{"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/117","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":117,"pages_in_order":249,"rows_per_page":100,"rows":[11601,11700],"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/116","next":"/method/multi-head-attention/papers/118","papers":[{"paper":null,"slug":"debcse-rethinking-unsupervised-contrastive","title":"DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective","date":"2023-09-14","arxiv_id":"2309.07396","n_code_links":0,"syntology":null},{"paper":null,"slug":"echotune-a-modular-extractor-leveraging-the","title":"Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks","date":"2023-09-14","arxiv_id":"2309.07765","n_code_links":0,"syntology":null},{"paper":"/paper/encodecmae-leveraging-neural-codecs-for","slug":"encodecmae-leveraging-neural-codecs-for","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","date":"2023-09-14","arxiv_id":"2309.07391","n_code_links":2,"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":["habla-liaa/encodecmae"],"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":"folding-attention-memory-and-power","title":"Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition","date":"2023-09-14","arxiv_id":"2309.07988","n_code_links":0,"syntology":null},{"paper":"/paper/higt-hierarchical-interaction-graph","slug":"higt-hierarchical-interaction-graph","title":"HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis","date":"2023-09-14","arxiv_id":"2309.07400","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"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) · 2 unverified","official":{"repos":["hku-medai/higt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"language-embedded-radiance-fields-for-zero","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","date":"2023-09-14","arxiv_id":"2309.07970","n_code_links":0,"syntology":null},{"paper":"/paper/learning-quasi-static-3d-models-of-markerless","slug":"learning-quasi-static-3d-models-of-markerless","title":"Learning Quasi-Static 3D Models of Markerless Deformable Linear Objects for Bimanual Robotic Manipulation","date":"2023-09-14","arxiv_id":"2309.07609","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-classification-of-cancer-clinical-trial","title":"Text Classification of Cancer Clinical Trial Eligibility Criteria","date":"2023-09-14","arxiv_id":"2309.07812","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-timin-repairing-smart-contracts-with-a","title":"Two Timin': Repairing Smart Contracts With A Two-Layered Approach","date":"2023-09-14","arxiv_id":"2309.07841","n_code_links":0,"syntology":null},{"paper":"/paper/virchow-a-million-slide-digital-pathology","slug":"virchow-a-million-slide-digital-pathology","title":"Virchow: A Million-Slide Digital Pathology Foundation Model","date":"2023-09-14","arxiv_id":"2309.07778","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"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) · 0 unverified","official":{"repos":["Paige-AI/paige-ml-sdk"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/aggregating-long-term-sharp-features-via","slug":"aggregating-long-term-sharp-features-via","title":"Aggregating Nearest Sharp Features via Hybrid Transformers for Video Deblurring","date":"2023-09-13","arxiv_id":"2309.07054","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-procedural-language","slug":"benchmarking-procedural-language","title":"Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish","date":"2023-09-13","arxiv_id":"2309.06698","n_code_links":1,"syntology":null},{"paper":"/paper/ccspnet-joint-efficient-joint-training-method","slug":"ccspnet-joint-efficient-joint-training-method","title":"CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions","date":"2023-09-13","arxiv_id":"2309.06902","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-keyphrase-generation-by-bart","title":"Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shuffling","date":"2023-09-13","arxiv_id":"2309.06726","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai","title":"Generative AI","date":"2023-09-13","arxiv_id":"2309.07930","n_code_links":0,"syntology":null},{"paper":"/paper/in-contextual-bias-suppression-for-large","slug":"in-contextual-bias-suppression-for-large","title":"In-Contextual Gender Bias Suppression for Large Language Models","date":"2023-09-13","arxiv_id":"2309.07251","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-can-infer-psychological","title":"Large Language Models Can Infer Psychological Dispositions of Social Media Users","date":"2023-09-13","arxiv_id":"2309.08631","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-network-based-coronary-dominance","title":"Neural network-based coronary dominance classification of RCA angiograms","date":"2023-09-13","arxiv_id":"2309.06958","n_code_links":0,"syntology":null},{"paper":"/paper/rain-your-language-models-can-align","slug":"rain-your-language-models-can-align","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","date":"2023-09-13","arxiv_id":"2309.07124","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SafeAILab/RAIN"],"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":"/paper/safetybench-evaluating-the-safety-of-large","slug":"safetybench-evaluating-the-safety-of-large","title":"SafetyBench: Evaluating the Safety of Large Language Models","date":"2023-09-13","arxiv_id":"2309.07045","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thu-coai/safetybench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/shadocformer-a-shadow-attentive-threshold","slug":"shadocformer-a-shadow-attentive-threshold","title":"ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal","date":"2023-09-13","arxiv_id":"2309.06670","n_code_links":1,"syntology":null},{"paper":"/paper/sudden-drops-in-the-loss-syntax-acquisition","slug":"sudden-drops-in-the-loss-syntax-acquisition","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","date":"2023-09-13","arxiv_id":"2309.07311","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":8,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["angie-chen55/sudden-drops-in-the-loss"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/traveling-words-a-geometric-interpretation-of","slug":"traveling-words-a-geometric-interpretation-of","title":"Traveling Words: A Geometric Interpretation of Transformers","date":"2023-09-13","arxiv_id":"2309.07315","n_code_links":1,"syntology":null},{"paper":"/paper/2309-05951","slug":"2309-05951","title":"Balanced and Explainable Social Media Analysis for Public Health with Large Language Models","date":"2023-09-12","arxiv_id":"2309.05951","n_code_links":1,"syntology":null},{"paper":null,"slug":"2309-05968","title":"Neural Network Layer Matrix Decomposition reveals Latent Manifold Encoding and Memory Capacity","date":"2023-09-12","arxiv_id":"2309.05968","n_code_links":0,"syntology":null},{"paper":"/paper/2309-05973","slug":"2309-05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","date":"2023-09-12","arxiv_id":"2309.05973","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["xanderdavies/circuit-breaking"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2309-06057","title":"RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair","date":"2023-09-12","arxiv_id":"2309.06057","n_code_links":0,"syntology":null},{"paper":"/paper/2309-06085","slug":"2309-06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","date":"2023-09-12","arxiv_id":"2309.06085","n_code_links":3,"syntology":null},{"paper":null,"slug":"2309-06112","title":"Characterizing Latent Perspectives of Media Houses Towards Public Figures","date":"2023-09-12","arxiv_id":"2309.06112","n_code_links":0,"syntology":null},{"paper":"/paper/2309-06212","slug":"2309-06212","title":"Long-term drought prediction using deep neural networks based on geospatial weather data","date":"2023-09-12","arxiv_id":"2309.06212","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-3m-hybrid-model-for-the-restoration-of","title":"A 3M-Hybrid Model for the Restoration of Unique Giant Murals: A Case Study on the Murals of Yongle Palace","date":"2023-09-12","arxiv_id":"2309.06194","n_code_links":0,"syntology":null},{"paper":"/paper/act-empowering-decision-transformer-with","slug":"act-empowering-decision-transformer-with","title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning","date":"2023-09-12","arxiv_id":"2309.05915","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":["lamda-rl/act"],"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":"automatically-estimating-the-effort-required","title":"PRESTI: Predicting Repayment Effort of Self-Admitted Technical Debt Using Textual Information","date":"2023-09-12","arxiv_id":"2309.06020","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-llama-2-and-gpt-3-llms-for-hpc","title":"Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation","date":"2023-09-12","arxiv_id":"2309.07103","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-large-language-models-for-ontology","slug":"exploring-large-language-models-for-ontology","title":"Exploring Large Language Models for Ontology Alignment","date":"2023-09-12","arxiv_id":"2309.07172","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-the-benefits-of-differentially","slug":"exploring-the-benefits-of-differentially","title":"Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers","date":"2023-09-12","arxiv_id":"2309.06526","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-aggregation-network-for-building","title":"Feature Aggregation Network for Building Extraction from High-resolution Remote Sensing Images","date":"2023-09-12","arxiv_id":"2309.06017","n_code_links":0,"syntology":null},{"paper":null,"slug":"fldnet-a-foreground-aware-network-for-polyp","title":"FLDNet: A Foreground-Aware Network for Polyp Segmentation Leveraging Long-Distance Dependencies","date":"2023-09-12","arxiv_id":"2309.05987","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-multi-task-learning-framework-1","title":"Hierarchical Multi-Task Learning Framework for Session-based Recommendations","date":"2023-09-12","arxiv_id":"2309.06533","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-representation-impact-in-context","title":"Breaking through the learning plateaus of in-context learning in Transformer","date":"2023-09-12","arxiv_id":"2309.06054","n_code_links":0,"syntology":null},{"paper":null,"slug":"ibaformer-intra-batch-attention-transformer","title":"IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation","date":"2023-09-12","arxiv_id":"2309.06282","n_code_links":0,"syntology":null},{"paper":null,"slug":"jersey-number-recognition-using-keyframe","title":"Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos","date":"2023-09-12","arxiv_id":"2309.06285","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-and-weak","title":"Leveraging Large Language Models and Weak Supervision for Social Media data annotation: an evaluation using COVID-19 self-reported vaccination tweets","date":"2023-09-12","arxiv_id":"2309.06503","n_code_links":0,"syntology":null},{"paper":null,"slug":"overview-of-memotion-3-sentiment-and-emotion","title":"Overview of Memotion 3: Sentiment and Emotion Analysis of Codemixed Hinglish Memes","date":"2023-09-12","arxiv_id":"2309.06517","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategic-behavior-of-large-language-models","title":"Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing","date":"2023-09-12","arxiv_id":"2309.05898","n_code_links":0,"syntology":null},{"paper":"/paper/the-moral-machine-experiment-on-large","slug":"the-moral-machine-experiment-on-large","title":"The Moral Machine Experiment on Large Language Models","date":"2023-09-12","arxiv_id":"2309.05958","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-the-potential-of-large-language","title":"Unveiling the potential of large language models in generating semantic and cross-language clones","date":"2023-09-12","arxiv_id":"2309.06424","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-netops-capability-of","title":"An Empirical Study of NetOps Capability of Pre-Trained Large Language Models","date":"2023-09-11","arxiv_id":"2309.05557","n_code_links":0,"syntology":null},{"paper":"/paper/applying-biobert-to-extract-germline-gene","slug":"applying-biobert-to-extract-germline-gene","title":"Applying BioBERT to Extract Germline Gene-Disease Associations for Building a Knowledge Graph from the Biomedical Literature","date":"2023-09-11","arxiv_id":"2309.13061","n_code_links":1,"syntology":null},{"paper":null,"slug":"black-box-analysis-gpts-across-time-in-legal","title":"Black-Box Analysis: GPTs Across Time in Legal Textual Entailment Task","date":"2023-09-11","arxiv_id":"2309.05501","n_code_links":0,"syntology":null},{"paper":"/paper/circle-feature-graphormer-can-circle-features","slug":"circle-feature-graphormer-can-circle-features","title":"Circle Feature Graphormer: Can Circle Features Stimulate Graph Transformer?","date":"2023-09-11","arxiv_id":"2309.06574","n_code_links":1,"syntology":null},{"paper":"/paper/cnn-or-vit-revisiting-vision-transformers","slug":"cnn-or-vit-revisiting-vision-transformers","title":"Toward a Deeper Understanding: RetNet Viewed through Convolution","date":"2023-09-11","arxiv_id":"2309.05375","n_code_links":1,"syntology":null},{"paper":null,"slug":"crisistransformers-pre-trained-language","title":"CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts","date":"2023-09-11","arxiv_id":"2309.05494","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-natural-language-biases-with-prompt","title":"Detecting Natural Language Biases with Prompt-based Learning","date":"2023-09-11","arxiv_id":"2309.05227","n_code_links":0,"syntology":null},{"paper":"/paper/hat-hybrid-attention-transformer-for-image","slug":"hat-hybrid-attention-transformer-for-image","title":"HAT: Hybrid Attention Transformer for Image Restoration","date":"2023-09-11","arxiv_id":"2309.05239","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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) · 0 unverified","official":{"repos":["xpixelgroup/hat"],"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/large-language-model-for-science-a-study-on-p","slug":"large-language-model-for-science-a-study-on-p","title":"Large Language Model for Science: A Study on P vs. NP","date":"2023-09-11","arxiv_id":"2309.05689","n_code_links":1,"syntology":null},{"paper":"/paper/long-range-transformer-architectures-for","slug":"long-range-transformer-architectures-for","title":"Long-Range Transformer Architectures for Document Understanding","date":"2023-09-11","arxiv_id":"2309.05503","n_code_links":1,"syntology":null},{"paper":"/paper/memory-injections-correcting-multi-hop","slug":"memory-injections-correcting-multi-hop","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","date":"2023-09-11","arxiv_id":"2309.05605","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["msakarvadia/memory_injections"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/restoring-snow-degraded-single-images-with","slug":"restoring-snow-degraded-single-images-with","title":"Restoring Snow-Degraded Single Images With Wavelet in Vision Transformer","date":"2023-09-11","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/sparseswin-swin-transformer-with-sparse","slug":"sparseswin-swin-transformer-with-sparse","title":"SparseSwin: Swin Transformer with Sparse Transformer Block","date":"2023-09-11","arxiv_id":"2309.05224","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-learning-with-minimum-instruction","title":"Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model","date":"2023-09-11","arxiv_id":"2309.05475","n_code_links":0,"syntology":null},{"paper":null,"slug":"devit-decomposing-vision-transformers-for","title":"DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices","date":"2023-09-10","arxiv_id":"2309.05015","n_code_links":0,"syntology":null},{"paper":null,"slug":"implementing-learning-principles-with-a","title":"Implementing Learning Principles with a Personal AI Tutor: A Case Study","date":"2023-09-10","arxiv_id":"2309.13060","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-personalized-user-preference-from","title":"Learning Personalized User Preference from Cold Start in Multi-turn Conversations","date":"2023-09-10","arxiv_id":"2309.05127","n_code_links":0,"syntology":null},{"paper":"/paper/neural-hidden-crf-a-robust-weakly-supervised","slug":"neural-hidden-crf-a-robust-weakly-supervised","title":"Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler","date":"2023-09-10","arxiv_id":"2309.05086","n_code_links":1,"syntology":null},{"paper":null,"slug":"rgat-a-deeper-look-into-syntactic-dependency","title":"RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution","date":"2023-09-10","arxiv_id":"2309.04977","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-contrastive-fusion-transformer-for","title":"Unified Contrastive Fusion Transformer for Multimodal Human Action Recognition","date":"2023-09-10","arxiv_id":"2309.05032","n_code_links":0,"syntology":null},{"paper":null,"slug":"denoising-mot-towards-multiple-object","title":"DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions","date":"2023-09-09","arxiv_id":"2309.04682","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-finetuning-large-language-models","title":"Efficient Finetuning Large Language Models For Vietnamese Chatbot","date":"2023-09-09","arxiv_id":"2309.04646","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-medical-image-segmentation-via-a","slug":"few-shot-medical-image-segmentation-via-a","title":"Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer","date":"2023-09-09","arxiv_id":"2309.04825","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-to-evaluate-semantic-communications-for","title":"How to Evaluate Semantic Communications for Images with ViTScore Metric?","date":"2023-09-09","arxiv_id":"2309.04891","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-transformer-with-domain","title":"Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection","date":"2023-09-09","arxiv_id":"2309.04795","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-deep-learning-detector-for","title":"Transformer-Based Deep Learning Detector for Dual-Mode Index Modulation 3D-OFDM","date":"2023-09-09","arxiv_id":"2309.04764","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-nlp-models-identify-distinguish-and","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","date":"2023-09-08","arxiv_id":"2309.04635","n_code_links":0,"syntology":null},{"paper":"/paper/cnn-injected-transformer-for-image-exposure","slug":"cnn-injected-transformer-for-image-exposure","title":"CNN Injected Transformer for Image Exposure Correction","date":"2023-09-08","arxiv_id":"2309.04366","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-aware-prompt-tuning-for-vision","title":"Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment","date":"2023-09-08","arxiv_id":"2309.04158","n_code_links":0,"syntology":null},{"paper":null,"slug":"curve-your-attention-mixed-curvature","title":"Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning","date":"2023-09-08","arxiv_id":"2309.04082","n_code_links":0,"syntology":null},{"paper":"/paper/encoding-multi-domain-scientific-papers-by","slug":"encoding-multi-domain-scientific-papers-by","title":"Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens","date":"2023-09-08","arxiv_id":"2309.04333","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["ronaldseoh/multi2spe"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/fimo-a-challenge-formal-dataset-for-automated","slug":"fimo-a-challenge-formal-dataset-for-automated","title":"FIMO: A Challenge Formal Dataset for Automated Theorem Proving","date":"2023-09-08","arxiv_id":"2309.04295","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-sparse-to-dense-gpt-4-summarization-with","title":"From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting","date":"2023-09-08","arxiv_id":"2309.04269","n_code_links":0,"syntology":null},{"paper":"/paper/fuzzy-fingerprinting-transformer-language","slug":"fuzzy-fingerprinting-transformer-language","title":"Fuzzy Fingerprinting Transformer Language-Models for Emotion Recognition in Conversations","date":"2023-09-08","arxiv_id":"2309.04292","n_code_links":0,"syntology":null},{"paper":"/paper/language-prompt-for-autonomous-driving","slug":"language-prompt-for-autonomous-driving","title":"Language Prompt for Autonomous Driving","date":"2023-09-08","arxiv_id":"2309.04379","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"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":["wudongming97/prompt4driving"],"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","unlocated"]}}},{"paper":null,"slug":"leveraging-pretrained-image-text-models-for","title":"Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning","date":"2023-09-08","arxiv_id":"2309.04628","n_code_links":0,"syntology":null},{"paper":"/paper/nestle-a-no-code-tool-for-statistical","slug":"nestle-a-no-code-tool-for-statistical","title":"NESTLE: a No-Code Tool for Statistical Analysis of Legal Corpus","date":"2023-09-08","arxiv_id":"2309.04146","n_code_links":1,"syntology":null},{"paper":"/paper/uq-at-smm4h-2023-alex-for-public-health","slug":"uq-at-smm4h-2023-alex-for-public-health","title":"UQ at #SMM4H 2023: ALEX for Public Health Analysis with Social Media","date":"2023-09-08","arxiv_id":"2309.04213","n_code_links":1,"syntology":null},{"paper":null,"slug":"adapting-self-supervised-representations-to","title":"Adapting Self-Supervised Representations to Multi-Domain Setups","date":"2023-09-07","arxiv_id":"2309.03999","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-pipeline-based-conversational","title":"Enhancing Pipeline-Based Conversational Agents with Large Language Models","date":"2023-09-07","arxiv_id":"2309.03748","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-chatgpt-as-a-recommender-system-a","slug":"evaluating-chatgpt-as-a-recommender-system-a","title":"Evaluating ChatGPT as a Recommender System: A Rigorous Approach","date":"2023-09-07","arxiv_id":"2309.03613","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-efficacy-of-supervised","slug":"evaluating-the-efficacy-of-supervised","title":"Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media","date":"2023-09-07","arxiv_id":"2309.03564","n_code_links":2,"syntology":null},{"paper":"/paper/evaluation-of-large-language-models-for","slug":"evaluation-of-large-language-models-for","title":"Evaluation of large language models for discovery of gene set function","date":"2023-09-07","arxiv_id":"2309.04019","n_code_links":1,"syntology":null},{"paper":null,"slug":"flm-101b-an-open-llm-and-how-to-train-it-with","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","date":"2023-09-07","arxiv_id":"2309.03852","n_code_links":0,"syntology":null},{"paper":null,"slug":"ms-unet-v2-adaptive-denoising-method-and","title":"MS-UNet-v2: Adaptive Denoising Method and Training Strategy for Medical Image Segmentation with Small Training Data","date":"2023-09-07","arxiv_id":"2309.03686","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-transformer-for-material","slug":"multimodal-transformer-for-material","title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","date":"2023-09-07","arxiv_id":"2309.04001","n_code_links":1,"syntology":null},{"paper":"/paper/propainter-improving-propagation-and","slug":"propainter-improving-propagation-and","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","date":"2023-09-07","arxiv_id":"2309.03897","n_code_links":3,"syntology":{"ran":20,"of":34,"n_ran_checked":12,"n_instrument":8,"unverified":14,"pointer_only":16,"phrase":"20 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 14 unverified","official":{"repos":["sczhou/propainter"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/s-adapter-generalizing-vision-transformer-for","slug":"s-adapter-generalizing-vision-transformer-for","title":"S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens","date":"2023-09-07","arxiv_id":"2309.04038","n_code_links":3,"syntology":null},{"paper":"/paper/zero-shot-audio-captioning-via-audibility","slug":"zero-shot-audio-captioning-via-audibility","title":"Zero-Shot Audio Captioning via Audibility Guidance","date":"2023-09-07","arxiv_id":"2309.03884","n_code_links":0,"syntology":null},{"paper":"/paper/certifying-llm-safety-against-adversarial","slug":"certifying-llm-safety-against-adversarial","title":"Certifying LLM Safety against Adversarial Prompting","date":"2023-09-06","arxiv_id":"2309.02705","n_code_links":1,"syntology":null},{"paper":"/paper/character-queries-a-transformer-based","slug":"character-queries-a-transformer-based","title":"Character Queries: A Transformer-based Approach to On-Line Handwritten Character Segmentation","date":"2023-09-06","arxiv_id":"2309.03072","n_code_links":1,"syntology":null},{"paper":"/paper/gpt-can-solve-mathematical-problems-without-a","slug":"gpt-can-solve-mathematical-problems-without-a","title":"GPT Can Solve Mathematical Problems Without a Calculator","date":"2023-09-06","arxiv_id":"2309.03241","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thudm/mathglm"],"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":"/paper/hae-rae-bench-evaluation-of-korean-knowledge","slug":"hae-rae-bench-evaluation-of-korean-knowledge","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","date":"2023-09-06","arxiv_id":"2309.02706","n_code_links":1,"syntology":null}],"record_sha256":"62f81d977ca08e12e4e41a9ea4ac97c1263c366a9198dd6b9fca04ce1ca80340","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}