{"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/43","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":43,"pages_in_order":140,"rows_per_page":100,"rows":[4201,4300],"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/42","next":"/method/transformer/papers/44","papers":[{"paper":null,"slug":"global-local-detail-guided-transformer-for","title":"Global-Local Detail Guided Transformer for Sea Ice Recognition in Optical Remote Sensing Images","date":"2024-05-21","arxiv_id":"2405.13197","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-jailbreaks-itself-with-near-perfect","title":"GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation","date":"2024-05-21","arxiv_id":"2405.13077","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-dataset-quality-still-a-concern-in","title":"Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?","date":"2024-05-21","arxiv_id":"2405.12584","n_code_links":0,"syntology":null},{"paper":"/paper/mamba-in-speech-towards-an-alternative-to","slug":"mamba-in-speech-towards-an-alternative-to","title":"Mamba in Speech: Towards an Alternative to Self-Attention","date":"2024-05-21","arxiv_id":"2405.12609","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-overconfidence-in-out-of","slug":"mitigating-overconfidence-in-out-of","title":"Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activations","date":"2024-05-21","arxiv_id":"2405.12658","n_code_links":1,"syntology":null},{"paper":"/paper/neural-operator-for-accelerating-coronal","slug":"neural-operator-for-accelerating-coronal","title":"Global-local Fourier Neural Operator for Accelerating Coronal Magnetic Field Model","date":"2024-05-21","arxiv_id":"2405.12754","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":["yutao-0718/gl-fno"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"pathocl-path-based-prompt-augmentation-for","title":"PathOCL: Path-Based Prompt Augmentation for OCL Generation with GPT-4","date":"2024-05-21","arxiv_id":"2405.12450","n_code_links":0,"syntology":null},{"paper":null,"slug":"pseudo-channel-time-embedding-for-motor","title":"Pseudo Channel: Time Embedding for Motor Imagery Decoding","date":"2024-05-21","arxiv_id":"2405.15812","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-modality-agnostic-pre","slug":"self-supervised-modality-agnostic-pre","title":"Self-Supervised Modality-Agnostic Pre-Training of Swin Transformers","date":"2024-05-21","arxiv_id":"2405.12781","n_code_links":1,"syntology":null},{"paper":null,"slug":"system-safety-monitoring-of-learned","title":"System Safety Monitoring of Learned Components Using Temporal Metric Forecasting","date":"2024-05-21","arxiv_id":"2405.13254","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-in-touch-a-survey","title":"Transformer in Touch: A Survey","date":"2024-05-21","arxiv_id":"2405.12779","n_code_links":0,"syntology":null},{"paper":"/paper/asymptotic-theory-of-in-context-learning-by","slug":"asymptotic-theory-of-in-context-learning-by","title":"Asymptotic theory of in-context learning by linear attention","date":"2024-05-20","arxiv_id":"2405.11751","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: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Pehlevan-Group/icl-asymptotic"],"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":"/paper/can-ai-relate-testing-large-language-model","slug":"can-ai-relate-testing-large-language-model","title":"Can AI Relate: Testing Large Language Model Response for Mental Health Support","date":"2024-05-20","arxiv_id":"2405.12021","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["skgabriel/mh-eval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ct-eval-benchmarking-chinese-text-to-table","title":"CT-Eval: Benchmarking Chinese Text-to-Table Performance in Large Language Models","date":"2024-05-20","arxiv_id":"2405.12174","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-optimization-of-large-scale","title":"Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks","date":"2024-05-20","arxiv_id":"2405.11704","n_code_links":0,"syntology":null},{"paper":"/paper/fennec-fine-grained-language-model-evaluation","slug":"fennec-fine-grained-language-model-evaluation","title":"Fennec: Fine-grained Language Model Evaluation and Correction Extended through Branching and Bridging","date":"2024-05-20","arxiv_id":"2405.12163","n_code_links":1,"syntology":null},{"paper":"/paper/is-mamba-compatible-with-trajectory","slug":"is-mamba-compatible-with-trajectory","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","date":"2024-05-20","arxiv_id":"2405.12094","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":1,"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) · 4 unverified","official":{"repos":["AndssY/DeMa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-scale-multi-center-ct-and-mri","slug":"large-scale-multi-center-ct-and-mri","title":"Large-Scale Multi-Center CT and MRI Segmentation of Pancreas with Deep Learning","date":"2024-05-20","arxiv_id":"2405.12367","n_code_links":1,"syntology":null},{"paper":null,"slug":"metacognitive-capabilities-of-llms-an","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","date":"2024-05-20","arxiv_id":"2405.12205","n_code_links":0,"syntology":null},{"paper":"/paper/ssamba-self-supervised-audio-representation","slug":"ssamba-self-supervised-audio-representation","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","date":"2024-05-20","arxiv_id":"2405.11831","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: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["siavashshams/ssamba"],"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":null,"slug":"a-multi-perspective-analysis-of-memorization","title":"A Multi-Perspective Analysis of Memorization in Large Language Models","date":"2024-05-19","arxiv_id":"2405.11577","n_code_links":0,"syntology":null},{"paper":"/paper/colorfoil-investigating-color-blindness-in","slug":"colorfoil-investigating-color-blindness-in","title":"ColorFoil: Investigating Color Blindness in Large Vision and Language Models","date":"2024-05-19","arxiv_id":"2405.11685","n_code_links":1,"syntology":null},{"paper":"/paper/du-in-discrete-units-guided-mask-modeling-for","slug":"du-in-discrete-units-guided-mask-modeling-for","title":"Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals","date":"2024-05-19","arxiv_id":"2405.11459","n_code_links":1,"syntology":null},{"paper":null,"slug":"hummer-towards-limited-competitive-preference","title":"Hummer: Towards Limited Competitive Preference Dataset","date":"2024-05-19","arxiv_id":"2405.11647","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-cnn-transformer-architecture-for","slug":"hybrid-cnn-transformer-architecture-for","title":"Hybrid CNN-Transformer Architecture for Efficient Large-Scale Video Snapshot Compressive Imaging","date":"2024-05-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-can-infer-personality","title":"Large Language Models Can Infer Personality from Free-Form User Interactions","date":"2024-05-19","arxiv_id":"2405.13052","n_code_links":0,"syntology":null},{"paper":"/paper/mhpp-exploring-the-capabilities-and","slug":"mhpp-exploring-the-capabilities-and","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","date":"2024-05-19","arxiv_id":"2405.11430","n_code_links":1,"syntology":null},{"paper":"/paper/netmamba-efficient-network-traffic","slug":"netmamba-efficient-network-traffic","title":"NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba","date":"2024-05-19","arxiv_id":"2405.11449","n_code_links":1,"syntology":null},{"paper":"/paper/review-of-deep-learning-models-for-crypto","slug":"review-of-deep-learning-models-for-crypto","title":"Review of deep learning models for crypto price prediction: implementation and evaluation","date":"2024-05-19","arxiv_id":"2405.11431","n_code_links":2,"syntology":null},{"paper":"/paper/vcformer-variable-correlation-transformer","slug":"vcformer-variable-correlation-transformer","title":"VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting","date":"2024-05-19","arxiv_id":"2405.11470","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["csyyn/vcformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-dual-power-grid-cascading-failure-model-for","title":"A Dual Power Grid Cascading Failure Model for the Vulnerability Analysis","date":"2024-05-18","arxiv_id":"2405.11311","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-ptsd-diagnostics-in-clinical","title":"Automating PTSD Diagnostics in Clinical Interviews: Leveraging Large Language Models for Trauma Assessments","date":"2024-05-18","arxiv_id":"2405.11178","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-public-llms-be-used-for-self-diagnosis-of","title":"Can Public LLMs be used for Self-Diagnosis of Medical Conditions ?","date":"2024-05-18","arxiv_id":"2405.11407","n_code_links":0,"syntology":null},{"paper":null,"slug":"activellm-large-language-model-based-active","title":"ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios","date":"2024-05-17","arxiv_id":"2405.10808","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-moral-hypocrites-a","title":"Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundations","date":"2024-05-17","arxiv_id":"2405.11100","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-large-language-models-on-cflue-a","slug":"benchmarking-large-language-models-on-cflue-a","title":"Benchmarking Large Language Models on CFLUE -- A Chinese Financial Language Understanding Evaluation Dataset","date":"2024-05-17","arxiv_id":"2405.10542","n_code_links":2,"syntology":null},{"paper":null,"slug":"enhancing-dialogue-state-tracking-models","title":"Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation","date":"2024-05-17","arxiv_id":"2405.13037","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-the-analysis-of-murine-neonatal","slug":"enhancing-the-analysis-of-murine-neonatal","title":"Enhancing the analysis of murine neonatal ultrasonic vocalizations: Development, evaluation, and application of different mathematical models","date":"2024-05-17","arxiv_id":"2405.12957","n_code_links":1,"syntology":null},{"paper":"/paper/evaluation-of-large-language-model","slug":"evaluation-of-large-language-model","title":"Evaluation of large language model performance on the Biomedical Language Understanding and Reasoning Benchmark","date":"2024-05-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hi-gmae-hierarchical-graph-masked","slug":"hi-gmae-hierarchical-graph-masked","title":"Hi-GMAE: Hierarchical Graph Masked Autoencoders","date":"2024-05-17","arxiv_id":"2405.10642","n_code_links":1,"syntology":null},{"paper":"/paper/know-in-advance-linear-complexity-forecasting","slug":"know-in-advance-linear-complexity-forecasting","title":"Know in AdVance: Linear-Complexity Forecasting of Ad Campaign Performance with Evolving User Interest","date":"2024-05-17","arxiv_id":"2405.10681","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-can-evaluate-themselves-via","slug":"language-models-can-evaluate-themselves-via","title":"Language Models can Evaluate Themselves via Probability Discrepancy","date":"2024-05-17","arxiv_id":"2405.10516","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-can-exploit-cross-task-in","slug":"language-models-can-exploit-cross-task-in","title":"Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks","date":"2024-05-17","arxiv_id":"2405.10548","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["c-anwoy/cross-task-icl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-in-wireless-application","title":"Large Language Models in Wireless Application Design: In-Context Learning-enhanced Automatic Network Intrusion Detection","date":"2024-05-17","arxiv_id":"2405.11002","n_code_links":0,"syntology":null},{"paper":"/paper/observational-scaling-laws-and-the","slug":"observational-scaling-laws-and-the","title":"Observational Scaling Laws and the Predictability of Language Model Performance","date":"2024-05-17","arxiv_id":"2405.10938","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["ryoungj/obsscaling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"persian-pronoun-resolution-leveraging-neural","title":"Persian Pronoun Resolution: Leveraging Neural Networks and Language Models","date":"2024-05-17","arxiv_id":"2405.10714","n_code_links":0,"syntology":null},{"paper":null,"slug":"simultaneous-deep-learning-of-myocardium","title":"Simultaneous Deep Learning of Myocardium Segmentation and T2 Quantification for Acute Myocardial Infarction MRI","date":"2024-05-17","arxiv_id":"2405.10570","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-distribution-assessment-of-jiles","title":"Uncertainty Distribution Assessment of Jiles-Atherton Parameter Estimation for Inrush Current Studies","date":"2024-05-17","arxiv_id":"2405.11011","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-tale-of-two-languages-large-vocabulary","title":"A Tale of Two Languages: Large-Vocabulary Continuous Sign Language Recognition from Spoken Language Supervision","date":"2024-05-16","arxiv_id":"2405.10266","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-implicit-multimodal-knowledge-into","slug":"distilling-implicit-multimodal-knowledge-into","title":"Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation","date":"2024-05-16","arxiv_id":"2405.10121","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-in-context-learning-with","slug":"dynamic-in-context-learning-with","title":"Dynamic In-context Learning with Conversational Models for Data Extraction and Materials Property Prediction","date":"2024-05-16","arxiv_id":"2405.10448","n_code_links":1,"syntology":null},{"paper":null,"slug":"fintextqa-a-dataset-for-long-form-financial","title":"FinTextQA: A Dataset for Long-form Financial Question Answering","date":"2024-05-16","arxiv_id":"2405.09980","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-store-mining-and-analysis","title":"GPT Store Mining and Analysis","date":"2024-05-16","arxiv_id":"2405.10210","n_code_links":0,"syntology":null},{"paper":"/paper/imgadapointr-improving-point-cloud-completion","slug":"imgadapointr-improving-point-cloud-completion","title":"ImgAdaPoinTr: Improving Point Cloud Completion via Images and Segmentation","date":"2024-05-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"infrared-adversarial-car-stickers","title":"Infrared Adversarial Car Stickers","date":"2024-05-16","arxiv_id":"2405.09924","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-relevance-of-pre-neural-approaches-in","title":"Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy","date":"2024-05-16","arxiv_id":"2405.09854","n_code_links":0,"syntology":null},{"paper":"/paper/specdetr-a-transformer-based-hyperspectral","slug":"specdetr-a-transformer-based-hyperspectral","title":"SpecDETR: A Transformer-based Hyperspectral Point Object Detection Network","date":"2024-05-16","arxiv_id":"2405.10148","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-ai-collaborator-bridging-human-ai","title":"The AI Collaborator: Bridging Human-AI Interaction in Educational and Professional Settings","date":"2024-05-16","arxiv_id":"2405.10460","n_code_links":0,"syntology":null},{"paper":null,"slug":"transcript-of-gpt-4-playing-a-rogue-agi-in-a","title":"Transcript of GPT-4 playing a rogue AGI in a Matrix Game","date":"2024-05-16","arxiv_id":"2405.10997","n_code_links":0,"syntology":null},{"paper":null,"slug":"alpine-unveiling-the-planning-capability-of","title":"ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models","date":"2024-05-15","arxiv_id":"2405.09220","n_code_links":0,"syntology":null},{"paper":"/paper/an-embarrassingly-simple-approach-to-enhance","slug":"an-embarrassingly-simple-approach-to-enhance","title":"An Embarrassingly Simple Approach to Enhance Transformer Performance in Genomic Selection for Crop Breeding","date":"2024-05-15","arxiv_id":"2405.09585","n_code_links":2,"syntology":null},{"paper":null,"slug":"comparing-the-efficacy-of-gpt-4-and-chat-gpt","title":"Comparing the Efficacy of GPT-4 and Chat-GPT in Mental Health Care: A Blind Assessment of Large Language Models for Psychological Support","date":"2024-05-15","arxiv_id":"2405.09300","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-maritime-trajectory-forecasting-via","title":"Enhancing Maritime Trajectory Forecasting via H3 Index and Causal Language Modelling (CLM)","date":"2024-05-15","arxiv_id":"2405.09596","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-potential-of-large-language-8","title":"Exploring the Potential of Large Language Models for Automation in Technical Customer Service","date":"2024-05-15","arxiv_id":"2405.09161","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-transformers-using-faithful","title":"Improving Transformers using Faithful Positional Encoding","date":"2024-05-15","arxiv_id":"2405.09061","n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-tutor-leveraging-chatgpt-and","title":"Intelligent Tutor: Leveraging ChatGPT and Microsoft Copilot Studio to Deliver a Generative AI Student Support and Feedback System within Teams","date":"2024-05-15","arxiv_id":"2405.13024","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-bilingual-sentence-processing","title":"Modeling Bilingual Sentence Processing: Evaluating RNN and Transformer Architectures for Cross-Language Structural Priming","date":"2024-05-15","arxiv_id":"2405.09508","n_code_links":0,"syntology":null},{"paper":null,"slug":"perception-and-fidelity-aware-reduced","title":"Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessment","date":"2024-05-15","arxiv_id":"2405.09472","n_code_links":0,"syntology":null},{"paper":"/paper/positional-knowledge-is-all-you-need-position","slug":"positional-knowledge-is-all-you-need-position","title":"Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning","date":"2024-05-15","arxiv_id":"2405.09285","n_code_links":1,"syntology":null},{"paper":null,"slug":"simulating-policy-impacts-developing-a","title":"Simulating Policy Impacts: Developing a Generative Scenario Writing Method to Evaluate the Perceived Effects of Regulation","date":"2024-05-15","arxiv_id":"2405.09679","n_code_links":0,"syntology":null},{"paper":null,"slug":"sql-to-schema-enhances-schema-linking-in-text","title":"SQL-to-Schema Enhances Schema Linking in Text-to-SQL","date":"2024-05-15","arxiv_id":"2405.09593","n_code_links":0,"syntology":null},{"paper":"/paper/tell-me-why-explainable-public-health-fact","slug":"tell-me-why-explainable-public-health-fact","title":"Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models","date":"2024-05-15","arxiv_id":"2405.09454","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-alignment-as-preference-for-machine","title":"Word Alignment as Preference for Machine Translation","date":"2024-05-15","arxiv_id":"2405.09223","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-survey-of-large-language","title":"A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine","date":"2024-05-14","arxiv_id":"2405.08603","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-timely-survey-on-vision-transformer-for","title":"A Timely Survey on Vision Transformer for Deepfake Detection","date":"2024-05-14","arxiv_id":"2405.08463","n_code_links":0,"syntology":null},{"paper":null,"slug":"airport-delay-prediction-with-temporal-fusion","title":"Airport Delay Prediction with Temporal Fusion Transformers","date":"2024-05-14","arxiv_id":"2405.08293","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-scaling-laws-understanding-transformer","title":"Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory","date":"2024-05-14","arxiv_id":"2405.08707","n_code_links":0,"syntology":null},{"paper":null,"slug":"dgcformer-deep-graph-clustering-transformer","title":"DGCformer: Deep Graph Clustering Transformer for Multivariate Time Series Forecasting","date":"2024-05-14","arxiv_id":"2405.08440","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-the-power-of-longitudinal-medical","slug":"harnessing-the-power-of-longitudinal-medical","title":"Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling","date":"2024-05-14","arxiv_id":"2405.08780","n_code_links":1,"syntology":null},{"paper":"/paper/improving-transformers-with-dynamically","slug":"improving-transformers-with-dynamically","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","date":"2024-05-14","arxiv_id":"2405.08553","n_code_links":2,"syntology":{"ran":9,"of":12,"n_ran_checked":6,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["caiyun-ai/dcformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/reinformer-max-return-sequence-modeling-for","slug":"reinformer-max-return-sequence-modeling-for","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","date":"2024-05-14","arxiv_id":"2405.08740","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 4 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) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["dragon-zhuang/reinformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rethinking-scanning-strategies-with-vision","title":"Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study","date":"2024-05-14","arxiv_id":"2405.08493","n_code_links":0,"syntology":null},{"paper":null,"slug":"rmt-bvqa-recurrent-memory-transformer-based","title":"RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content","date":"2024-05-14","arxiv_id":"2405.08621","n_code_links":0,"syntology":null},{"paper":null,"slug":"tfwt-tabular-feature-weighting-with","title":"TFWT: Tabular Feature Weighting with Transformer","date":"2024-05-14","arxiv_id":"2405.08403","n_code_links":0,"syntology":null},{"paper":null,"slug":"watermamba-visual-state-space-model-for","title":"WaterMamba: Visual State Space Model for Underwater Image Enhancement","date":"2024-05-14","arxiv_id":"2405.08419","n_code_links":0,"syntology":null},{"paper":"/paper/can-language-models-explain-their-own","slug":"can-language-models-explain-their-own","title":"Can Language Models Explain Their Own Classification Behavior?","date":"2024-05-13","arxiv_id":"2405.07436","n_code_links":1,"syntology":null},{"paper":"/paper/cdformer-when-degradation-prediction-embraces","slug":"cdformer-when-degradation-prediction-embraces","title":"CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution","date":"2024-05-13","arxiv_id":"2405.07648","n_code_links":1,"syntology":{"ran":11,"of":17,"n_ran_checked":10,"n_instrument":1,"unverified":6,"pointer_only":1,"phrase":"11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["i2-multimedia-lab/cdformer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/coding-historical-causes-of-death-data-with","slug":"coding-historical-causes-of-death-data-with","title":"Coding historical causes of death data with Large Language Models","date":"2024-05-13","arxiv_id":"2405.07560","n_code_links":1,"syntology":null},{"paper":null,"slug":"fighter-flight-trajectory-prediction-based-on","title":"Fighter flight trajectory prediction based on spatio-temporal graphcial attention network","date":"2024-05-13","arxiv_id":"2405.08034","n_code_links":0,"syntology":null},{"paper":null,"slug":"ground-based-image-deconvolution-with-swin","title":"Ground-based image deconvolution with Swin Transformer UNet","date":"2024-05-13","arxiv_id":"2405.07842","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-decision-mamba","slug":"hierarchical-decision-mamba","title":"Decision Mamba Architectures","date":"2024-05-13","arxiv_id":"2405.07943","n_code_links":2,"syntology":null},{"paper":"/paper/hybridhash-hybrid-convolutional-and-self","slug":"hybridhash-hybrid-convolutional-and-self","title":"HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval","date":"2024-05-13","arxiv_id":"2405.07524","n_code_links":1,"syntology":null},{"paper":null,"slug":"metareflection-learning-instructions-for","title":"MetaReflection: Learning Instructions for Language Agents using Past Reflections","date":"2024-05-13","arxiv_id":"2405.13009","n_code_links":0,"syntology":null},{"paper":null,"slug":"plot2code-a-comprehensive-benchmark-for","title":"Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots","date":"2024-05-13","arxiv_id":"2405.07990","n_code_links":0,"syntology":null},{"paper":"/paper/quantifying-and-optimizing-global","slug":"quantifying-and-optimizing-global","title":"Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing","date":"2024-05-13","arxiv_id":"2405.07726","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["KomeijiForce/Active_Passive_Constraint_Koishiday_2024"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/restad-reconstruction-and-similarity-based","slug":"restad-reconstruction-and-similarity-based","title":"RESTAD: REconstruction and Similarity based Transformer for time series Anomaly Detection","date":"2024-05-13","arxiv_id":"2405.07509","n_code_links":1,"syntology":null},{"paper":null,"slug":"sambanova-sn40l-scaling-the-ai-memory-wall","title":"SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts","date":"2024-05-13","arxiv_id":"2405.07518","n_code_links":0,"syntology":null},{"paper":"/paper/boq-a-place-is-worth-a-bag-of-learnable","slug":"boq-a-place-is-worth-a-bag-of-learnable","title":"BoQ: A Place is Worth a Bag of Learnable Queries","date":"2024-05-12","arxiv_id":"2405.07364","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["amaralibey/bag-of-queries"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cafa-global-weather-forecasting-with","slug":"cafa-global-weather-forecasting-with","title":"CaFA: Global Weather Forecasting with Factorized Attention on Sphere","date":"2024-05-12","arxiv_id":"2405.07395","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["BaratiLab/CaFA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hgtdr-advancing-drug-repurposing-with","title":"HGTDR: Advancing Drug Repurposing with Heterogeneous Graph Transformers","date":"2024-05-12","arxiv_id":"2405.08031","n_code_links":0,"syntology":null}],"record_sha256":"2090f804c4d9835579a77f8051f00df5077c83fb7452aed564fbd6bce8dccfd4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}