{"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/64","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":64,"pages_in_order":140,"rows_per_page":100,"rows":[6301,6400],"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/63","next":"/method/transformer/papers/65","papers":[{"paper":"/paper/chada-vit-channel-adaptive-attention-for","slug":"chada-vit-channel-adaptive-attention-for","title":"ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images","date":"2023-11-26","arxiv_id":"2311.15264","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nicoboou/chadavit","nicoboou/chada_vit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"spectro-vit-a-vision-transformer-model-for","title":"Spectro-ViT: A Vision Transformer Model for GABA-edited MRS Reconstruction Using Spectrograms","date":"2023-11-26","arxiv_id":"2311.15386","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-range-gesture-recognition-using-an-rgb","title":"Ultra-Range Gesture Recognition using a Web-Camera in Human-Robot Interaction","date":"2023-11-26","arxiv_id":"2311.15361","n_code_links":0,"syntology":null},{"paper":"/paper/autoeval-video-an-automatic-benchmark-for","slug":"autoeval-video-an-automatic-benchmark-for","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","date":"2023-11-25","arxiv_id":"2311.14906","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-text-to-image-exploring-gpt-4vision-s","title":"From Text to Image: Exploring GPT-4Vision's Potential in Advanced Radiological Analysis across Subspecialties","date":"2023-11-24","arxiv_id":"2311.14777","n_code_links":0,"syntology":null},{"paper":"/paper/llamol-a-dynamic-multi-conditional-generative","slug":"llamol-a-dynamic-multi-conditional-generative","title":"LLamol: A Dynamic Multi-Conditional Generative Transformer for De Novo Molecular Design","date":"2023-11-24","arxiv_id":"2311.14407","n_code_links":1,"syntology":null},{"paper":"/paper/one-fits-all-universal-time-series-analysis","slug":"one-fits-all-universal-time-series-analysis","title":"Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter View","date":"2023-11-24","arxiv_id":"2311.14782","n_code_links":1,"syntology":null},{"paper":null,"slug":"rsb-pose-robust-short-baseline-binocular-3d","title":"RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handling","date":"2023-11-24","arxiv_id":"2311.14242","n_code_links":0,"syntology":null},{"paper":null,"slug":"tvt-training-free-vision-transformer-search","title":"TVT: Training-Free Vision Transformer Search on Tiny Datasets","date":"2023-11-24","arxiv_id":"2311.14337","n_code_links":0,"syntology":null},{"paper":null,"slug":"auditing-and-mitigating-cultural-bias-in-llms","title":"Cultural Bias and Cultural Alignment of Large Language Models","date":"2023-11-23","arxiv_id":"2311.14096","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-gpt-4-s-vision-capabilities-on","slug":"evaluating-gpt-4-s-vision-capabilities-on","title":"Evaluating GPT-4's Vision Capabilities on Brazilian University Admission Exams","date":"2023-11-23","arxiv_id":"2311.14169","n_code_links":1,"syntology":null},{"paper":null,"slug":"fvit-grasp-grasping-objects-with-using-fast","title":"FViT-Grasp: Grasping Objects With Using Fast Vision Transformers","date":"2023-11-23","arxiv_id":"2311.13986","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-based-semantic","title":"Knowledge Distillation Based Semantic Communications For Multiple Users","date":"2023-11-23","arxiv_id":"2311.13789","n_code_links":0,"syntology":null},{"paper":"/paper/lacformer-toward-accurate-and-efficient-polyp","slug":"lacformer-toward-accurate-and-efficient-polyp","title":"LACFormer: Toward accurate and efficient polyp segmentation","date":"2023-11-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"progressive-learning-with-visual-prompt","title":"Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression","date":"2023-11-23","arxiv_id":"2311.13846","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-explainable-strategy-templates-using","title":"Towards Explainable Strategy Templates using NLP Transformers","date":"2023-11-23","arxiv_id":"2311.14061","n_code_links":0,"syntology":null},{"paper":null,"slug":"beat-aligned-spectrogram-to-sequence","title":"Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts","date":"2023-11-22","arxiv_id":"2311.13687","n_code_links":0,"syntology":null},{"paper":null,"slug":"benthiq-a-transformer-based-benthic","title":"BenthIQ: a Transformer-Based Benthic Classification Model for Coral Restoration","date":"2023-11-22","arxiv_id":"2311.13661","n_code_links":0,"syntology":null},{"paper":null,"slug":"bitformer-an-efficient-transformer-with","title":"Bitformer: An efficient Transformer with bitwise operation-based attention for Big Data Analytics at low-cost low-precision devices","date":"2023-11-22","arxiv_id":"2311.13502","n_code_links":0,"syntology":null},{"paper":null,"slug":"combatting-human-trafficking-in-the","title":"Combatting Human Trafficking in the Cyberspace: A Natural Language Processing-Based Methodology to Analyze the Language in Online Advertisements","date":"2023-11-22","arxiv_id":"2311.13118","n_code_links":0,"syntology":null},{"paper":"/paper/hevitpose-high-efficiency-vision-transformer","slug":"hevitpose-high-efficiency-vision-transformer","title":"HEViTPose: High-Efficiency Vision Transformer for Human Pose Estimation","date":"2023-11-22","arxiv_id":"2311.13615","n_code_links":1,"syntology":null},{"paper":"/paper/input-compression-with-positional-consistency","slug":"input-compression-with-positional-consistency","title":"Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neural Networks","date":"2023-11-22","arxiv_id":"2312.12385","n_code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-layout-transformer-for","slug":"retrieval-augmented-layout-transformer-for","title":"Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation","date":"2023-11-22","arxiv_id":"2311.13602","n_code_links":1,"syntology":null},{"paper":null,"slug":"surpassing-gpt-4-medical-coding-with-a-two","title":"Surpassing GPT-4 Medical Coding with a Two-Stage Approach","date":"2023-11-22","arxiv_id":"2311.13735","n_code_links":0,"syntology":null},{"paper":"/paper/towards-improving-document-understanding-an","slug":"towards-improving-document-understanding-an","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","date":"2023-11-22","arxiv_id":"2311.13194","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["harrytea/tgdoc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ve-a-chatbot-for-latin","title":"@ve: A Chatbot for Latin","date":"2023-11-22","arxiv_id":"2311.14741","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-transformer-architecture-in-long","slug":"advancing-transformer-architecture-in-long","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","date":"2023-11-21","arxiv_id":"2311.12351","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-large-multimodal-model-is-watching","title":"GeoLocator: a location-integrated large multimodal model for inferring geo-privacy","date":"2023-11-21","arxiv_id":"2311.13018","n_code_links":0,"syntology":null},{"paper":"/paper/audiolog-llms-powered-long-audio-logging-with","slug":"audiolog-llms-powered-long-audio-logging-with","title":"AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning","date":"2023-11-21","arxiv_id":"2311.12371","n_code_links":1,"syntology":null},{"paper":null,"slug":"causality-is-all-you-need","title":"Causality is all you need","date":"2023-11-21","arxiv_id":"2311.12307","n_code_links":0,"syntology":null},{"paper":"/paper/from-classification-to-clinical-insights","slug":"from-classification-to-clinical-insights","title":"From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models","date":"2023-11-21","arxiv_id":"2311.13063","n_code_links":1,"syntology":null},{"paper":"/paper/gaia-a-benchmark-for-general-ai-assistants","slug":"gaia-a-benchmark-for-general-ai-assistants","title":"GAIA: a benchmark for General AI Assistants","date":"2023-11-21","arxiv_id":"2311.12983","n_code_links":2,"syntology":null},{"paper":null,"slug":"gpt4motion-scripting-physical-motions-in-text","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","date":"2023-11-21","arxiv_id":"2311.12631","n_code_links":0,"syntology":null},{"paper":"/paper/hover-unet-accelerating-hovernet-with-unet","slug":"hover-unet-accelerating-hovernet-with-unet","title":"HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillation","date":"2023-11-21","arxiv_id":"2311.12553","n_code_links":1,"syntology":null},{"paper":"/paper/how-capable-can-a-transformer-become-a-study","slug":"how-capable-can-a-transformer-become-a-study","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","date":"2023-11-21","arxiv_id":"2311.12997","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":["rahul13ramesh/compositional_capabilities"],"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":"hpcneuronet-advancing-neuromorphic-audio","title":"HPCNeuroNet: Advancing Neuromorphic Audio Signal Processing with Transformer-Enhanced Spiking Neural Networks","date":"2023-11-21","arxiv_id":"2311.12449","n_code_links":0,"syntology":null},{"paper":null,"slug":"iekm-a-model-incorporating-external-keyword","title":"IEKM: A Model Incorporating External Keyword Matrices","date":"2023-11-21","arxiv_id":"2311.12310","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-source-free-target-adaptation-with","title":"Improving Source-Free Target Adaptation with Vision Transformers Leveraging Domain Representation Images","date":"2023-11-21","arxiv_id":"2311.12589","n_code_links":0,"syntology":null},{"paper":"/paper/interpretation-of-the-transformer-and","slug":"interpretation-of-the-transformer-and","title":"Interpretation of the Transformer and Improvement of the Extractor","date":"2023-11-21","arxiv_id":"2311.12678","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-compute-grobner-bases","slug":"learning-to-compute-grobner-bases","title":"Learning to Compute Gröbner Bases","date":"2023-11-21","arxiv_id":"2311.12904","n_code_links":2,"syntology":{"ran":12,"of":18,"n_ran_checked":12,"n_instrument":0,"unverified":6,"pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hiroshikera/transformer-groebner"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-to-optimise-wind-farms-with-graph","title":"Learning to Optimise Wind Farms with Graph Transformers","date":"2023-11-21","arxiv_id":"2311.12750","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-mil-scaling-long-contextual-multiple","title":"Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysis","date":"2023-11-21","arxiv_id":"2311.12885","n_code_links":0,"syntology":null},{"paper":"/paper/oasis-data-curation-and-assessment-system-for","slug":"oasis-data-curation-and-assessment-system-for","title":"Oasis: Data Curation and Assessment System for Pretraining of Large Language Models","date":"2023-11-21","arxiv_id":"2311.12537","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-transformer-based-approach-for-soil","title":"A novel transformer-based approach for soil temperature prediction","date":"2023-11-20","arxiv_id":"2311.11626","n_code_links":0,"syntology":null},{"paper":null,"slug":"correlated-attention-in-transformers-for","title":"Correlated Attention in Transformers for Multivariate Time Series","date":"2023-11-20","arxiv_id":"2311.11959","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoupled-detr-for-few-shot-object-detection","title":"Decoupled DETR For Few-shot Object Detection","date":"2023-11-20","arxiv_id":"2311.11570","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-structure-and-appearance-in-vit","title":"Disentangling Structure and Appearance in ViT Feature Space","date":"2023-11-20","arxiv_id":"2311.12193","n_code_links":0,"syntology":null},{"paper":"/paper/evil-geniuses-delving-into-the-safety-of-llm","slug":"evil-geniuses-delving-into-the-safety-of-llm","title":"Evil Geniuses: Delving into the Safety of LLM-based Agents","date":"2023-11-20","arxiv_id":"2311.11855","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"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":["t1ans1r/evil-geniuses"],"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":null,"slug":"generating-valid-and-natural-adversarial","title":"Generating Valid and Natural Adversarial Examples with Large Language Models","date":"2023-11-20","arxiv_id":"2311.11861","n_code_links":0,"syntology":null},{"paper":"/paper/gpqa-a-graduate-level-google-proof-q-a","slug":"gpqa-a-graduate-level-google-proof-q-a","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","date":"2023-11-20","arxiv_id":"2311.12022","n_code_links":3,"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":["idavidrein/gpqa"],"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/how-to-use-large-language-models-for-text","slug":"how-to-use-large-language-models-for-text","title":"Towards Human-Level Text Coding with LLMs: The Case of Fatherhood Roles in Public Policy Documents","date":"2023-11-20","arxiv_id":"2311.11844","n_code_links":1,"syntology":null},{"paper":"/paper/lidar-hmr-3d-human-mesh-recovery-from-lidar","slug":"lidar-hmr-3d-human-mesh-recovery-from-lidar","title":"LiDAR-HMR: 3D Human Mesh Recovery from LiDAR","date":"2023-11-20","arxiv_id":"2311.11971","n_code_links":2,"syntology":null},{"paper":"/paper/meta-prompting-for-agi-systems","slug":"meta-prompting-for-agi-systems","title":"Meta Prompting for AI Systems","date":"2023-11-20","arxiv_id":"2311.11482","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["meta-prompting/meta-prompting"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mgct-mutual-guided-cross-modality-transformer","slug":"mgct-mutual-guided-cross-modality-transformer","title":"MGCT: Mutual-Guided Cross-Modality Transformer for Survival Outcome Prediction using Integrative Histopathology-Genomic Features","date":"2023-11-20","arxiv_id":"2311.11659","n_code_links":1,"syntology":null},{"paper":null,"slug":"pmp-swin-multi-scale-patch-message-passing","title":"PMP-Swin: Multi-Scale Patch Message Passing Swin Transformer for Retinal Disease Classification","date":"2023-11-20","arxiv_id":"2311.11669","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-the-power-of-self-attention-for","slug":"unveiling-the-power-of-self-attention-for","title":"Unveiling the Power of Self-Attention for Shipping Cost Prediction: The Rate Card Transformer","date":"2023-11-20","arxiv_id":"2311.11694","n_code_links":1,"syntology":null},{"paper":"/paper/which-ai-technique-is-better-to-classify","slug":"which-ai-technique-is-better-to-classify","title":"Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT","date":"2023-11-20","arxiv_id":"2311.11547","n_code_links":1,"syntology":null},{"paper":null,"slug":"inspecting-explainability-of-transformer","title":"Inspecting Explainability of Transformer Models with Additional Statistical Information","date":"2023-11-19","arxiv_id":"2311.11378","n_code_links":0,"syntology":null},{"paper":null,"slug":"behavior-optimized-image-generation","title":"Behavior Optimized Image Generation","date":"2023-11-18","arxiv_id":"2311.10995","n_code_links":0,"syntology":null},{"paper":null,"slug":"partially-randomizing-transformer-weights-for","title":"Partially Randomizing Transformer Weights for Dialogue Response Diversity","date":"2023-11-18","arxiv_id":"2311.10943","n_code_links":0,"syntology":null},{"paper":"/paper/structure-aware-sparse-view-x-ray-3d","slug":"structure-aware-sparse-view-x-ray-3d","title":"Structure-Aware Sparse-View X-ray 3D Reconstruction","date":"2023-11-18","arxiv_id":"2311.10959","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"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":["caiyuanhao1998/sax-nerf"],"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","unlocated"]}}},{"paper":null,"slug":"visual-ai-and-linguistic-intelligence-through","title":"Visual AI and Linguistic Intelligence Through Steerability and Composability","date":"2023-11-18","arxiv_id":"2312.12383","n_code_links":0,"syntology":null},{"paper":null,"slug":"bias-a-head-analyzing-bias-in-transformer","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","date":"2023-11-17","arxiv_id":"2311.10395","n_code_links":0,"syntology":null},{"paper":null,"slug":"eduquick-a-dataset-toward-evaluating","title":"EduQuick: A Dataset Toward Evaluating Summarization of Informal Educational Content for Social Media","date":"2023-11-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-entity-video-transformers-for-fine","slug":"multi-entity-video-transformers-for-fine","title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","date":"2023-11-17","arxiv_id":"2311.10873","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-attention-exploring-shallow-feed","title":"Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers","date":"2023-11-17","arxiv_id":"2311.10642","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-vit-knowledge-distillation","title":"Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction","date":"2023-11-17","arxiv_id":"2311.10305","n_code_links":0,"syntology":null},{"paper":"/paper/taco-enhancing-cross-lingual-transfer-for-low","slug":"taco-enhancing-cross-lingual-transfer-for-low","title":"TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes","date":"2023-11-17","arxiv_id":"2311.10797","n_code_links":1,"syntology":null},{"paper":"/paper/blt-can-large-language-models-handle-basic","slug":"blt-can-large-language-models-handle-basic","title":"BLT: Can Large Language Models Handle Basic Legal Text?","date":"2023-11-16","arxiv_id":"2311.09693","n_code_links":1,"syntology":null},{"paper":null,"slug":"enchancing-semi-supervised-learning-for","title":"Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization","date":"2023-11-16","arxiv_id":"2311.09559","n_code_links":0,"syntology":null},{"paper":"/paper/gee-grammar-error-explanation-with-large","slug":"gee-grammar-error-explanation-with-large","title":"GEE! Grammar Error Explanation with Large Language Models","date":"2023-11-16","arxiv_id":"2311.09517","n_code_links":1,"syntology":null},{"paper":"/paper/huatuogpt-ii-one-stage-training-for-medical","slug":"huatuogpt-ii-one-stage-training-for-medical","title":"HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs","date":"2023-11-16","arxiv_id":"2311.09774","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":11,"n_instrument":2,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["freedomintelligence/huatuogpt-ii"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"human-still-wins-over-llm-an-empirical-study","title":"Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks","date":"2023-11-16","arxiv_id":"2311.09825","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-data-contamination-in-modern","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","date":"2023-11-16","arxiv_id":"2311.09783","n_code_links":0,"syntology":null},{"paper":"/paper/knowledgemath-knowledge-intensive-math-word","slug":"knowledgemath-knowledge-intensive-math-word","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains","date":"2023-11-16","arxiv_id":"2311.09797","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":12,"n_instrument":0,"unverified":3,"pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["yale-nlp/knowledgemath"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-for-propaganda-span","slug":"large-language-models-for-propaganda-span","title":"Large Language Models for Propaganda Span Annotation","date":"2023-11-16","arxiv_id":"2311.09812","n_code_links":1,"syntology":null},{"paper":null,"slug":"marformer-an-efficient-metal-artifact","title":"MARformer: An Efficient Metal Artifact Reduction Transformer for Dental CBCT Images","date":"2023-11-16","arxiv_id":"2311.09590","n_code_links":0,"syntology":null},{"paper":"/paper/ml-bench-large-language-models-leverage-open","slug":"ml-bench-large-language-models-leverage-open","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","date":"2023-11-16","arxiv_id":"2311.09835","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gersteinlab/ml-bench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-view-spectrogram-transformer-for","slug":"multi-view-spectrogram-transformer-for","title":"Multi-View Spectrogram Transformer for Respiratory Sound Classification","date":"2023-11-16","arxiv_id":"2311.09655","n_code_links":1,"syntology":null},{"paper":"/paper/neural-logic-human-object-interaction","slug":"neural-logic-human-object-interaction","title":"Neural-Logic Human-Object Interaction Detection","date":"2023-11-16","arxiv_id":"2311.09817","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":null}},{"paper":null,"slug":"on-evaluating-the-integration-of-reasoning","title":"On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering","date":"2023-11-16","arxiv_id":"2311.09721","n_code_links":0,"syntology":null},{"paper":null,"slug":"psybench-a-balanced-and-in-depth","title":"ConceptPsy:A Benchmark Suite with Conceptual Comprehensiveness in Psychology","date":"2023-11-16","arxiv_id":"2311.09861","n_code_links":0,"syntology":null},{"paper":"/paper/score-a-framework-for-self-contradictory","slug":"score-a-framework-for-self-contradictory","title":"Self-Contradictory Reasoning Evaluation and Detection","date":"2023-11-16","arxiv_id":"2311.09603","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["uscnlp-lime/Self-Contradictory"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/structured-chemistry-reasoning-with-large","slug":"structured-chemistry-reasoning-with-large","title":"Structured Chemistry Reasoning with Large Language Models","date":"2023-11-16","arxiv_id":"2311.09656","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ozyyshr/structchem"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/survtimesurvival-survival-analysis-on-the","slug":"survtimesurvival-survival-analysis-on-the","title":"SurvTimeSurvival: Survival Analysis On The Patient With Multiple Visits/Records","date":"2023-11-16","arxiv_id":"2311.09854","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-autonomous-hypothesis-verification","title":"Towards Autonomous Hypothesis Verification via Language Models with Minimal Guidance","date":"2023-11-16","arxiv_id":"2311.09706","n_code_links":0,"syntology":null},{"paper":"/paper/unifiedvisiongpt-streamlining-vision-oriented","slug":"unifiedvisiongpt-streamlining-vision-oriented","title":"UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework","date":"2023-11-16","arxiv_id":"2311.10125","n_code_links":1,"syntology":null},{"paper":"/paper/wildfire-smoke-detection-with-cross-contrast","slug":"wildfire-smoke-detection-with-cross-contrast","title":"Wildfire Smoke Detection with Cross Contrast Patch Embedding","date":"2023-11-16","arxiv_id":"2311.10116","n_code_links":1,"syntology":null},{"paper":"/paper/can-large-language-models-follow-concept","slug":"can-large-language-models-follow-concept","title":"Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains","date":"2023-11-15","arxiv_id":"2311.08704","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparing-generalization-in-learning-with","title":"Comparing Generalization in Learning with Limited Numbers of Exemplars: Transformer vs. RNN in Attractor Dynamics","date":"2023-11-15","arxiv_id":"2311.10763","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-transformer-learning-with","slug":"contrastive-transformer-learning-with","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","date":"2023-11-15","arxiv_id":"2311.09084","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":5,"n_instrument":2,"unverified":0,"pointer_only":7,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hcplab-sysu/personsearch-ctlg"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-group-interest-modeling-of-full-lifelong","title":"Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction","date":"2023-11-15","arxiv_id":"2311.10764","n_code_links":0,"syntology":null},{"paper":"/paper/degradation-estimation-recurrent-neural","slug":"degradation-estimation-recurrent-neural","title":"Degradation Estimation Recurrent Neural Network with Local and Non-Local Priors for Compressive Spectral Imaging","date":"2023-11-15","arxiv_id":"2311.08808","n_code_links":1,"syntology":null},{"paper":null,"slug":"dista-denoising-spiking-transformer-with","title":"DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention","date":"2023-11-15","arxiv_id":"2311.09376","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-machine-translation-through","title":"Enhancing Machine Translation through Advanced In-Context Learning: A Methodological Strategy for GPT-4 Improvement","date":"2023-11-15","arxiv_id":"2311.10765","n_code_links":0,"syntology":null},{"paper":"/paper/factcheck-gpt-end-to-end-fine-grained","slug":"factcheck-gpt-end-to-end-fine-grained","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","date":"2023-11-15","arxiv_id":"2311.09000","n_code_links":2,"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":["yuxiaw/factcheck-gpt"],"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":"generalizable-imitation-learning-through-pre","title":"Generalizable Imitation Learning Through Pre-Trained Representations","date":"2023-11-15","arxiv_id":"2311.09350","n_code_links":0,"syntology":null},{"paper":null,"slug":"grim-graph-based-interactive-narrative","title":"GENEVA: GENErating and Visualizing branching narratives using LLMs","date":"2023-11-15","arxiv_id":"2311.09213","n_code_links":0,"syntology":null},{"paper":"/paper/i-was-blind-but-now-i-see-implementing-vision","slug":"i-was-blind-but-now-i-see-implementing-vision","title":"I Was Blind but Now I See: Implementing Vision-Enabled Dialogue in Social Robots","date":"2023-11-15","arxiv_id":"2311.08957","n_code_links":1,"syntology":null},{"paper":null,"slug":"jailbreaking-gpt-4v-via-self-adversarial","title":"Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts","date":"2023-11-15","arxiv_id":"2311.09127","n_code_links":0,"syntology":null}],"record_sha256":"180a1b4ed9e3ef3666c13138ae4705c30715e6682ce31131d2b7cb6ad5f6e9cc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}