{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/attention/papers/178","list_of":"/method/attention","method":"Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":178,"pages_in_order":316,"rows_per_page":100,"rows":[17701,17800],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention","prev":"/method/attention/papers/177","next":"/method/attention/papers/179","papers":[{"paper":"/paper/expanding-the-vocabulary-of-bert-for","slug":"expanding-the-vocabulary-of-bert-for","title":"Expanding the Vocabulary of BERT for Knowledge Base Construction","date":"2023-10-12","arxiv_id":"2310.08291","n_code_links":1,"syntology":null},{"paper":"/paper/impact-of-time-and-note-duration","slug":"impact-of-time-and-note-duration","title":"Impact of time and note duration tokenizations on deep learning symbolic music modeling","date":"2023-10-12","arxiv_id":"2310.08497","n_code_links":1,"syntology":null},{"paper":"/paper/interpreting-reward-models-in-rlhf-tuned","slug":"interpreting-reward-models-in-rlhf-tuned","title":"Interpreting Learned Feedback Patterns in Large Language Models","date":"2023-10-12","arxiv_id":"2310.08164","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["apartresearch/interpreting-reward-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"investigating-the-robustness-and-properties","title":"Investigating the Robustness and Properties of Detection Transformers (DETR) Toward Difficult Images","date":"2023-10-12","arxiv_id":"2310.08772","n_code_links":0,"syntology":null},{"paper":"/paper/jailbreaking-black-box-large-language-models","slug":"jailbreaking-black-box-large-language-models","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","date":"2023-10-12","arxiv_id":"2310.08419","n_code_links":1,"syntology":{"ran":2,"of":7,"n_ran_checked":1,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["patrickrchao/jailbreakingllms"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-can-replicate-cross","title":"Large language models can replicate cross-cultural differences in personality","date":"2023-10-12","arxiv_id":"2310.10679","n_code_links":0,"syntology":null},{"paper":"/paper/lemon-lossless-model-expansion","slug":"lemon-lossless-model-expansion","title":"LEMON: Lossless model expansion","date":"2023-10-12","arxiv_id":"2310.07999","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":["YiteWang/lemon-pytorch"],"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":"llm-augmented-preference-learning-from","title":"LLM-augmented Preference Learning from Natural Language","date":"2023-10-12","arxiv_id":"2310.08523","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiclass-classification-of-policy-documents","title":"Multiclass Classification of Policy Documents with Large Language Models","date":"2023-10-12","arxiv_id":"2310.08167","n_code_links":0,"syntology":null},{"paper":"/paper/octopus-embodied-vision-language-programmer","slug":"octopus-embodied-vision-language-programmer","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","date":"2023-10-12","arxiv_id":"2310.08588","n_code_links":1,"syntology":{"ran":12,"of":12,"n_ran_checked":6,"n_instrument":6,"unverified":0,"pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dongyh20/octopus"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/prometheus-inducing-fine-grained-evaluation","slug":"prometheus-inducing-fine-grained-evaluation","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","date":"2023-10-12","arxiv_id":"2310.08491","n_code_links":3,"syntology":{"ran":4,"of":9,"n_ran_checked":3,"n_instrument":1,"unverified":5,"pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["kaistAI/Prometheus"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"promptor-a-conversational-and-autonomous","title":"Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques","date":"2023-10-12","arxiv_id":"2310.08101","n_code_links":0,"syntology":null},{"paper":"/paper/qasina-religious-domain-question-answering","slug":"qasina-religious-domain-question-answering","title":"QASiNa: Religious Domain Question Answering using Sirah Nabawiyah","date":"2023-10-12","arxiv_id":"2310.08102","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-data-augmentation-for-rotational","title":"Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks","date":"2023-10-12","arxiv_id":"2310.08429","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-visual-learning-for-analyzing","title":"Self-supervised visual learning for analyzing firearms trafficking activities on the Web","date":"2023-10-12","arxiv_id":"2310.07975","n_code_links":0,"syntology":null},{"paper":"/paper/the-uncertainty-based-retrieval-framework-for-1","slug":"the-uncertainty-based-retrieval-framework-for-1","title":"The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POS","date":"2023-10-12","arxiv_id":"2310.08496","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-generative-question-answering-on","title":"Training Generative Question-Answering on Synthetic Data Obtained from an Instruct-tuned Model","date":"2023-10-12","arxiv_id":"2310.08072","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-choice-net-a-transformer-neural","title":"Transformer Choice Net: A Transformer Neural Network for Choice Prediction","date":"2023-10-12","arxiv_id":"2310.08716","n_code_links":0,"syntology":null},{"paper":"/paper/transport-hub-aware-spatial-temporal-adaptive","slug":"transport-hub-aware-spatial-temporal-adaptive","title":"Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow Prediction","date":"2023-10-12","arxiv_id":"2310.08328","n_code_links":1,"syntology":null},{"paper":null,"slug":"ziya-vl-bilingual-large-vision-language-model","title":"Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning","date":"2023-10-12","arxiv_id":"2310.08166","n_code_links":0,"syntology":null},{"paper":"/paper/3d-transunet-advancing-medical-image","slug":"3d-transunet-advancing-medical-image","title":"3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers","date":"2023-10-11","arxiv_id":"2310.07781","n_code_links":3,"syntology":null},{"paper":null,"slug":"accelerating-vision-transformers-based-on","title":"Accelerating Vision Transformers Based on Heterogeneous Attention Patterns","date":"2023-10-11","arxiv_id":"2310.07664","n_code_links":0,"syntology":null},{"paper":null,"slug":"atom-motif-contrastive-transformer-for","title":"Atom-Motif Contrastive Transformer for Molecular Property Prediction","date":"2023-10-11","arxiv_id":"2310.07351","n_code_links":0,"syntology":null},{"paper":"/paper/cognate-transformer-for-automated","slug":"cognate-transformer-for-automated","title":"Cognate Transformer for Automated Phonological Reconstruction and Cognate Reflex Prediction","date":"2023-10-11","arxiv_id":"2310.07487","n_code_links":1,"syntology":null},{"paper":"/paper/daspeech-directed-acyclic-transformer-for-1","slug":"daspeech-directed-acyclic-transformer-for-1","title":"DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation","date":"2023-10-11","arxiv_id":"2310.07403","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"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) · 2 unverified","official":{"repos":["ictnlp/daspeech"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"distance-based-weighted-transformer-network","title":"Distance Weighted Trans Network for Image Completion","date":"2023-10-11","arxiv_id":"2310.07440","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-efficient-vision-transformers-from","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","date":"2023-10-11","arxiv_id":"2310.07265","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversity-of-thought-improves-reasoning","title":"Diversity of Thought Improves Reasoning Abilities of LLMs","date":"2023-10-11","arxiv_id":"2310.07088","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-resistance-to-style-transfer-equal-shape","title":"Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configuration","date":"2023-10-11","arxiv_id":"2310.07555","n_code_links":0,"syntology":null},{"paper":null,"slug":"ethical-reasoning-over-moral-alignment-a-case","title":"Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs","date":"2023-10-11","arxiv_id":"2310.07251","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-landscape-of-large-language","title":"Do Large Language Models have Shared Weaknesses in Medical Question Answering?","date":"2023-10-11","arxiv_id":"2310.07225","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-electra-for-efficient-pre-training","title":"Fast-ELECTRA for Efficient Pre-training","date":"2023-10-11","arxiv_id":"2310.07347","n_code_links":0,"syntology":null},{"paper":"/paper/found-in-the-middle-permutation-self","slug":"found-in-the-middle-permutation-self","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","date":"2023-10-11","arxiv_id":"2310.07712","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["castorini/perm-sc"],"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/generalized-neural-sorting-networks-with","slug":"generalized-neural-sorting-networks-with","title":"Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions","date":"2023-10-11","arxiv_id":"2310.07174","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":2,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"global-minima-recoverability-thresholds-and","title":"Global Minima, Recoverability Thresholds, and Higher-Order Structure in GNNS","date":"2023-10-11","arxiv_id":"2310.07667","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-transformer-network-for-flood","title":"Graph Transformer Network for Flood Forecasting with Heterogeneous Covariates","date":"2023-10-11","arxiv_id":"2310.07631","n_code_links":0,"syntology":null},{"paper":"/paper/instructretro-instruction-tuning-post","slug":"instructretro-instruction-tuning-post","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","date":"2023-10-11","arxiv_id":"2310.07713","n_code_links":1,"syntology":null},{"paper":null,"slug":"jaeger-a-concatenation-based-multi","title":"Jaeger: A Concatenation-Based Multi-Transformer VQA Model","date":"2023-10-11","arxiv_id":"2310.07091","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-zero-shot-time-1","slug":"large-language-models-are-zero-shot-time-1","title":"Large Language Models Are Zero-Shot Time Series Forecasters","date":"2023-10-11","arxiv_id":"2310.07820","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ngruver/llmtime"],"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":["listed","official"]}}},{"paper":"/paper/matformer-nested-transformer-for-elastic","slug":"matformer-nested-transformer-for-elastic","title":"MatFormer: Nested Transformer for Elastic Inference","date":"2023-10-11","arxiv_id":"2310.07707","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":null}},{"paper":"/paper/nutime-numerically-multi-scaled-embedding-for","slug":"nutime-numerically-multi-scaled-embedding-for","title":"NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining","date":"2023-10-11","arxiv_id":"2310.07402","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["chenguolin/nutime"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"parrot-enhancing-multi-turn-chat-models-by","title":"Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models","date":"2023-10-11","arxiv_id":"2310.07301","n_code_links":0,"syntology":null},{"paper":null,"slug":"protohpe-prototype-guided-high-frequency","title":"ProtoHPE: Prototype-guided High-frequency Patch Enhancement for Visible-Infrared Person Re-identification","date":"2023-10-11","arxiv_id":"2310.07552","n_code_links":0,"syntology":null},{"paper":"/paper/ptychodv-vision-transformer-based-deep","slug":"ptychodv-vision-transformer-based-deep","title":"PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction","date":"2023-10-11","arxiv_id":"2310.07504","n_code_links":1,"syntology":null},{"paper":"/paper/relational-prior-knowledge-graphs-for","slug":"relational-prior-knowledge-graphs-for","title":"Relational Prior Knowledge Graphs for Detection and Instance Segmentation","date":"2023-10-11","arxiv_id":"2310.07573","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-the-bert-like-pretraining-for-dna","title":"Toward Understanding BERT-Like Pre-Training for DNA Foundation Models","date":"2023-10-11","arxiv_id":"2310.07644","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-universal-transformer","slug":"sparse-universal-transformer","title":"Sparse Universal Transformer","date":"2023-10-11","arxiv_id":"2310.07096","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"towards-foundation-models-for-learning-on","title":"From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models","date":"2023-10-11","arxiv_id":"2310.07338","n_code_links":0,"syntology":null},{"paper":"/paper/uncovering-hidden-connections-iterative","slug":"uncovering-hidden-connections-iterative","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","date":"2023-10-11","arxiv_id":"2310.07259","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":6,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hyu-zhang/itr","Hyu-Zhang/ISR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"wigenai-the-symphony-of-wireless-and","title":"Diffusion Models for Wireless Communications","date":"2023-10-11","arxiv_id":"2310.07312","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformer-based-1","title":"A Comparative Study of Transformer-based Neural Text Representation Techniques on Bug Triaging","date":"2023-10-10","arxiv_id":"2310.06913","n_code_links":0,"syntology":null},{"paper":null,"slug":"advective-diffusion-transformers-for","title":"Supercharging Graph Transformers with Advective Diffusion","date":"2023-10-10","arxiv_id":"2310.06417","n_code_links":0,"syntology":null},{"paper":null,"slug":"answer-candidate-type-selection-text-to-text","title":"Answer Candidate Type Selection: Text-to-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs","date":"2023-10-10","arxiv_id":"2310.07008","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-clinical-coding-using-off-the-shelf","title":"Automated clinical coding using off-the-shelf large language models","date":"2023-10-10","arxiv_id":"2310.06552","n_code_links":0,"syntology":null},{"paper":null,"slug":"computational-pathology-at-health-system","title":"Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Images","date":"2023-10-10","arxiv_id":"2310.07033","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-adaptation-of-large-vision-1","slug":"efficient-adaptation-of-large-vision-1","title":"Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing","date":"2023-10-10","arxiv_id":"2310.06234","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["davidyanande/arc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/evit-an-eagle-vision-transformer-with-bi","slug":"evit-an-eagle-vision-transformer-with-bi","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","date":"2023-10-10","arxiv_id":"2310.06629","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-and-evaluating-tests-for-k-12","title":"Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency","date":"2023-10-10","arxiv_id":"2310.06837","n_code_links":0,"syntology":null},{"paper":"/paper/geollm-extracting-geospatial-knowledge-from","slug":"geollm-extracting-geospatial-knowledge-from","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","date":"2023-10-10","arxiv_id":"2310.06213","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rohinmanvi/GeoLLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-4-as-an-agronomist-assistant-answering","title":"GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models","date":"2023-10-10","arxiv_id":"2310.06225","n_code_links":0,"syntology":null},{"paper":"/paper/humans-and-language-models-diverge-when","slug":"humans-and-language-models-diverge-when","title":"Humans and language models diverge when predicting repeating text","date":"2023-10-10","arxiv_id":"2310.06408","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["huthlab/lm-repeating-text"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/itransformer-inverted-transformers-are","slug":"itransformer-inverted-transformers-are","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","date":"2023-10-10","arxiv_id":"2310.06625","n_code_links":11,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thuml/iTransformer"],"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-models-for-propaganda","slug":"large-language-models-for-propaganda","title":"Large Language Models for Propaganda Detection","date":"2023-10-10","arxiv_id":"2310.06422","n_code_links":2,"syntology":null},{"paper":"/paper/learning-stackable-and-skippable-lego-bricks","slug":"learning-stackable-and-skippable-lego-bricks","title":"Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling","date":"2023-10-10","arxiv_id":"2310.06389","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":8,"n_instrument":5,"unverified":4,"pointer_only":8,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["JegZheng/LEGODiffusion"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"llms-as-potential-brainstorming-partners-for","title":"LLMs as Potential Brainstorming Partners for Math and Science Problems","date":"2023-10-10","arxiv_id":"2310.10677","n_code_links":0,"syntology":null},{"paper":"/paper/longllmlingua-accelerating-and-enhancing-llms","slug":"longllmlingua-accelerating-and-enhancing-llms","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","date":"2023-10-10","arxiv_id":"2310.06839","n_code_links":3,"syntology":null},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","n_code_links":6,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/multilingual-jailbreak-challenges-in-large","slug":"multilingual-jailbreak-challenges-in-large","title":"Multilingual Jailbreak Challenges in Large Language Models","date":"2023-10-10","arxiv_id":"2310.06474","n_code_links":1,"syntology":null},{"paper":null,"slug":"newton-are-large-language-models-capable-of","title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?","date":"2023-10-10","arxiv_id":"2310.07018","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-finetuning-for-inference-acceleration","slug":"sparse-finetuning-for-inference-acceleration","title":"Sparse Fine-tuning for Inference Acceleration of Large Language Models","date":"2023-10-10","arxiv_id":"2310.06927","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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ist-daslab/sparsefinetuning"],"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/swe-bench-can-language-models-resolve-real","slug":"swe-bench-can-language-models-resolve-real","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","date":"2023-10-10","arxiv_id":"2310.06770","n_code_links":8,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":"/paper/wavenet-wave-aware-image-enhancement","slug":"wavenet-wave-aware-image-enhancement","title":"WaveNet: Wave-Aware Image Enhancement","date":"2023-10-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/what-does-stable-diffusion-know-about-the-3d","slug":"what-does-stable-diffusion-know-about-the-3d","title":"A General Protocol to Probe Large Vision Models for 3D Physical Understanding","date":"2023-10-10","arxiv_id":"2310.06836","n_code_links":1,"syntology":null},{"paper":"/paper/what-if-the-tv-was-off-examining","slug":"what-if-the-tv-was-off-examining","title":"What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models","date":"2023-10-10","arxiv_id":"2310.06627","n_code_links":1,"syntology":null},{"paper":"/paper/why-bother-with-geometry-on-the-relevance-of","slug":"why-bother-with-geometry-on-the-relevance-of","title":"Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings","date":"2023-10-10","arxiv_id":"2310.06977","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-glance-is-enough-extract-target-sentence-by","title":"A Glance is Enough: Extract Target Sentence By Looking at A keyword","date":"2023-10-09","arxiv_id":"2310.05352","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-meta-learning-perspective-on-transformers","title":"A Meta-Learning Perspective on Transformers for Causal Language Modeling","date":"2023-10-09","arxiv_id":"2310.05884","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-and-robust-framework-for-cross","slug":"a-simple-and-robust-framework-for-cross","title":"A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers","date":"2023-10-09","arxiv_id":"2310.05572","n_code_links":2,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-large-document","title":"Abstractive Summarization of Large Document Collections Using GPT","date":"2023-10-09","arxiv_id":"2310.05690","n_code_links":0,"syntology":null},{"paper":null,"slug":"auditing-gender-analyzers-on-text-data","title":"Auditing Gender Analyzers on Text Data","date":"2023-10-09","arxiv_id":"2310.06061","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-customer-service-using-langchain","title":"Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizations","date":"2023-10-09","arxiv_id":"2310.05421","n_code_links":0,"syntology":null},{"paper":null,"slug":"cabbage-sweeter-than-cake-analysing-the","title":"Cabbage Sweeter than Cake? Analysing the Potential of Large Language Models for Learning Conceptual Spaces","date":"2023-10-09","arxiv_id":"2310.05481","n_code_links":0,"syntology":null},{"paper":null,"slug":"dyst-towards-dynamic-neural-scene","title":"DyST: Towards Dynamic Neural Scene Representations on Real-World Videos","date":"2023-10-09","arxiv_id":"2310.06020","n_code_links":0,"syntology":null},{"paper":"/paper/fireact-toward-language-agent-fine-tuning","slug":"fireact-toward-language-agent-fine-tuning","title":"FireAct: Toward Language Agent Fine-tuning","date":"2023-10-09","arxiv_id":"2310.05915","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-models-meet-visualizations","title":"Foundation Models Meet Visualizations: Challenges and Opportunities","date":"2023-10-09","arxiv_id":"2310.05771","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-graphs-with-large-language-models","title":"Integrating Graphs with Large Language Models: Methods and Prospects","date":"2023-10-09","arxiv_id":"2310.05499","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-stock-features-and-global","title":"Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction","date":"2023-10-09","arxiv_id":"2310.05627","n_code_links":0,"syntology":null},{"paper":"/paper/learning-language-guided-adaptive-hyper","slug":"learning-language-guided-adaptive-hyper","title":"Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis","date":"2023-10-09","arxiv_id":"2310.05804","n_code_links":1,"syntology":null},{"paper":"/paper/mbbc-exploring-the-multilingual-maze","slug":"mbbc-exploring-the-multilingual-maze","title":"Exploring the Maze of Multilingual Modeling","date":"2023-10-09","arxiv_id":"2310.05404","n_code_links":0,"syntology":null},{"paper":null,"slug":"memory-consistent-neural-networks-for","title":"Memory-Consistent Neural Networks for Imitation Learning","date":"2023-10-09","arxiv_id":"2310.06171","n_code_links":0,"syntology":null},{"paper":"/paper/put-your-money-where-your-mouth-is-evaluating","slug":"put-your-money-where-your-mouth-is-evaluating","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","date":"2023-10-09","arxiv_id":"2310.05746","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":["jiangjiechen/auction-arena"],"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/reinforcement-learning-in-the-era-of-llms","slug":"reinforcement-learning-in-the-era-of-llms","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","date":"2023-10-09","arxiv_id":"2310.06147","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":null}},{"paper":null,"slug":"sc-safety-a-multi-round-open-ended-question","title":"SC-Safety: A Multi-round Open-ended Question Adversarial Safety Benchmark for Large Language Models in Chinese","date":"2023-10-09","arxiv_id":"2310.05818","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplr-a-simple-and-plain-transformer-for","title":"SimPLR: A Simple and Plain Transformer for Scaling-Efficient Object Detection and Segmentation","date":"2023-10-09","arxiv_id":"2310.05920","n_code_links":0,"syntology":null},{"paper":null,"slug":"take-a-step-back-evoking-reasoning-via","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","date":"2023-10-09","arxiv_id":"2310.06117","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-importance-of-prompt-tuning-for-automated","title":"The Importance of Prompt Tuning for Automated Neuron Explanations","date":"2023-10-09","arxiv_id":"2310.06200","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-program-testing-ability-of-large-language","title":"The Program Testing Ability of Large Language Models for Code","date":"2023-10-09","arxiv_id":"2310.05727","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-fusion-with-optimal-transport","slug":"transformer-fusion-with-optimal-transport","title":"Transformer Fusion with Optimal Transport","date":"2023-10-09","arxiv_id":"2310.05719","n_code_links":1,"syntology":{"ran":3,"of":10,"n_ran_checked":0,"n_instrument":3,"unverified":7,"pointer_only":10,"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) · 7 unverified","official":{"repos":["graldij/transformer-fusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformers-and-large-language-models-for","title":"Transformers and Large Language Models for Chemistry and Drug Discovery","date":"2023-10-09","arxiv_id":"2310.06083","n_code_links":0,"syntology":null},{"paper":null,"slug":"vits-are-everywhere-a-comprehensive-study","title":"ViTs are Everywhere: A Comprehensive Study Showcasing Vision Transformers in Different Domain","date":"2023-10-09","arxiv_id":"2310.05664","n_code_links":0,"syntology":null}],"record_sha256":"869d0f9cfeae690bec55772c0376679bec437d075e801fdf5a1c672ad73e4ea3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}