{"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/transformer/papers/79","list_of":"/method/transformer","method":"Transformer","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":79,"pages_in_order":140,"rows_per_page":100,"rows":[7801,7900],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/78","next":"/method/transformer/papers/80","papers":[{"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":"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/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":"/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/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":"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":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":"/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/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":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":"/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":"/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},{"paper":"/paper/mathbf-c-2-former-calibrated-and","slug":"mathbf-c-2-former-calibrated-and","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","date":"2023-06-28","arxiv_id":"2306.16175","n_code_links":2,"syntology":null},{"paper":null,"slug":"skillnet-x-a-multilingual-multitask-model","title":"SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills","date":"2023-06-28","arxiv_id":"2306.16176","n_code_links":0,"syntology":null},{"paper":"/paper/taqyim-evaluating-arabic-nlp-tasks-using","slug":"taqyim-evaluating-arabic-nlp-tasks-using","title":"Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models","date":"2023-06-28","arxiv_id":"2306.16322","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-2nd-place-solution-for-2023-waymo-open","title":"The 2nd Place Solution for 2023 Waymo Open Sim Agents Challenge","date":"2023-06-28","arxiv_id":"2306.15914","n_code_links":0,"syntology":null},{"paper":"/paper/cellvit-vision-transformers-for-precise-cell","slug":"cellvit-vision-transformers-for-precise-cell","title":"CellViT: Vision Transformers for Precise Cell Segmentation and Classification","date":"2023-06-27","arxiv_id":"2306.15350","n_code_links":3,"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":["tio-ikim/cellvit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"evaluating-gpt-3-5-and-gpt-4-on-grammatical","title":"Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese","date":"2023-06-27","arxiv_id":"2306.15788","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedet-a-communication-efficient-federated","title":"FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer","date":"2023-06-27","arxiv_id":"2306.15347","n_code_links":0,"syntology":null},{"paper":"/paper/hyenadna-long-range-genomic-sequence-modeling","slug":"hyenadna-long-range-genomic-sequence-modeling","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","date":"2023-06-27","arxiv_id":"2306.15794","n_code_links":4,"syntology":{"ran":17,"of":28,"n_ran_checked":13,"n_instrument":4,"unverified":11,"pointer_only":1,"phrase":"17 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","official":{"repos":["HazyResearch/hyena-dna"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/leandojo-theorem-proving-with-retrieval-1","slug":"leandojo-theorem-proving-with-retrieval-1","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","date":"2023-06-27","arxiv_id":"2306.15626","n_code_links":3,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["lean-dojo/leandojo","lean-dojo/leandojochatgpt","lean-dojo/reprover"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/novel-hybrid-learning-algorithms-for-improved","slug":"novel-hybrid-learning-algorithms-for-improved","title":"Novel Hybrid-Learning Algorithms for Improved Millimeter-Wave Imaging Systems","date":"2023-06-27","arxiv_id":"2306.15341","n_code_links":1,"syntology":null},{"paper":null,"slug":"style-transfer-based-speech-and-audio-visual","title":"Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos","date":"2023-06-27","arxiv_id":"2306.15644","n_code_links":0,"syntology":null},{"paper":null,"slug":"taming-detection-transformers-for-medical","title":"Taming Detection Transformers for Medical Object Detection","date":"2023-06-27","arxiv_id":"2306.15472","n_code_links":0,"syntology":null},{"paper":"/paper/towards-predicting-pedestrian-evacuation-time","slug":"towards-predicting-pedestrian-evacuation-time","title":"Towards predicting Pedestrian Evacuation Time and Density from Floorplans using a Vision Transformer","date":"2023-06-27","arxiv_id":"2306.15318","n_code_links":1,"syntology":null},{"paper":null,"slug":"variational-latent-discrete-representation","title":"Variational latent discrete representation for time series modelling","date":"2023-06-27","arxiv_id":"2306.15282","n_code_links":0,"syntology":null},{"paper":"/paper/cst-yolo-a-novel-method-for-blood-cell","slug":"cst-yolo-a-novel-method-for-blood-cell","title":"CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer","date":"2023-06-26","arxiv_id":"2306.14590","n_code_links":1,"syntology":null},{"paper":"/paper/dnabert-2-efficient-foundation-model-and","slug":"dnabert-2-efficient-foundation-model-and","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","date":"2023-06-26","arxiv_id":"2306.15006","n_code_links":6,"syntology":{"ran":13,"of":23,"n_ran_checked":9,"n_instrument":4,"unverified":10,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified","official":{"repos":["magics-lab/dnabert_2","zhihan1996/dnabert_2"],"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/fesvibs-federated-split-learning-of-vision","slug":"fesvibs-federated-split-learning-of-vision","title":"FeSViBS: Federated Split Learning of Vision Transformer with Block Sampling","date":"2023-06-26","arxiv_id":"2306.14638","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-multimodal-models-notes-on-cvpr-2023","title":"Large Multimodal Models: Notes on CVPR 2023 Tutorial","date":"2023-06-26","arxiv_id":"2306.14895","n_code_links":0,"syntology":null},{"paper":null,"slug":"lm4hpc-towards-effective-language-model","title":"LM4HPC: Towards Effective Language Model Application in High-Performance Computing","date":"2023-06-26","arxiv_id":"2306.14979","n_code_links":0,"syntology":null},{"paper":"/paper/longcoder-a-long-range-pre-trained-language","slug":"longcoder-a-long-range-pre-trained-language","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","date":"2023-06-26","arxiv_id":"2306.14893","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":["microsoft/CodeBERT"],"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":"parameternet-parameters-are-all-you-need-for","title":"ParameterNet: Parameters Are All You Need","date":"2023-06-26","arxiv_id":"2306.14525","n_code_links":0,"syntology":null},{"paper":null,"slug":"supervised-pretraining-can-learn-in-context","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","date":"2023-06-26","arxiv_id":"2306.14892","n_code_links":0,"syntology":null},{"paper":"/paper/vint-a-foundation-model-for-visual-navigation","slug":"vint-a-foundation-model-for-visual-navigation","title":"ViNT: A Foundation Model for Visual Navigation","date":"2023-06-26","arxiv_id":"2306.14846","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-window-pruning-for-efficient-local","title":"Adaptive Window Pruning for Efficient Local Motion Deblurring","date":"2023-06-25","arxiv_id":"2306.14268","n_code_links":0,"syntology":null},{"paper":null,"slug":"g-sto-sequential-main-shopping-intention","title":"G-STO: Sequential Main Shopping Intention Detection via Graph-Regularized Stochastic Transformer","date":"2023-06-25","arxiv_id":"2306.14314","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-cross-contrastive-learning-for","title":"Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentation","date":"2023-06-25","arxiv_id":"2306.14293","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-cyber-threat-detection-with","title":"Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices","date":"2023-06-25","arxiv_id":"2306.14263","n_code_links":0,"syntology":null},{"paper":null,"slug":"steganographic-capacity-of-deep-learning","title":"Steganographic Capacity of Deep Learning Models","date":"2023-06-25","arxiv_id":"2306.17189","n_code_links":0,"syntology":null},{"paper":null,"slug":"action-q-transformer-visual-explanation-in","title":"Action Q-Transformer: Visual Explanation in Deep Reinforcement Learning with Encoder-Decoder Model using Action Query","date":"2023-06-24","arxiv_id":"2306.13879","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-4-support-analysis-of-textual-data-in","title":"Can GPT-4 Support Analysis of Textual Data in Tasks Requiring Highly Specialized Domain Expertise?","date":"2023-06-24","arxiv_id":"2306.13906","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-flip-reasoning-in-multiparty-1","title":"Emotion Flip Reasoning in Multiparty Conversations","date":"2023-06-24","arxiv_id":"2306.13959","n_code_links":0,"syntology":null},{"paper":"/paper/fusing-multimodal-signals-on-hyper-complex","slug":"fusing-multimodal-signals-on-hyper-complex","title":"Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents","date":"2023-06-24","arxiv_id":"2306.13968","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-sequence-models-for-sequential-decision","title":"Large Sequence Models for Sequential Decision-Making: A Survey","date":"2023-06-24","arxiv_id":"2306.13945","n_code_links":0,"syntology":null},{"paper":null,"slug":"waypoint-transformer-reinforcement-learning","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","date":"2023-06-24","arxiv_id":"2306.14069","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-the-performance-gap-between-detr-and","slug":"bridging-the-performance-gap-between-detr-and","title":"Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images","date":"2023-06-23","arxiv_id":"2306.13526","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-language-speech-emotion-recognition","title":"Cross-Language Speech Emotion Recognition Using Multimodal Dual Attention Transformers","date":"2023-06-23","arxiv_id":"2306.13804","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-online-processing-with-deep-neural","slug":"efficient-online-processing-with-deep-neural","title":"Efficient Online Processing with Deep Neural Networks","date":"2023-06-23","arxiv_id":"2306.13474","n_code_links":1,"syntology":null},{"paper":"/paper/incorporating-graph-information-in","slug":"incorporating-graph-information-in","title":"Incorporating Graph Information in Transformer-based AMR Parsing","date":"2023-06-23","arxiv_id":"2306.13467","n_code_links":1,"syntology":null},{"paper":"/paper/long-range-language-modeling-with-self","slug":"long-range-language-modeling-with-self","title":"Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval","date":"2023-06-23","arxiv_id":"2306.13421","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ohadrubin/rpt"],"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":["official"]}}},{"paper":"/paper/prores-exploring-degradation-aware-visual","slug":"prores-exploring-degradation-aware-visual","title":"ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration","date":"2023-06-23","arxiv_id":"2306.13653","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":["leonmakise/prores"],"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":"swin-free-achieving-better-cross-window","title":"Swin-Free: Achieving Better Cross-Window Attention and Efficiency with Size-varying Window","date":"2023-06-23","arxiv_id":"2306.13776","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-double-helix-inside-the-nlp-transformer","title":"The Double Helix inside the NLP Transformer","date":"2023-06-23","arxiv_id":"2306.13817","n_code_links":0,"syntology":null},{"paper":null,"slug":"upscaling-global-hourly-gpp-with-temporal","title":"Upscaling Global Hourly GPP with Temporal Fusion Transformer (TFT)","date":"2023-06-23","arxiv_id":"2306.13815","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparison-of-time-based-models-for","title":"A Comparison of Time-based Models for Multimodal Emotion Recognition","date":"2023-06-22","arxiv_id":"2306.13076","n_code_links":0,"syntology":null},{"paper":"/paper/can-llms-express-their-uncertainty-an","slug":"can-llms-express-their-uncertainty-an","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","date":"2023-06-22","arxiv_id":"2306.13063","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["miaoxiong2320/llm-uncertainty"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-lingual-cross-temporal-summarization","slug":"cross-lingual-cross-temporal-summarization","title":"Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation","date":"2023-06-22","arxiv_id":"2306.12916","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-metric-learning-with-soft-orthogonal","title":"Deep Metric Learning with Soft Orthogonal Proxies","date":"2023-06-22","arxiv_id":"2306.13055","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-visual-observation-via-offline-1","title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","date":"2023-06-22","arxiv_id":"2306.12860","n_code_links":0,"syntology":null},{"paper":"/paper/minimalist-and-high-quality-panoramic-imaging","slug":"minimalist-and-high-quality-panoramic-imaging","title":"Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers","date":"2023-06-22","arxiv_id":"2306.12992","n_code_links":1,"syntology":null},{"paper":"/paper/visual-adversarial-examples-jailbreak-large","slug":"visual-adversarial-examples-jailbreak-large","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","date":"2023-06-22","arxiv_id":"2306.13213","n_code_links":1,"syntology":null},{"paper":"/paper/aries-a-corpus-of-scientific-paper-edits-made","slug":"aries-a-corpus-of-scientific-paper-edits-made","title":"ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews","date":"2023-06-21","arxiv_id":"2306.12587","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["allenai/aries"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-language-networks-joint-prompt-training","slug":"deep-language-networks-joint-prompt-training","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","date":"2023-06-21","arxiv_id":"2306.12509","n_code_links":1,"syntology":{"ran":3,"of":19,"n_ran_checked":0,"n_instrument":3,"unverified":16,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 16 unverified","official":{"repos":["microsoft/deep-language-networks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":16,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-segment-anything","slug":"fast-segment-anything","title":"Fast Segment Anything","date":"2023-06-21","arxiv_id":"2306.12156","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-based-models-meet-simulation-how-to","title":"GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Tasks","date":"2023-06-21","arxiv_id":"2306.13679","n_code_links":0,"syntology":null},{"paper":null,"slug":"hsr-diff-hyperspectral-image-super-resolution","title":"HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion Models","date":"2023-06-21","arxiv_id":"2306.12085","n_code_links":0,"syntology":null},{"paper":"/paper/inter-instance-similarity-modeling-for","slug":"inter-instance-similarity-modeling-for","title":"Inter-Instance Similarity Modeling for Contrastive Learning","date":"2023-06-21","arxiv_id":"2306.12243","n_code_links":1,"syntology":null},{"paper":null,"slug":"msw-transformer-multi-scale-shifted-windows","title":"MSW-Transformer: Multi-Scale Shifted Windows Transformer Networks for 12-Lead ECG Classification","date":"2023-06-21","arxiv_id":"2306.12098","n_code_links":0,"syntology":null},{"paper":"/paper/neural-multigrid-memory-for-computational","slug":"neural-multigrid-memory-for-computational","title":"Neural Multigrid Memory For Computational Fluid Dynamics","date":"2023-06-21","arxiv_id":"2306.12545","n_code_links":1,"syntology":null},{"paper":null,"slug":"probing-the-limit-of-hydrologic","title":"Probing the limit of hydrologic predictability with the Transformer network","date":"2023-06-21","arxiv_id":"2306.12384","n_code_links":0,"syntology":null},{"paper":"/paper/starvqa-co-training-space-time-attention-for","slug":"starvqa-co-training-space-time-attention-for","title":"StarVQA+: Co-training Space-Time Attention for Video Quality Assessment","date":"2023-06-21","arxiv_id":"2306.12298","n_code_links":1,"syntology":null},{"paper":"/paper/what-constitutes-good-contrastive-learning-in","slug":"what-constitutes-good-contrastive-learning-in","title":"What Constitutes Good Contrastive Learning in Time-Series Forecasting?","date":"2023-06-21","arxiv_id":"2306.12086","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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chiyuzhang94/contrastive_learning_time-series_e2e"],"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/augmenting-sub-model-to-improve-main-model","slug":"augmenting-sub-model-to-improve-main-model","title":"Masking meets Supervision: A Strong Learning Alliance","date":"2023-06-20","arxiv_id":"2306.11339","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparing-deep-learning-models-for-volatility","title":"Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Data","date":"2023-06-20","arxiv_id":"2306.12446","n_code_links":0,"syntology":null},{"paper":null,"slug":"decodingtrust-a-comprehensive-assessment-of","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","date":"2023-06-20","arxiv_id":"2306.11698","n_code_links":0,"syntology":null},{"paper":null,"slug":"democratizing-llms-for-low-resource-languages","title":"Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts","date":"2023-06-20","arxiv_id":"2306.11372","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-4-reticular-chemist-for-mof-discovery","slug":"gpt-4-reticular-chemist-for-mof-discovery","title":"A GPT-4 Reticular Chemist for Guiding MOF Discovery","date":"2023-06-20","arxiv_id":"2306.14915","n_code_links":1,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-adversarial-prompting","title":"Harnessing the Power of Adversarial Prompting and Large Language Models for Robust Hypothesis Generation in Astronomy","date":"2023-06-20","arxiv_id":"2306.11648","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-generate-better-than-your-llm","slug":"learning-to-generate-better-than-your-llm","title":"Learning to Generate Better Than Your LLM","date":"2023-06-20","arxiv_id":"2306.11816","n_code_links":1,"syntology":null},{"paper":null,"slug":"multiverse-transformer-1st-place-solution-for","title":"Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023","date":"2023-06-20","arxiv_id":"2306.11868","n_code_links":0,"syntology":null},{"paper":null,"slug":"rm-prt-realistic-robotic-manipulation","title":"Surfer: Progressive Reasoning with World Models for Robotic Manipulation","date":"2023-06-20","arxiv_id":"2306.11335","n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-graphs-for-enhanced-attribute","title":"Transforming Graphs for Enhanced Attribute Clustering: An Innovative Graph Transformer-Based Method","date":"2023-06-20","arxiv_id":"2306.11307","n_code_links":0,"syntology":null},{"paper":null,"slug":"unfolding-framework-with-prior-of-convolution","title":"Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging","date":"2023-06-20","arxiv_id":"2306.11316","n_code_links":0,"syntology":null},{"paper":"/paper/amrs-assemble-learning-to-ensemble-with","slug":"amrs-assemble-learning-to-ensemble-with","title":"AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing","date":"2023-06-19","arxiv_id":"2306.10786","n_code_links":1,"syntology":null},{"paper":"/paper/bayling-bridging-cross-lingual-alignment-and","slug":"bayling-bridging-cross-lingual-alignment-and","title":"BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models","date":"2023-06-19","arxiv_id":"2306.10968","n_code_links":1,"syntology":null},{"paper":"/paper/multi-task-learning-for-radar-signal","slug":"multi-task-learning-for-radar-signal","title":"Multi-task Learning for Radar Signal Characterisation","date":"2023-06-19","arxiv_id":"2306.13105","n_code_links":1,"syntology":null},{"paper":null,"slug":"multitrack-music-transcription-with-a-time","title":"Multitrack Music Transcription with a Time-Frequency Perceiver","date":"2023-06-19","arxiv_id":"2306.10785","n_code_links":0,"syntology":null},{"paper":"/paper/nar-former-v2-rethinking-transformer-for-1","slug":"nar-former-v2-rethinking-transformer-for-1","title":"NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning","date":"2023-06-19","arxiv_id":"2306.10792","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["yuny220/NAR-Former-V2"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}}],"record_sha256":"c95d71aaf35e1583d024c26cd5d3989814e0e6020181c0d10082cc9eaa0e9a5d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}