{"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/124","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":124,"pages_in_order":249,"rows_per_page":100,"rows":[12301,12400],"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/123","next":"/method/multi-head-attention/papers/125","papers":[{"paper":"/paper/multi-granularity-prediction-with-learnable","slug":"multi-granularity-prediction-with-learnable","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","date":"2023-07-25","arxiv_id":"2307.13244","n_code_links":2,"syntology":null},{"paper":"/paper/predicting-code-coverage-without-execution","slug":"predicting-code-coverage-without-execution","title":"Predicting Code Coverage without Execution","date":"2023-07-25","arxiv_id":"2307.13383","n_code_links":1,"syntology":null},{"paper":null,"slug":"speech-representation-learning-learning","title":"Speech representation learning: Learning bidirectional encoders with single-view, multi-view, and multi-task methods","date":"2023-07-25","arxiv_id":"2308.00129","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-resolving-word-ambiguity-with-word","title":"Towards Resolving Word Ambiguity with Word Embeddings","date":"2023-07-25","arxiv_id":"2307.13417","n_code_links":0,"syntology":null},{"paper":"/paper/watermarking-conditional-text-generation-for","slug":"watermarking-conditional-text-generation-for","title":"Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy","date":"2023-07-25","arxiv_id":"2307.13808","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-sense-disambiguation-as-a-game-of","title":"Word Sense Disambiguation as a Game of Neurosymbolic Darts","date":"2023-07-25","arxiv_id":"2307.16663","n_code_links":0,"syntology":null},{"paper":null,"slug":"xdlm-cross-lingual-diffusion-language-model","title":"XDLM: Cross-lingual Diffusion Language Model for Machine Translation","date":"2023-07-25","arxiv_id":"2307.13560","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-good-student-is-cooperative-and-reliable","title":"A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation","date":"2023-07-24","arxiv_id":"2307.12574","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-machine-learning-model-for","title":"A Hybrid Machine Learning Model for Classifying Gene Mutations in Cancer using LSTM, BiLSTM, CNN, GRU, and GloVe","date":"2023-07-24","arxiv_id":"2307.14361","n_code_links":0,"syntology":null},{"paper":null,"slug":"amae-adaptation-of-pre-trained-masked","title":"AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays","date":"2023-07-24","arxiv_id":"2307.12721","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-isometric-stochastic-optimizer","title":"An Isometric Stochastic Optimizer","date":"2023-07-24","arxiv_id":"2307.12979","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-for-software-security-exploring-the","slug":"chatgpt-for-software-security-exploring-the","title":"How Does Naming Affect LLMs on Code Analysis Tasks?","date":"2023-07-24","arxiv_id":"2307.12488","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-drug-gpt-and-chatgpt","title":"Comparative Analysis of Drug-GPT and ChatGPT LLMs for Healthcare Insights: Evaluating Accuracy and Relevance in Patient and HCP Contexts","date":"2023-07-24","arxiv_id":"2307.16850","n_code_links":0,"syntology":null},{"paper":null,"slug":"dense-transformer-based-enhanced-coding","title":"Dense Transformer based Enhanced Coding Network for Unsupervised Metal Artifact Reduction","date":"2023-07-24","arxiv_id":"2307.12717","n_code_links":0,"syntology":null},{"paper":null,"slug":"entropy-transformer-networks-a-learning","title":"Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold","date":"2023-07-24","arxiv_id":"2307.12517","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-existence-of-secret","title":"Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models","date":"2023-07-24","arxiv_id":"2307.12507","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-attention-all-you-need-in-medical-image","title":"Is attention all you need in medical image analysis? A review","date":"2023-07-24","arxiv_id":"2307.12775","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-of-large-language-models-in-a","title":"Performance of Large Language Models in a Computer Science Degree Program","date":"2023-07-24","arxiv_id":"2308.02432","n_code_links":0,"syntology":null},{"paper":"/paper/swinmm-masked-multi-view-with-swin","slug":"swinmm-masked-multi-view-with-swin","title":"SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation","date":"2023-07-24","arxiv_id":"2307.12591","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ucsc-vlaa/swinmm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-potential-of-llms-for-coding-with-low","title":"The potential of LLMs for coding with low-resource and domain-specific programming languages","date":"2023-07-24","arxiv_id":"2307.13018","n_code_links":0,"syntology":null},{"paper":"/paper/testing-hateful-speeches-against-policies","slug":"testing-hateful-speeches-against-policies","title":"HateModerate: Testing Hate Speech Detectors against Content Moderation Policies","date":"2023-07-23","arxiv_id":"2307.12418","n_code_links":1,"syntology":null},{"paper":"/paper/validation-of-a-zero-shot-learning-natural","slug":"validation-of-a-zero-shot-learning-natural","title":"Validation of a Zero-Shot Learning Natural Language Processing Tool for Data Abstraction from Unstructured Healthcare Data","date":"2023-07-23","arxiv_id":"2308.00107","n_code_links":1,"syntology":null},{"paper":"/paper/identifying-misinformation-on-youtube-through","slug":"identifying-misinformation-on-youtube-through","title":"Identifying Misinformation on YouTube through Transcript Contextual Analysis with Transformer Models","date":"2023-07-22","arxiv_id":"2307.12155","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-effectiveness-of-spectral","slug":"on-the-effectiveness-of-spectral","title":"On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement","date":"2023-07-22","arxiv_id":"2307.12027","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-then-prune-toward-efficient-vision","slug":"sparse-then-prune-toward-efficient-vision","title":"Sparse then Prune: Toward Efficient Vision Transformers","date":"2023-07-22","arxiv_id":"2307.11988","n_code_links":1,"syntology":null},{"paper":null,"slug":"two-stream-multi-level-dynamic-point","title":"Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition","date":"2023-07-22","arxiv_id":"2307.11973","n_code_links":0,"syntology":null},{"paper":null,"slug":"aigc-empowering-telecom-sector-white-paper","title":"AIGC Empowering Telecom Sector White Paper_chinese","date":"2023-07-21","arxiv_id":"2307.11449","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-intelligence-generated-terahertz","title":"Artificial Intelligence-Generated Terahertz Multi-Resonant Metasurfaces via Improved Transformer and CGAN Neural Networks","date":"2023-07-21","arxiv_id":"2307.11794","n_code_links":0,"syntology":null},{"paper":null,"slug":"deftri-a-few-shot-label-fused-contextual-1","title":"DEFTri: A Few-Shot Label Fused Contextual Representation Learning For Product Defect Triage in e-Commerce","date":"2023-07-21","arxiv_id":"2307.11344","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-clip-with-gpt-4-harnessing-visual","slug":"enhancing-clip-with-gpt-4-harnessing-visual","title":"Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts","date":"2023-07-21","arxiv_id":"2307.11661","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":{"repos":["mayug/vdt-adapter"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-your-trained-detrs-with-box","slug":"enhancing-your-trained-detrs-with-box","title":"Enhancing Your Trained DETRs with Box Refinement","date":"2023-07-21","arxiv_id":"2307.11828","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yiqunchen1999/refinebox"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-4-can-t-reason","title":"GPT-4 Can't Reason","date":"2023-07-21","arxiv_id":"2308.03762","n_code_links":0,"syntology":null},{"paper":"/paper/latent-ofer-detect-mask-and-reconstruct-with","slug":"latent-ofer-detect-mask-and-reconstruct-with","title":"Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition","date":"2023-07-21","arxiv_id":"2307.11404","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 2 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":["leeisack/latent-ofer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"predict-ai-bility-of-how-humans-balance-self","title":"Assessing Large Language Models' ability to predict how humans balance self-interest and the interest of others","date":"2023-07-21","arxiv_id":"2307.12776","n_code_links":0,"syntology":null},{"paper":"/paper/statement-based-memory-for-neural-source-code","slug":"statement-based-memory-for-neural-source-code","title":"Statement-based Memory for Neural Source Code Summarization","date":"2023-07-21","arxiv_id":"2307.11709","n_code_links":1,"syntology":null},{"paper":"/paper/the-looming-threat-of-fake-and-llm-generated","slug":"the-looming-threat-of-fake-and-llm-generated","title":"The Looming Threat of Fake and LLM-generated LinkedIn Profiles: Challenges and Opportunities for Detection and Prevention","date":"2023-07-21","arxiv_id":"2307.11864","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-can-a-single-attention-layer-learn-a","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","date":"2023-07-21","arxiv_id":"2307.11353","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-llm-assisted-exploitation-of-ai-guardian","title":"A LLM Assisted Exploitation of AI-Guardian","date":"2023-07-20","arxiv_id":"2307.15008","n_code_links":0,"syntology":null},{"paper":"/paper/a-systematic-evaluation-of-federated-learning","slug":"a-systematic-evaluation-of-federated-learning","title":"An In-Depth Evaluation of Federated Learning on Biomedical Natural Language Processing","date":"2023-07-20","arxiv_id":"2307.11254","n_code_links":2,"syntology":null},{"paper":"/paper/aligndet-aligning-pre-training-and-fine","slug":"aligndet-aligning-pre-training-and-fine","title":"AlignDet: Aligning Pre-training and Fine-tuning in Object Detection","date":"2023-07-20","arxiv_id":"2307.11077","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["liming-ai/AlignDet"],"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":"an-adaptive-dual-level-reinforcement-learning","title":"An Adaptive Dual-level Reinforcement Learning Approach for Optimal Trade Execution","date":"2023-07-20","arxiv_id":"2307.10649","n_code_links":0,"syntology":null},{"paper":"/paper/generative-language-models-on-nucleotide","slug":"generative-language-models-on-nucleotide","title":"Generative Language Models on Nucleotide Sequences of Human Genes","date":"2023-07-20","arxiv_id":"2307.10634","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-feature-embedding-for-automatic","title":"Hybrid Feature Embedding For Automatic Building Outline Extraction","date":"2023-07-20","arxiv_id":"2307.10609","n_code_links":0,"syntology":null},{"paper":null,"slug":"instruction-following-evaluation-through","title":"Instruction-following Evaluation through Verbalizer Manipulation","date":"2023-07-20","arxiv_id":"2307.10558","n_code_links":0,"syntology":null},{"paper":"/paper/ivygpt-interactive-chinese-pathway-language","slug":"ivygpt-interactive-chinese-pathway-language","title":"IvyGPT: InteractiVe Chinese pathwaY language model in medical domain","date":"2023-07-20","arxiv_id":"2307.10512","n_code_links":1,"syntology":null},{"paper":"/paper/l-eval-instituting-standardized-evaluation","slug":"l-eval-instituting-standardized-evaluation","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","date":"2023-07-20","arxiv_id":"2307.11088","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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":["openlmlab/leval"],"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":"layer-wise-representation-fusion-for","title":"Layer-wise Representation Fusion for Compositional Generalization","date":"2023-07-20","arxiv_id":"2307.10799","n_code_links":0,"syntology":null},{"paper":"/paper/llm-cognitive-judgements-differ-from-human","slug":"llm-cognitive-judgements-differ-from-human","title":"LLM Cognitive Judgements Differ From Human","date":"2023-07-20","arxiv_id":"2307.11787","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["sotlampr/llm-cognitive-judgements"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":null,"slug":"mediagpt-a-large-language-model-target","title":"MediaGPT : A Large Language Model For Chinese Media","date":"2023-07-20","arxiv_id":"2307.10930","n_code_links":0,"syntology":null},{"paper":"/paper/msqnet-actor-agnostic-action-recognition-with","slug":"msqnet-actor-agnostic-action-recognition-with","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","date":"2023-07-20","arxiv_id":"2307.10763","n_code_links":1,"syntology":null},{"paper":"/paper/of-models-and-tin-men-a-behavioural-economics","slug":"of-models-and-tin-men-a-behavioural-economics","title":"Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models","date":"2023-07-20","arxiv_id":"2307.11137","n_code_links":2,"syntology":null},{"paper":null,"slug":"pasta-pretrained-action-state-transformer","title":"PASTA: Pretrained Action-State Transformer Agents","date":"2023-07-20","arxiv_id":"2307.10936","n_code_links":0,"syntology":null},{"paper":"/paper/reverse-knowledge-distillation-training-a","slug":"reverse-knowledge-distillation-training-a","title":"Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited Data","date":"2023-07-20","arxiv_id":"2307.10698","n_code_links":1,"syntology":null},{"paper":"/paper/the-role-of-entropy-and-reconstruction-in","slug":"the-role-of-entropy-and-reconstruction-in","title":"The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning","date":"2023-07-20","arxiv_id":"2307.10907","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":["apple/ml-entropy-reconstruction"],"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":"towards-general-game-representations","title":"Towards General Game Representations: Decomposing Games Pixels into Content and Style","date":"2023-07-20","arxiv_id":"2307.11141","n_code_links":0,"syntology":null},{"paper":"/paper/a-step-towards-worldwide-biodiversity","slug":"a-step-towards-worldwide-biodiversity","title":"A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset","date":"2023-07-19","arxiv_id":"2307.10455","n_code_links":2,"syntology":null},{"paper":null,"slug":"dp-tbart-a-transformer-based-autoregressive","title":"DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation","date":"2023-07-19","arxiv_id":"2307.10430","n_code_links":0,"syntology":null},{"paper":"/paper/dvpt-dynamic-visual-prompt-tuning-of-large","slug":"dvpt-dynamic-visual-prompt-tuning-of-large","title":"DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis","date":"2023-07-19","arxiv_id":"2307.09787","n_code_links":1,"syntology":null},{"paper":null,"slug":"embedded-heterogeneous-attention-transformer","title":"Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning","date":"2023-07-19","arxiv_id":"2307.09915","n_code_links":0,"syntology":null},{"paper":"/paper/fingpt-democratizing-internet-scale-data-for","slug":"fingpt-democratizing-internet-scale-data-for","title":"FinGPT: Democratizing Internet-scale Data for Financial Large Language Models","date":"2023-07-19","arxiv_id":"2307.10485","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-mathematical-derivations-with","title":"Controlling Equational Reasoning in Large Language Models with Prompt Interventions","date":"2023-07-19","arxiv_id":"2307.09998","n_code_links":0,"syntology":null},{"paper":null,"slug":"mood-classification-of-bangla-songs-based-on","title":"Mood Classification of Bangla Songs Based on Lyrics","date":"2023-07-19","arxiv_id":"2307.10314","n_code_links":0,"syntology":null},{"paper":null,"slug":"perturbing-a-neural-network-to-infer","title":"Perturbing a Neural Network to Infer Effective Connectivity: Evidence from Synthetic EEG Data","date":"2023-07-19","arxiv_id":"2307.09770","n_code_links":0,"syntology":null},{"paper":null,"slug":"pharmacygpt-the-ai-pharmacist","title":"PharmacyGPT: The AI Pharmacist","date":"2023-07-19","arxiv_id":"2307.10432","n_code_links":0,"syntology":null},{"paper":"/paper/polyffusion-a-diffusion-model-for-polyphonic","slug":"polyffusion-a-diffusion-model-for-polyphonic","title":"Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls","date":"2023-07-19","arxiv_id":"2307.10304","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-acoustic-word-embedding","title":"Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder","date":"2023-07-19","arxiv_id":"2307.09871","n_code_links":0,"syntology":null},{"paper":"/paper/sprint-a-unified-toolkit-for-evaluating-and","slug":"sprint-a-unified-toolkit-for-evaluating-and","title":"SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval","date":"2023-07-19","arxiv_id":"2307.10488","n_code_links":1,"syntology":null},{"paper":"/paper/analyzing-sports-commentary-in-order-to","slug":"analyzing-sports-commentary-in-order-to","title":"Analyzing sports commentary in order to automatically recognize events and extract insights","date":"2023-07-18","arxiv_id":"2307.10303","n_code_links":2,"syntology":null},{"paper":"/paper/anticipating-technical-expertise-and","slug":"anticipating-technical-expertise-and","title":"Anticipating Technical Expertise and Capability Evolution in Research Communities using Dynamic Graph Transformers","date":"2023-07-18","arxiv_id":"2307.09665","n_code_links":1,"syntology":null},{"paper":"/paper/application-of-bert-in-wind-power-forecasting","slug":"application-of-bert-in-wind-power-forecasting","title":"Application of BERT in Wind Power Forecasting-Teletraan's Solution in Baidu KDD Cup 2022","date":"2023-07-18","arxiv_id":"2307.09248","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-ableism-an-exploration-of-explicit","title":"Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models","date":"2023-07-18","arxiv_id":"2307.09209","n_code_links":0,"syntology":null},{"paper":"/paper/can-model-fusing-help-transformers-in-long","slug":"can-model-fusing-help-transformers-in-long","title":"Can Model Fusing Help Transformers in Long Document Classification? An Empirical Study","date":"2023-07-18","arxiv_id":"2307.09532","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatspot-bootstrapping-multimodal-llms-via","title":"ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning","date":"2023-07-18","arxiv_id":"2307.09474","n_code_links":0,"syntology":null},{"paper":null,"slug":"ditto-diffusion-inspired-temporal-transformer","title":"Real-time Inference and Extrapolation via a Diffusion-inspired Temporal Transformer Operator (DiTTO)","date":"2023-07-18","arxiv_id":"2307.09072","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotional-intelligence-of-large-language","title":"Emotional Intelligence of Large Language Models","date":"2023-07-18","arxiv_id":"2307.09042","n_code_links":0,"syntology":null},{"paper":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lchen001/llmdrift"],"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"]}}},{"paper":null,"slug":"human-action-recognition-in-still-images","title":"Human Action Recognition in Still Images Using ConViT","date":"2023-07-18","arxiv_id":"2307.08994","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-text-semantic-similarity-modeling","title":"Improving Text Semantic Similarity Modeling through a 3D Siamese Network","date":"2023-07-18","arxiv_id":"2307.09274","n_code_links":0,"syntology":null},{"paper":"/paper/jazzvar-a-dataset-of-variations-found-within","slug":"jazzvar-a-dataset-of-variations-found-within","title":"JAZZVAR: A Dataset of Variations found within Solo Piano Performances of Jazz Standards for Music Overpainting","date":"2023-07-18","arxiv_id":"2307.09670","n_code_links":1,"syntology":null},{"paper":null,"slug":"katie-a-system-for-key-attributes","title":"KATIE: A System for Key Attributes Identification in Product Knowledge Graph Construction","date":"2023-07-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"light-weight-vision-transformer-with-parallel","title":"Light-Weight Vision Transformer with Parallel Local and Global Self-Attention","date":"2023-07-18","arxiv_id":"2307.09120","n_code_links":0,"syntology":null},{"paper":"/paper/lightgt-a-light-graph-transformer-for","slug":"lightgt-a-light-graph-transformer-for","title":"LightGT: A Light Graph Transformer for Multimedia Recommendation","date":"2023-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/moca-self-supervised-representation-learning","slug":"moca-self-supervised-representation-learning","title":"MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments","date":"2023-07-18","arxiv_id":"2307.09361","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":12,"n_instrument":1,"unverified":2,"pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["valeoai/moca"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-modal-discussion-transformer","slug":"multi-modal-discussion-transformer","title":"Multi-Modal Discussion Transformer: Integrating Text, Images and Graph Transformers to Detect Hate Speech on Social Media","date":"2023-07-18","arxiv_id":"2307.09312","n_code_links":1,"syntology":null},{"paper":"/paper/nu-mcc-multiview-compressive-coding-with-1","slug":"nu-mcc-multiview-compressive-coding-with-1","title":"NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF","date":"2023-07-18","arxiv_id":"2307.09112","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":8,"n_instrument":3,"unverified":5,"pointer_only":2,"phrase":"11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["sail-sg/numcc"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"u-shaped-transformer-retain-high-frequency","title":"U-shaped Transformer: Retain High Frequency Context in Time Series Analysis","date":"2023-07-18","arxiv_id":"2307.09019","n_code_links":0,"syntology":null},{"paper":null,"slug":"unitabe-pretraining-a-unified-tabular-encoder","title":"UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science","date":"2023-07-18","arxiv_id":"2307.09249","n_code_links":0,"syntology":null},{"paper":null,"slug":"unveiling-gender-bias-in-terms-of-profession","title":"Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implications","date":"2023-07-18","arxiv_id":"2307.09162","n_code_links":0,"syntology":null},{"paper":"/paper/a-mixed-policy-to-improve-performance-of","slug":"a-mixed-policy-to-improve-performance-of","title":"A mixed policy to improve performance of language models on math problems","date":"2023-07-17","arxiv_id":"2307.08767","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-on-the-performance-of-generative-pre","title":"A Study on the Performance of Generative Pre-trained Transformer (GPT) in Simulating Depressed Individuals on the Standardized Depressive Symptom Scale","date":"2023-07-17","arxiv_id":"2307.08576","n_code_links":0,"syntology":null},{"paper":null,"slug":"abductive-reasoning-with-the-gpt-4-language","title":"Abductive Reasoning with the GPT-4 Language Model: Case studies from criminal investigation, medical practice, scientific research","date":"2023-07-17","arxiv_id":"2307.10250","n_code_links":0,"syntology":null},{"paper":"/paper/alpagasus-training-a-better-alpaca-with-fewer","slug":"alpagasus-training-a-better-alpaca-with-fewer","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","date":"2023-07-17","arxiv_id":"2307.08701","n_code_links":3,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gpt4life/alpagasus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bus-efficient-and-effective-vision-language","title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization","date":"2023-07-17","arxiv_id":"2307.08504","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-is-good-but-bing-chat-is-better-for","title":"ChatGPT is Good but Bing Chat is Better for Vietnamese Students","date":"2023-07-17","arxiv_id":"2307.08272","n_code_links":0,"syntology":null},{"paper":"/paper/collie-systematic-construction-of-constrained","slug":"collie-systematic-construction-of-constrained","title":"COLLIE: Systematic Construction of Constrained Text Generation Tasks","date":"2023-07-17","arxiv_id":"2307.08689","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["princeton-nlp/Collie"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"complexity-matters-rethinking-the-latent","title":"Complexity Matters: Rethinking the Latent Space for Generative Modeling","date":"2023-07-17","arxiv_id":"2307.08283","n_code_links":0,"syntology":null},{"paper":"/paper/deficiency-aware-masked-transformer-for-video","slug":"deficiency-aware-masked-transformer-for-video","title":"Deficiency-Aware Masked Transformer for Video Inpainting","date":"2023-07-17","arxiv_id":"2307.08629","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-prediction-of-peptide-self-assembly","slug":"efficient-prediction-of-peptide-self-assembly","title":"Efficient Prediction of Peptide Self-assembly through Sequential and Graphical Encoding","date":"2023-07-17","arxiv_id":"2307.09169","n_code_links":1,"syntology":null},{"paper":"/paper/gbt-two-stage-transformer-framework-for-non","slug":"gbt-two-stage-transformer-framework-for-non","title":"GBT: Two-stage transformer framework for non-stationary time series forecasting","date":"2023-07-17","arxiv_id":"2307.08302","n_code_links":1,"syntology":null},{"paper":"/paper/gear-augmenting-language-models-with","slug":"gear-augmenting-language-models-with","title":"GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution","date":"2023-07-17","arxiv_id":"2307.08775","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["yining610/gear"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"8b2a074cf8eb151df3efad0cd2043db80dd11626657d12ea467980c51dd455b8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}