{"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/attention/papers/193","list_of":"/method/attention","method":"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":193,"pages_in_order":316,"rows_per_page":100,"rows":[19201,19300],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/192","next":"/method/attention/papers/194","papers":[{"paper":"/paper/emoji-prediction-using-transformer-models","slug":"emoji-prediction-using-transformer-models","title":"Emoji Prediction in Tweets using BERT","date":"2023-07-05","arxiv_id":"2307.02054","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-large","title":"Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations","date":"2023-07-05","arxiv_id":"2307.03678","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-continual-learning-for-code","title":"Exploring Continual Learning for Code Generation Models","date":"2023-07-05","arxiv_id":"2307.02435","n_code_links":0,"syntology":null},{"paper":"/paper/external-reasoning-towards-multi-large","slug":"external-reasoning-towards-multi-large","title":"External Reasoning: Towards Multi-Large-Language-Models Interchangeable Assistance with Human Feedback","date":"2023-07-05","arxiv_id":"2307.12057","n_code_links":1,"syntology":null},{"paper":"/paper/hoodwinked-deception-and-cooperation-in-a","slug":"hoodwinked-deception-and-cooperation-in-a","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","date":"2023-07-05","arxiv_id":"2308.01404","n_code_links":1,"syntology":null},{"paper":"/paper/improving-automatic-parallel-training-via","slug":"improving-automatic-parallel-training-via","title":"Improving Automatic Parallel Training via Balanced Memory Workload Optimization","date":"2023-07-05","arxiv_id":"2307.02031","n_code_links":1,"syntology":null},{"paper":"/paper/jailbroken-how-does-llm-safety-training-fail","slug":"jailbroken-how-does-llm-safety-training-fail","title":"Jailbroken: How Does LLM Safety Training Fail?","date":"2023-07-05","arxiv_id":"2307.02483","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-denoised-abstract-meaning","title":"Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction","date":"2023-07-05","arxiv_id":"2307.02127","n_code_links":0,"syntology":null},{"paper":"/paper/longnet-scaling-transformers-to-1000000000","slug":"longnet-scaling-transformers-to-1000000000","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","date":"2023-07-05","arxiv_id":"2307.02486","n_code_links":3,"syntology":null},{"paper":"/paper/mae-dfer-efficient-masked-autoencoder-for","slug":"mae-dfer-efficient-masked-autoencoder-for","title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition","date":"2023-07-05","arxiv_id":"2307.02227","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":12,"n_instrument":1,"unverified":1,"pointer_only":7,"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) · 1 unverified","official":{"repos":["sunlicai/mae-dfer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"make-a-long-image-short-adaptive-token-length-1","title":"Make A Long Image Short: Adaptive Token Length for Vision Transformers","date":"2023-07-05","arxiv_id":"2307.02092","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-prototypical-transformer-for","title":"Multi-Scale Prototypical Transformer for Whole Slide Image Classification","date":"2023-07-05","arxiv_id":"2307.02308","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-controllable-transformer-based","slug":"multilingual-controllable-transformer-based","title":"Multilingual Controllable Transformer-Based Lexical Simplification","date":"2023-07-05","arxiv_id":"2307.02120","n_code_links":1,"syntology":null},{"paper":null,"slug":"named-entity-inclusion-in-abstractive-text-1","title":"Named Entity Inclusion in Abstractive Text Summarization","date":"2023-07-05","arxiv_id":"2307.02570","n_code_links":0,"syntology":null},{"paper":"/paper/natural-language-deduction-with-incomplete-1","slug":"natural-language-deduction-with-incomplete-1","title":"Deductive Additivity for Planning of Natural Language Proofs","date":"2023-07-05","arxiv_id":"2307.02472","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-source-large-language-models-outperform","title":"Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning","date":"2023-07-05","arxiv_id":"2307.02179","n_code_links":0,"syntology":null},{"paper":null,"slug":"sumformer-universal-approximation-for","title":"Sumformer: Universal Approximation for Efficient Transformers","date":"2023-07-05","arxiv_id":"2307.02301","n_code_links":0,"syntology":null},{"paper":"/paper/task-specific-alignment-and-multiple-level","slug":"task-specific-alignment-and-multiple-level","title":"Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition","date":"2023-07-05","arxiv_id":"2307.01985","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-formai-dataset-generative-ai-in-software","title":"The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification","date":"2023-07-05","arxiv_id":"2307.02192","n_code_links":0,"syntology":null},{"paper":"/paper/deep-attention-q-network-for-personalized","slug":"deep-attention-q-network-for-personalized","title":"Deep Attention Q-Network for Personalized Treatment Recommendation","date":"2023-07-04","arxiv_id":"2307.01519","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-features-for-contactless-fingerprint","title":"Deep Features for Contactless Fingerprint Presentation Attack Detection: Can They Be Generalized?","date":"2023-07-04","arxiv_id":"2307.01845","n_code_links":0,"syntology":null},{"paper":"/paper/dit-3d-exploring-plain-diffusion-transformers-1","slug":"dit-3d-exploring-plain-diffusion-transformers-1","title":"DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation","date":"2023-07-04","arxiv_id":"2307.01831","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/edgeface-efficient-face-recognition-model-for","slug":"edgeface-efficient-face-recognition-model-for","title":"EdgeFace: Efficient Face Recognition Model for Edge Devices","date":"2023-07-04","arxiv_id":"2307.01838","n_code_links":3,"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":["otroshi/edgeface"],"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":"/paper/embodied-task-planning-with-large-language","slug":"embodied-task-planning-with-large-language","title":"Embodied Task Planning with Large Language Models","date":"2023-07-04","arxiv_id":"2307.01848","n_code_links":1,"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":["Gary3410/TaPA"],"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":"exploring-transformers-for-on-line","title":"Exploring Transformers for On-Line Handwritten Signature Verification","date":"2023-07-04","arxiv_id":"2307.01663","n_code_links":0,"syntology":null},{"paper":"/paper/h-denseformer-an-efficient-hybrid-densely","slug":"h-denseformer-an-efficient-hybrid-densely","title":"H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation","date":"2023-07-04","arxiv_id":"2307.01486","n_code_links":1,"syntology":null},{"paper":"/paper/kdstm-neural-semi-supervised-topic-modeling","slug":"kdstm-neural-semi-supervised-topic-modeling","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","date":"2023-07-04","arxiv_id":"2307.01878","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 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":null}},{"paper":null,"slug":"knowledge-graph-for-nlg-in-the-context-of","title":"Knowledge Graph for NLG in the context of conversational agents","date":"2023-07-04","arxiv_id":"2307.01548","n_code_links":0,"syntology":null},{"paper":null,"slug":"last-layer-state-space-model-for","title":"Last layer state space model for representation learning and uncertainty quantification","date":"2023-07-04","arxiv_id":"2307.01566","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-prompt-in-the-classroom-to","title":"Learning to Prompt in the Classroom to Understand AI Limits: A pilot study","date":"2023-07-04","arxiv_id":"2307.01540","n_code_links":0,"syntology":null},{"paper":"/paper/maskbev-joint-object-detection-and-footprint","slug":"maskbev-joint-object-detection-and-footprint","title":"MaskBEV: Joint Object Detection and Footprint Completion for Bird's-eye View 3D Point Clouds","date":"2023-07-04","arxiv_id":"2307.01864","n_code_links":1,"syntology":null},{"paper":"/paper/pretraining-is-all-you-need-a-multi-atlas","slug":"pretraining-is-all-you-need-a-multi-atlas","title":"Pretraining is All You Need: A Multi-Atlas Enhanced Transformer Framework for Autism Spectrum Disorder Classification","date":"2023-07-04","arxiv_id":"2307.01759","n_code_links":1,"syntology":null},{"paper":"/paper/sageformer-series-aware-graph-enhanced","slug":"sageformer-series-aware-graph-enhanced","title":"SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecasting","date":"2023-07-04","arxiv_id":"2307.01616","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhangzw16/SageFormer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"selffed-self-supervised-federated-learning","title":"SelfFed: Self-supervised Federated Learning for Data Heterogeneity and Label Scarcity in IoMT","date":"2023-07-04","arxiv_id":"2307.01514","n_code_links":0,"syntology":null},{"paper":"/paper/spike-driven-transformer-1","slug":"spike-driven-transformer-1","title":"Spike-driven Transformer","date":"2023-07-04","arxiv_id":"2307.01694","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["biclab/spike-driven-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/transformed-protoform-reconstruction","slug":"transformed-protoform-reconstruction","title":"Transformed Protoform Reconstruction","date":"2023-07-04","arxiv_id":"2307.01896","n_code_links":1,"syntology":null},{"paper":null,"slug":"alberti-a-multilingual-domain-specific","title":"ALBERTI, a Multilingual Domain Specific Language Model for Poetry Analysis","date":"2023-07-03","arxiv_id":"2307.01387","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-the-snapshot-brain-tokenized-graph","slug":"beyond-the-snapshot-brain-tokenized-graph","title":"Beyond the Snapshot: Brain Tokenized Graph Transformer for Longitudinal Brain Functional Connectome Embedding","date":"2023-07-03","arxiv_id":"2307.00858","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-prediction-of-knee-osteoarthritis","slug":"end-to-end-prediction-of-knee-osteoarthritis","title":"End-To-End Prediction of Knee Osteoarthritis Progression With Multi-Modal Transformers","date":"2023-07-03","arxiv_id":"2307.00873","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-shutdown-avoidance-of-language","slug":"evaluating-shutdown-avoidance-of-language","title":"Evaluating Shutdown Avoidance of Language Models in Textual Scenarios","date":"2023-07-03","arxiv_id":"2307.00787","n_code_links":1,"syntology":null},{"paper":null,"slug":"guided-patch-grouping-wavelet-transformer","title":"Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation","date":"2023-07-03","arxiv_id":"2307.00711","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-memory-transformer-for","slug":"implicit-memory-transformer-for","title":"Implicit Memory Transformer for Computationally Efficient Simultaneous Speech Translation","date":"2023-07-03","arxiv_id":"2307.01381","n_code_links":1,"syntology":null},{"paper":"/paper/improving-language-plasticity-via-pretraining","slug":"improving-language-plasticity-via-pretraining","title":"Improving Language Plasticity via Pretraining with Active Forgetting","date":"2023-07-03","arxiv_id":"2307.01163","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpretability-and-transparency-driven","title":"Interpretability and Transparency-Driven Detection and Transformation of Textual Adversarial Examples (IT-DT)","date":"2023-07-03","arxiv_id":"2307.01225","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-zero-shot-llm-prompting-for","title":"Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction","date":"2023-07-03","arxiv_id":"2307.01128","n_code_links":0,"syntology":null},{"paper":null,"slug":"population-age-group-sensitivity-for-covid-19","title":"Population Age Group Sensitivity for COVID-19 Infections with Deep Learning","date":"2023-07-03","arxiv_id":"2307.00751","n_code_links":0,"syntology":null},{"paper":"/paper/shiftable-context-addressing-training","slug":"shiftable-context-addressing-training","title":"Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation","date":"2023-07-03","arxiv_id":"2307.01377","n_code_links":1,"syntology":null},{"paper":"/paper/trainable-transformer-in-transformer","slug":"trainable-transformer-in-transformer","title":"Trainable Transformer in Transformer","date":"2023-07-03","arxiv_id":"2307.01189","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":["abhishekpanigrahi1996/transformer_in_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"unbiased-pain-assessment-through-wearables","title":"Wearable-based Fair and Accurate Pain Assessment Using Multi-Attribute Fairness Loss in Convolutional Neural Networks","date":"2023-07-03","arxiv_id":"2307.05333","n_code_links":0,"syntology":null},{"paper":null,"slug":"volta-diverse-and-controllable-question","title":"VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder","date":"2023-07-03","arxiv_id":"2307.00852","n_code_links":0,"syntology":null},{"paper":"/paper/biocpt-contrastive-pre-trained-transformers","slug":"biocpt-contrastive-pre-trained-transformers","title":"MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval","date":"2023-07-02","arxiv_id":"2307.00589","n_code_links":2,"syntology":null},{"paper":"/paper/clipsitu-effectively-leveraging-clip-for","slug":"clipsitu-effectively-leveraging-clip-for","title":"ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition","date":"2023-07-02","arxiv_id":"2307.00586","n_code_links":1,"syntology":null},{"paper":null,"slug":"conformer-llms-convolution-augmented-large","title":"Conformer LLMs -- Convolution Augmented Large Language Models","date":"2023-07-02","arxiv_id":"2307.00461","n_code_links":0,"syntology":null},{"paper":null,"slug":"referring-video-object-segmentation-with","title":"Bidirectional Correlation-Driven Inter-Frame Interaction Transformer for Referring Video Object Segmentation","date":"2023-07-02","arxiv_id":"2307.00536","n_code_links":0,"syntology":null},{"paper":null,"slug":"tensorgpt-efficient-compression-of-the","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","date":"2023-07-02","arxiv_id":"2307.00526","n_code_links":0,"syntology":null},{"paper":"/paper/autost-training-free-neural-architecture","slug":"autost-training-free-neural-architecture","title":"AutoST: Training-free Neural Architecture Search for Spiking Transformers","date":"2023-07-01","arxiv_id":"2307.00293","n_code_links":1,"syntology":null},{"paper":null,"slug":"effective-matching-of-patients-to-clinical","title":"Effective Matching of Patients to Clinical Trials using Entity Extraction and Neural Re-ranking","date":"2023-07-01","arxiv_id":"2307.00381","n_code_links":0,"syntology":null},{"paper":null,"slug":"general-part-assembly-planning","title":"Rearrangement Planning for General Part Assembly","date":"2023-07-01","arxiv_id":"2307.00206","n_code_links":0,"syntology":null},{"paper":"/paper/how-far-is-language-model-from-100-few-shot","slug":"how-far-is-language-model-from-100-few-shot","title":"How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain","date":"2023-07-01","arxiv_id":"2307.00186","n_code_links":1,"syntology":null},{"paper":"/paper/learning-content-enhanced-mask-transformer","slug":"learning-content-enhanced-mask-transformer","title":"Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation","date":"2023-07-01","arxiv_id":"2307.00371","n_code_links":1,"syntology":null},{"paper":null,"slug":"more-for-less-compact-convolutional","title":"More for Less: Compact Convolutional Transformers Enable Robust Medical Image Classification with Limited Data","date":"2023-07-01","arxiv_id":"2307.00213","n_code_links":0,"syntology":null},{"paper":null,"slug":"pm-detr-domain-adaptive-prompt-memory-for","title":"PM-DETR: Domain Adaptive Prompt Memory for Object Detection with Transformers","date":"2023-07-01","arxiv_id":"2307.00313","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-temporal-enhanced-transformer-towards","slug":"spatial-temporal-enhanced-transformer-towards","title":"Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection","date":"2023-07-01","arxiv_id":"2307.00347","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":["eaphan/stemd"],"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":"/paper/act3d-infinite-resolution-action-detection","slug":"act3d-infinite-resolution-action-detection","title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","date":"2023-06-30","arxiv_id":"2306.17817","n_code_links":2,"syntology":null},{"paper":null,"slug":"harnessing-llms-in-curricular-design-using","title":"Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectives","date":"2023-06-30","arxiv_id":"2306.17459","n_code_links":0,"syntology":null},{"paper":"/paper/hvtsurv-hierarchical-vision-transformer-for","slug":"hvtsurv-hierarchical-vision-transformer-for","title":"HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image","date":"2023-06-30","arxiv_id":"2306.17373","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["szc19990412/hvtsurv"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-are-effective-text","title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting","date":"2023-06-30","arxiv_id":"2306.17563","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-gpt-for-automating","title":"Large Language Models (GPT) for automating feedback on programming assignments","date":"2023-06-30","arxiv_id":"2307.00150","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-localize-with-attention-from","title":"Learning to Localize with Attention: from sparse mmWave channel estimates from a single BS to high accuracy 3D location","date":"2023-06-30","arxiv_id":"2307.00167","n_code_links":0,"syntology":null},{"paper":"/paper/meta-reasoning-semantics-symbol","slug":"meta-reasoning-semantics-symbol","title":"Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models","date":"2023-06-30","arxiv_id":"2306.17820","n_code_links":1,"syntology":null},{"paper":"/paper/preference-ranking-optimization-for-human","slug":"preference-ranking-optimization-for-human","title":"Preference Ranking Optimization for Human Alignment","date":"2023-06-30","arxiv_id":"2306.17492","n_code_links":1,"syntology":null},{"paper":null,"slug":"spae-semantic-pyramid-autoencoder-for","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","date":"2023-06-30","arxiv_id":"2306.17842","n_code_links":0,"syntology":null},{"paper":"/paper/spatr-mocap-3d-human-action-recognition-based","slug":"spatr-mocap-3d-human-action-recognition-based","title":"SpATr: MoCap 3D Human Action Recognition based on Spiral Auto-encoder and Transformer Network","date":"2023-06-30","arxiv_id":"2306.17574","n_code_links":1,"syntology":null},{"paper":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","n_code_links":0,"syntology":null},{"paper":"/paper/summqa-at-mediqa-chat-2023-in-context","slug":"summqa-at-mediqa-chat-2023-in-context","title":"SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization","date":"2023-06-30","arxiv_id":"2306.17384","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-shaped-transformer-attention-models-in","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","date":"2023-06-30","arxiv_id":"2306.17759","n_code_links":0,"syntology":null},{"paper":null,"slug":"ticket-bert-labeling-incident-management","title":"Ticket-BERT: Labeling Incident Management Tickets with Language Models","date":"2023-06-30","arxiv_id":"2307.00108","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-improving-the-performance-of-pre","title":"Towards Improving the Performance of Pre-Trained Speech Models for Low-Resource Languages Through Lateral Inhibition","date":"2023-06-30","arxiv_id":"2306.17792","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-in-healthcare-a-survey","title":"Transformers in Healthcare: A Survey","date":"2023-06-30","arxiv_id":"2307.00067","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-negation-detection-assessment-of-gpts","title":"A negation detection assessment of GPTs: analysis with the xNot360 dataset","date":"2023-06-29","arxiv_id":"2306.16638","n_code_links":0,"syntology":null},{"paper":"/paper/answer-mining-from-a-pool-of-images-towards","slug":"answer-mining-from-a-pool-of-images-towards","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","date":"2023-06-29","arxiv_id":"2306.16713","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":6,"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) · 0 unverified","official":{"repos":["Abhiram4572/mi_bart"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"benchmarking-large-language-model","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","date":"2023-06-29","arxiv_id":"2306.16793","n_code_links":0,"syntology":null},{"paper":"/paper/binaryvit-pushing-binary-vision-transformers","slug":"binaryvit-pushing-binary-vision-transformers","title":"BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models","date":"2023-06-29","arxiv_id":"2306.16678","n_code_links":1,"syntology":null},{"paper":null,"slug":"classifying-crime-types-using-judgment","title":"Classifying Crime Types using Judgment Documents from Social Media","date":"2023-06-29","arxiv_id":"2306.17020","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmath-can-your-language-model-pass-chinese","title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?","date":"2023-06-29","arxiv_id":"2306.16636","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-for-programming-education","title":"Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors","date":"2023-06-29","arxiv_id":"2306.17156","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-hugging-face","title":"Harnessing the Power of Hugging Face Transformers for Predicting Mental Health Disorders in Social Networks","date":"2023-06-29","arxiv_id":"2306.16891","n_code_links":0,"syntology":null},{"paper":"/paper/llavar-enhanced-visual-instruction-tuning-for","slug":"llavar-enhanced-visual-instruction-tuning-for","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","date":"2023-06-29","arxiv_id":"2306.17107","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":2,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SALT-NLP/LLaVAR"],"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/lyricwhiz-robust-multilingual-zero-shot","slug":"lyricwhiz-robust-multilingual-zero-shot","title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT","date":"2023-06-29","arxiv_id":"2306.17103","n_code_links":1,"syntology":null},{"paper":"/paper/mnisq-a-large-scale-quantum-circuit-dataset","slug":"mnisq-a-large-scale-quantum-circuit-dataset","title":"MNISQ: A Large-Scale Quantum Circuit Dataset for Machine Learning on/for Quantum Computers in the NISQ era","date":"2023-06-29","arxiv_id":"2306.16627","n_code_links":1,"syntology":null},{"paper":"/paper/multi-source-semantic-graph-based-multimodal","slug":"multi-source-semantic-graph-based-multimodal","title":"Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation","date":"2023-06-29","arxiv_id":"2306.16650","n_code_links":1,"syntology":null},{"paper":"/paper/umass-bionlp-at-mediqa-chat-2023-can-llms","slug":"umass-bionlp-at-mediqa-chat-2023-can-llms","title":"UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?","date":"2023-06-29","arxiv_id":"2306.16931","n_code_links":1,"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":["believewhat/dr.noteaid"],"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/an-efficient-sparse-inference-software","slug":"an-efficient-sparse-inference-software","title":"An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs","date":"2023-06-28","arxiv_id":"2306.16601","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-calibration-and-error-correction","title":"Pareto Optimal Learning for Estimating Large Language Model Errors","date":"2023-06-28","arxiv_id":"2306.16564","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-the-hype-assessing-the-performance","title":"Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5","date":"2023-06-28","arxiv_id":"2306.15887","n_code_links":0,"syntology":null},{"paper":"/paper/chatlaw-open-source-legal-large-language","slug":"chatlaw-open-source-legal-large-language","title":"Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model","date":"2023-06-28","arxiv_id":"2306.16092","n_code_links":1,"syntology":null},{"paper":null,"slug":"inferring-the-goals-of-communicating-agents","title":"Inferring the Goals of Communicating Agents from Actions and Instructions","date":"2023-06-28","arxiv_id":"2306.16207","n_code_links":0,"syntology":null},{"paper":"/paper/is-chatgpt-a-biomedical-expert-exploring-the","slug":"is-chatgpt-a-biomedical-expert-exploring-the","title":"Is ChatGPT a Biomedical Expert? -- Exploring the Zero-Shot Performance of Current GPT Models in Biomedical Tasks","date":"2023-06-28","arxiv_id":"2306.16108","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-gpt-4-for-food-effect","title":"Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting","date":"2023-06-28","arxiv_id":"2306.16275","n_code_links":0,"syntology":null},{"paper":null,"slug":"mass-spectra-prediction-with-structural-motif","title":"Mass Spectra Prediction with Structural Motif-based Graph Neural Networks","date":"2023-06-28","arxiv_id":"2306.16085","n_code_links":0,"syntology":null}],"record_sha256":"ee1a0a98b26b58789d09691e02c439c60d4b7393fae029fbc8cdc4b30eef00f0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}