.08330","n_code_links":3,"syntology":{"ran":10,"of":18,"n_ran_checked":7,"n_instrument":3,"unverified":8,"pointer_only":18,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["innse/motcat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"research-on-named-entity-recognition-in","title":"Research on Named Entity Recognition in Improved transformer with R-Drop structure","date":"2023-06-14","arxiv_id":"2306.08315","n_code_links":0,"syntology":null},{"paper":"/paper/the-elm-neuron-an-efficient-and-expressive","slug":"the-elm-neuron-an-efficient-and-expressive","title":"The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks","date":"2023-06-14","arxiv_id":"2306.16922","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["AaronSpieler/elmneuron"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-agi-in-computer-vision-lessons","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","date":"2023-06-14","arxiv_id":"2306.08641","n_code_links":0,"syntology":null},{"paper":"/paper/tsmixer-lightweight-mlp-mixer-model-for","slug":"tsmixer-lightweight-mlp-mixer-model-for","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","date":"2023-06-14","arxiv_id":"2306.09364","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibm/tsfm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unraveling-the-arc-puzzle-mimicking-human","title":"Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer","date":"2023-06-14","arxiv_id":"2306.08204","n_code_links":0,"syntology":null},{"paper":"/paper/when-to-use-efficient-self-attention","slug":"when-to-use-efficient-self-attention","title":"When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants","date":"2023-06-14","arxiv_id":"2306.08667","n_code_links":1,"syntology":null},{"paper":"/paper/world-to-words-grounded-open-vocabulary","slug":"world-to-words-grounded-open-vocabulary","title":"World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models","date":"2023-06-14","arxiv_id":"2306.08685","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["sled-group/world-to-words"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/arxiveri-automatic-table-verification-with","slug":"arxiveri-automatic-table-verification-with","title":"arXiVeri: Automatic table verification with GPT","date":"2023-06-13","arxiv_id":"2306.07968","n_code_links":1,"syntology":null},{"paper":"/paper/can-chatgpt-enable-its-the-case-of-mixed","slug":"can-chatgpt-enable-its-the-case-of-mixed","title":"Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning","date":"2023-06-13","arxiv_id":"2306.08094","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using-1","slug":"enhancing-social-network-hate-detection-using-1","title":"Enhancing Social Network Hate Detection Using Back Translation and GPT-3 Augmentations During Training and Test-Time","date":"2023-06-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"flame-few-shot-learning-from-natural-language","title":"FLamE: Few-shot Learning from Natural Language Explanations","date":"2023-06-13","arxiv_id":"2306.08042","n_code_links":0,"syntology":null},{"paper":null,"slug":"gemo-clap-gender-attribute-enhanced","title":"GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition","date":"2023-06-13","arxiv_id":"2306.07848","n_code_links":0,"syntology":null},{"paper":"/paper/h2ogpt-democratizing-large-language-models","slug":"h2ogpt-democratizing-large-language-models","title":"h2oGPT: Democratizing Large Language Models","date":"2023-06-13","arxiv_id":"2306.08161","n_code_links":2,"syntology":null},{"paper":null,"slug":"human-like-intuitive-behavior-and-reasoning","title":"Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models -- and Disappeared in GPT-4","date":"2023-06-13","arxiv_id":"2306.07622","n_code_links":0,"syntology":null},{"paper":"/paper/improving-zero-shot-detection-of-low","slug":"improving-zero-shot-detection-of-low","title":"Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models","date":"2023-06-13","arxiv_id":"2306.08000","n_code_links":1,"syntology":null},{"paper":null,"slug":"molcap-molecular-chemical-reactivity","title":"MolCAP: Molecular Chemical reActivity pretraining and prompted-finetuning enhanced molecular representation learning","date":"2023-06-13","arxiv_id":"2306.09187","n_code_links":0,"syntology":null},{"paper":null,"slug":"monolingual-and-cross-lingual-knowledge","title":"Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification","date":"2023-06-13","arxiv_id":"2306.07797","n_code_links":0,"syntology":null},{"paper":null,"slug":"reviving-shift-equivariance-in-vision","title":"Reviving Shift Equivariance in Vision Transformers","date":"2023-06-13","arxiv_id":"2306.07470","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-learning-made-simple-with-1","slug":"semi-supervised-learning-made-simple-with-1","title":"Semi-supervised learning made simple with self-supervised clustering","date":"2023-06-13","arxiv_id":"2306.07483","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":5,"phrase":"2 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["pietroastolfi/suave-daino"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"vector-quantized-graph-auto-encoder","title":"Discrete Graph Auto-Encoder","date":"2023-06-13","arxiv_id":"2306.07735","n_code_links":0,"syntology":null},{"paper":"/paper/xraygpt-chest-radiographs-summarization-using","slug":"xraygpt-chest-radiographs-summarization-using","title":"XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models","date":"2023-06-13","arxiv_id":"2306.07971","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-of-vision-language-pre-training-from","title":"A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation","date":"2023-06-12","arxiv_id":"2306.07198","n_code_links":0,"syntology":null},{"paper":"/paper/aerialformer-multi-resolution-transformer-for","slug":"aerialformer-multi-resolution-transformer-for","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","date":"2023-06-12","arxiv_id":"2306.06842","n_code_links":1,"syntology":null},{"paper":null,"slug":"cd-ctfm-a-lightweight-cnn-transformer-network","title":"CD-CTFM: A Lightweight CNN-Transformer Network for Remote Sensing Cloud Detection Fusing Multiscale Features","date":"2023-06-12","arxiv_id":"2306.07186","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-covid-19-diagnosis-through-vision","title":"Enhancing COVID-19 Diagnosis through Vision Transformer-Based Analysis of Chest X-ray Images","date":"2023-06-12","arxiv_id":"2306.06914","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-attention-mechanisms-for-multimodal","title":"Exploring Attention Mechanisms for Multimodal Emotion Recognition in an Emergency Call Center Corpus","date":"2023-06-12","arxiv_id":"2306.07115","n_code_links":0,"syntology":null},{"paper":null,"slug":"imbalanced-multi-label-classification-for","title":"Imbalanced Multi-label Classification for Business-related Text with Moderately Large Label Spaces","date":"2023-06-12","arxiv_id":"2306.07046","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-and-non-linguistic","title":"Large language models and (non-)linguistic recursion","date":"2023-06-12","arxiv_id":"2306.07195","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-tax-attorneys-a-case","title":"Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence","date":"2023-06-12","arxiv_id":"2306.07075","n_code_links":0,"syntology":null},{"paper":"/paper/learning-multilingual-sentence","slug":"learning-multilingual-sentence","title":"Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization","date":"2023-06-12","arxiv_id":"2306.06919","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-mask-and-permute-visual-tokens","slug":"learning-to-mask-and-permute-visual-tokens","title":"Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training","date":"2023-06-12","arxiv_id":"2306.07346","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-skill-to-skill-supervision-for","title":"Leveraging Skill-to-Skill Supervision for Knowledge Tracing","date":"2023-06-12","arxiv_id":"2306.06841","n_code_links":0,"syntology":null},{"paper":"/paper/linear-classifier-an-often-forgotten-baseline","slug":"linear-classifier-an-often-forgotten-baseline","title":"Linear Classifier: An Often-Forgotten Baseline for Text Classification","date":"2023-06-12","arxiv_id":"2306.07111","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jameslyc88/text_classification_baseline_code"],"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":"lost-in-translation-large-language-models-in","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","date":"2023-06-12","arxiv_id":"2306.07377","n_code_links":0,"syntology":null},{"paper":"/paper/maskedfusion360-reconstruct-lidar-data-by","slug":"maskedfusion360-reconstruct-lidar-data-by","title":"MaskedFusion360: Reconstruct LiDAR Data by Querying Camera Features","date":"2023-06-12","arxiv_id":"2306.07087","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-transformer-overconfidence-via","slug":"mitigating-transformer-overconfidence-via","title":"Mitigating Transformer Overconfidence via Lipschitz Regularization","date":"2023-06-12","arxiv_id":"2306.06849","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-audio-textual-architecture-for-1","title":"Multimodal Audio-textual Architecture for Robust Spoken Language Understanding","date":"2023-06-12","arxiv_id":"2306.06819","n_code_links":0,"syntology":null},{"paper":null,"slug":"network-robustness-learning-via-graph","title":"A Graph Transformer-Driven Approach for Network Robustness Learning","date":"2023-06-12","arxiv_id":"2306.06913","n_code_links":0,"syntology":null},{"paper":null,"slug":"npvforensics-jointing-non-critical-phonemes","title":"NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake Detection","date":"2023-06-12","arxiv_id":"2306.06885","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-n-gram-approximation-of-pre-trained","title":"On the N-gram Approximation of Pre-trained Language Models","date":"2023-06-12","arxiv_id":"2306.06892","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-based-extraction-of-social","title":"Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning","date":"2023-06-12","arxiv_id":"2306.07170","n_code_links":0,"syntology":null},{"paper":"/paper/recursion-of-thought-a-divide-and-conquer","slug":"recursion-of-thought-a-divide-and-conquer","title":"Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models","date":"2023-06-12","arxiv_id":"2306.06891","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-bea-2023-shared-task-on-generating-ai","title":"The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues","date":"2023-06-12","arxiv_id":"2306.06941","n_code_links":0,"syntology":null},{"paper":"/paper/unipoll-a-unified-social-media-poll","slug":"unipoll-a-unified-social-media-poll","title":"UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization","date":"2023-06-12","arxiv_id":"2306.06851","n_code_links":1,"syntology":null},{"paper":"/paper/waffling-around-for-performance-visual","slug":"waffling-around-for-performance-visual","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","date":"2023-06-12","arxiv_id":"2306.07282","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":1,"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":["explainableml/waffleclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/attention-compilation-and-solver-based","slug":"attention-compilation-and-solver-based","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","date":"2023-06-11","arxiv_id":"2306.06755","n_code_links":1,"syntology":null},{"paper":"/paper/e-2-equivariant-vision-transformer","slug":"e-2-equivariant-vision-transformer","title":"$E(2)$-Equivariant Vision Transformer","date":"2023-06-11","arxiv_id":"2306.06722","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":["zjucdsyangkaifan/gevit"],"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/easyguide-esg-issue-identification-framework","slug":"easyguide-esg-issue-identification-framework","title":"EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models","date":"2023-06-11","arxiv_id":"2306.06662","n_code_links":1,"syntology":null},{"paper":"/paper/inductive-reasoning-in-humans-and-large","slug":"inductive-reasoning-in-humans-and-large","title":"Inductive reasoning in humans and large language models","date":"2023-06-11","arxiv_id":"2306.06548","n_code_links":1,"syntology":null},{"paper":"/paper/local-to-global-perspectives-on-graph-neural","slug":"local-to-global-perspectives-on-graph-neural","title":"Local-to-global Perspectives on Graph Neural Networks","date":"2023-06-11","arxiv_id":"2306.06547","n_code_links":1,"syntology":null},{"paper":null,"slug":"robertweet-a-bert-language-model-for-romanian","title":"RoBERTweet: A BERT Language Model for Romanian Tweets","date":"2023-06-11","arxiv_id":"2306.06598","n_code_links":0,"syntology":null},{"paper":"/paper/vpuformer-visual-prompt-unified-transformer","slug":"vpuformer-visual-prompt-unified-transformer","title":"PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation","date":"2023-06-11","arxiv_id":"2306.06656","n_code_links":2,"syntology":null},{"paper":null,"slug":"enhancing-low-resource-ner-using-assisting","title":"Enhancing Low Resource NER Using Assisting Language And Transfer Learning","date":"2023-06-10","arxiv_id":"2306.06477","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-data-augmentation-via-chatgpt-a-case","title":"Medical Data Augmentation via ChatGPT: A Case Study on Medication Identification and Medication Event Classification","date":"2023-06-10","arxiv_id":"2306.07297","n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-pre-training-for-medical-vision","slug":"multi-modal-pre-training-for-medical-vision","title":"Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark","date":"2023-06-10","arxiv_id":"2306.06494","n_code_links":1,"syntology":null},{"paper":null,"slug":"shuffled-autoregression-for-motion","title":"Shuffled Autoregression For Motion Interpolation","date":"2023-06-10","arxiv_id":"2306.06367","n_code_links":0,"syntology":null},{"paper":null,"slug":"vista-morph-unsupervised-image-registration","title":"Vista-Morph: Unsupervised Image Registration of Visible-Thermal Facial Pairs","date":"2023-06-10","arxiv_id":"2306.06505","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-can-an-accent-identifier-learn-probing","title":"What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model","date":"2023-06-10","arxiv_id":"2306.06524","n_code_links":0,"syntology":null},{"paper":"/paper/14-examples-of-how-llms-can-transform","slug":"14-examples-of-how-llms-can-transform","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","date":"2023-06-09","arxiv_id":"2306.06283","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 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","official":{"repos":["qai222/llm_organic_synthesis","doncamilom/bollama"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-dual-source-attention-transformer-for-multi","title":"A Gated Attention Transformer for Multi-Person Pose Tracking","date":"2023-06-09","arxiv_id":"2306.05807","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-generative-approach-to-product","title":"A Unified Generative Approach to Product Attribute-Value Identification","date":"2023-06-09","arxiv_id":"2306.05605","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-fast-and-high-quality-speech","title":"Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion","date":"2023-06-09","arxiv_id":"2306.05708","n_code_links":0,"syntology":null},{"paper":null,"slug":"cover-a-heuristic-greedy-adversarial-attack","title":"COVER: A Heuristic Greedy Adversarial Attack on Prompt-based Learning in Language Models","date":"2023-06-09","arxiv_id":"2306.05659","n_code_links":0,"syntology":null},{"paper":null,"slug":"customizing-general-purpose-foundation-models","title":"Customizing General-Purpose Foundation Models for Medical Report Generation","date":"2023-06-09","arxiv_id":"2306.05642","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-neural-network-compression-via","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","date":"2023-06-09","arxiv_id":"2306.05785","n_code_links":0,"syntology":null},{"paper":"/paper/everybody-compose-deep-beats-to-music","slug":"everybody-compose-deep-beats-to-music","title":"Everybody Compose: Deep Beats To Music","date":"2023-06-09","arxiv_id":"2306.06284","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-responses-of-large-language","title":"Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests","date":"2023-06-09","arxiv_id":"2306.05715","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-calls-enhancing-call-segmentation-and","title":"GPT-Calls: Enhancing Call Segmentation and Tagging by Generating Synthetic Conversations via Large Language Models","date":"2023-06-09","arxiv_id":"2306.07941","n_code_links":0,"syntology":null},{"paper":"/paper/illumination-controllable-dehazing-network","slug":"illumination-controllable-dehazing-network","title":"Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding","date":"2023-06-09","arxiv_id":"2306.05675","n_code_links":1,"syntology":null},{"paper":null,"slug":"implementing-bert-and-fine-tuned-roberta-to","title":"Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT","date":"2023-06-09","arxiv_id":"2306.07401","n_code_links":0,"syntology":null},{"paper":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1","slug":"judging-llm-as-a-judge-with-mt-bench-and-1","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","date":"2023-06-09","arxiv_id":"2306.05685","n_code_links":11,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lm-sys/fastchat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/language-models-can-learn-exceptions-to","slug":"language-models-can-learn-exceptions-to","title":"Language Models Can Learn Exceptions to Syntactic Rules","date":"2023-06-09","arxiv_id":"2306.05969","n_code_links":1,"syntology":null},{"paper":null,"slug":"lightweight-monocular-depth-estimation-via","title":"Lightweight Monocular Depth Estimation via Token-Sharing Transformer","date":"2023-06-09","arxiv_id":"2306.05682","n_code_links":0,"syntology":null},{"paper":"/paper/modet-learning-deformable-image-registration","slug":"modet-learning-deformable-image-registration","title":"ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer","date":"2023-06-09","arxiv_id":"2306.05688","n_code_links":1,"syntology":null},{"paper":"/paper/morphosyntactic-probing-of-multilingual-bert","slug":"morphosyntactic-probing-of-multilingual-bert","title":"Morphosyntactic probing of multilingual BERT models","date":"2023-06-09","arxiv_id":"2306.06205","n_code_links":1,"syntology":null},{"paper":"/paper/poet-a-generative-model-of-protein-families","slug":"poet-a-generative-model-of-protein-families","title":"PoET: A generative model of protein families as sequences-of-sequences","date":"2023-06-09","arxiv_id":"2306.06156","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["OpenProteinAI/PoET"],"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":"/paper/prodigy-an-expeditiously-adaptive-parameter","slug":"prodigy-an-expeditiously-adaptive-parameter","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","date":"2023-06-09","arxiv_id":"2306.06101","n_code_links":1,"syntology":null},{"paper":"/paper/rankformer-listwise-learning-to-rank-using","slug":"rankformer-listwise-learning-to-rank-using","title":"RankFormer: Listwise Learning-to-Rank Using Listwide Labels","date":"2023-06-09","arxiv_id":"2306.05808","n_code_links":1,"syntology":null},{"paper":"/paper/reconstructing-human-expressiveness-in-piano","slug":"reconstructing-human-expressiveness-in-piano","title":"Reconstructing Human Expressiveness in Piano Performances with a Transformer Network","date":"2023-06-09","arxiv_id":"2306.06040","n_code_links":1,"syntology":null},{"paper":"/paper/reliability-check-an-analysis-of-gpt-3-s","slug":"reliability-check-an-analysis-of-gpt-3-s","title":"Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording","date":"2023-06-09","arxiv_id":"2306.06199","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-telecom-language-through-large","title":"Understanding Telecom Language Through Large Language Models","date":"2023-06-09","arxiv_id":"2306.07933","n_code_links":0,"syntology":null},{"paper":null,"slug":"virtual-node-tuning-for-few-shot-node","title":"Virtual Node Tuning for Few-shot Node Classification","date":"2023-06-09","arxiv_id":"2306.06063","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-hessians-with-inter-layer","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","date":"2023-06-08","arxiv_id":"2306.04879","n_code_links":0,"syntology":null},{"paper":"/paper/bias-against-93-stigmatized-groups-in-masked","slug":"bias-against-93-stigmatized-groups-in-masked","title":"Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks","date":"2023-06-08","arxiv_id":"2306.05550","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["mooniem/mlms_bias_stigmas"],"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":"city-wide-origin-destination-matrix","title":"Complexity-aware Large Scale Origin-Destination Network Generation via Diffusion Model","date":"2023-06-08","arxiv_id":"2306.04873","n_code_links":0,"syntology":null},{"paper":null,"slug":"connectional-style-guided-contextual","title":"Connectional-Style-Guided Contextual Representation Learning for Brain Disease Diagnosis","date":"2023-06-08","arxiv_id":"2306.05297","n_code_links":0,"syntology":null},{"paper":"/paper/daccord-un-jeu-de-donnees-pour-la-detection","slug":"daccord-un-jeu-de-donnees-pour-la-detection","title":"DACCORD : un jeu de données pour la Détection Automatique d'énonCés COntRaDictoires en français","date":"2023-06-08","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"deep-learning-method-for-object-tracking","title":"Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time","date":"2023-06-08","arxiv_id":"2306.06126","n_code_links":0,"syntology":null}],"record_sha256":"6643510a5721010b27fed633408e9668fd3bd14a825bf6307ce05db732118ae8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}