{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/multi-head-attention/papers/51","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":51,"pages_in_order":249,"rows_per_page":100,"rows":[5001,5100],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/multi-head-attention","prev":"/method/multi-head-attention/papers/50","next":"/method/multi-head-attention/papers/52","papers":[{"paper":null,"slug":"negation-blindness-in-large-language-models","title":"Negation Blindness in Large Language Models: Unveiling the NO Syndrome in Image Generation","date":"2024-08-27","arxiv_id":"2409.00105","n_code_links":0,"syntology":null},{"paper":null,"slug":"parameter-efficient-quantized-mixture-of","title":"Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis","date":"2024-08-27","arxiv_id":"2408.15305","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategic-optimization-and-challenges-of","title":"Strategic Optimization and Challenges of Large Language Models in Object-Oriented Programming","date":"2024-08-27","arxiv_id":"2408.14834","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-benefits-of-balance-from-information","title":"The Benefits of Balance: From Information Projections to Variance Reduction","date":"2024-08-27","arxiv_id":"2408.15065","n_code_links":0,"syntology":null},{"paper":"/paper/the-mamba-in-the-llama-distilling-and","slug":"the-mamba-in-the-llama-distilling-and","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","date":"2024-08-27","arxiv_id":"2408.15237","n_code_links":2,"syntology":{"ran":9,"of":14,"n_ran_checked":7,"n_instrument":2,"unverified":5,"pointer_only":5,"phrase":"9 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["itsdaniele/speculative_mamba","jxiw/mambainllama"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-uniqueness-of-llama3-70b-with-per-channel","title":"The Uniqueness of LLaMA3-70B Series with Per-Channel Quantization","date":"2024-08-27","arxiv_id":"2408.15301","n_code_links":0,"syntology":null},{"paper":"/paper/toursynbio-a-multi-modal-large-model-and","slug":"toursynbio-a-multi-modal-large-model-and","title":"TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering","date":"2024-08-27","arxiv_id":"2408.15299","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-visual-reasoning-by-vision-language","title":"Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis","date":"2024-08-27","arxiv_id":"2409.00106","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-detection-leveraging-large-language","title":"Beyond Detection: Leveraging Large Language Models for Cyber Attack Prediction in IoT Networks","date":"2024-08-26","arxiv_id":"2408.14045","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaknet-discontinuity-resilient-multi-scale","title":"BreakNet: Discontinuity-Resilient Multi-Scale Transformer Segmentation of Retinal Layers","date":"2024-08-26","arxiv_id":"2408.14606","n_code_links":0,"syntology":null},{"paper":"/paper/chartom-a-visual-theory-of-mind-benchmark-for","slug":"chartom-a-visual-theory-of-mind-benchmark-for","title":"CHARTOM: A Visual Theory-of-Mind Benchmark for Multimodal Large Language Models","date":"2024-08-26","arxiv_id":"2408.14419","n_code_links":1,"syntology":null},{"paper":"/paper/msfmamba-multi-scale-feature-fusion-state","slug":"msfmamba-multi-scale-feature-fusion-state","title":"MSFMamba: Multi-Scale Feature Fusion State Space Model for Multi-Source Remote Sensing Image Classification","date":"2024-08-26","arxiv_id":"2408.14255","n_code_links":2,"syntology":null},{"paper":null,"slug":"probing-causality-manipulation-of-large","title":"Probing Causality Manipulation of Large Language Models","date":"2024-08-26","arxiv_id":"2408.14380","n_code_links":0,"syntology":null},{"paper":"/paper/question-answering-system-of-bridge-design","slug":"question-answering-system-of-bridge-design","title":"Question answering system of bridge design specification based on large language model","date":"2024-08-26","arxiv_id":"2408.13282","n_code_links":1,"syntology":null},{"paper":null,"slug":"rate-distortion-perception-controllable-joint","title":"Rate-Distortion-Perception Controllable Joint Source-Channel Coding for High-Fidelity Generative Communications","date":"2024-08-26","arxiv_id":"2408.14127","n_code_links":0,"syntology":null},{"paper":null,"slug":"reprogramming-foundational-large-language","title":"Reprogramming Foundational Large Language Models(LLMs) for Enterprise Adoption for Spatio-Temporal Forecasting Applications: Unveiling a New Era in Copilot-Guided Cross-Modal Time Series Representation Learning","date":"2024-08-26","arxiv_id":"2408.14387","n_code_links":0,"syntology":null},{"paper":null,"slug":"satellite-sunroof-high-res-digital-surface","title":"Satellite Sunroof: High-res Digital Surface Models and Roof Segmentation for Global Solar Mapping","date":"2024-08-26","arxiv_id":"2408.14400","n_code_links":0,"syntology":null},{"paper":"/paper/3d-rcnet-learning-from-transformer-to-build-a","slug":"3d-rcnet-learning-from-transformer-to-build-a","title":"3D-RCNet: Learning from Transformer to Build a 3D Relational ConvNet for Hyperspectral Image Classification","date":"2024-08-25","arxiv_id":"2408.13728","n_code_links":1,"syntology":null},{"paper":null,"slug":"bidirectional-awareness-induction-in","title":"Bidirectional Awareness Induction in Autoregressive Seq2Seq Models","date":"2024-08-25","arxiv_id":"2408.13959","n_code_links":0,"syntology":null},{"paper":null,"slug":"cnn-transformer-rectified-collaborative","title":"CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation","date":"2024-08-25","arxiv_id":"2408.13698","n_code_links":0,"syntology":null},{"paper":"/paper/codegraph-enhancing-graph-reasoning-of-llms","slug":"codegraph-enhancing-graph-reasoning-of-llms","title":"CodeGraph: Enhancing Graph Reasoning of LLMs with Code","date":"2024-08-25","arxiv_id":"2408.13863","n_code_links":1,"syntology":null},{"paper":"/paper/extremely-fine-grained-visual-classification","slug":"extremely-fine-grained-visual-classification","title":"Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild","date":"2024-08-25","arxiv_id":"2408.13774","n_code_links":1,"syntology":null},{"paper":"/paper/flexible-game-playing-ai-with-alphavit","slug":"flexible-game-playing-ai-with-alphavit","title":"AlphaViT: A Flexible Game-Playing AI for Multiple Games and Variable Board Sizes","date":"2024-08-25","arxiv_id":"2408.13871","n_code_links":1,"syntology":null},{"paper":null,"slug":"lowclip-adapting-the-clip-model-architecture","title":"LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval Task","date":"2024-08-25","arxiv_id":"2408.13909","n_code_links":0,"syntology":null},{"paper":null,"slug":"shifted-window-fourier-transform-and","title":"Shifted Window Fourier Transform And Retention For Image Captioning","date":"2024-08-25","arxiv_id":"2408.13963","n_code_links":0,"syntology":null},{"paper":"/paper/vision-language-and-large-language-model","slug":"vision-language-and-large-language-model","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","date":"2024-08-25","arxiv_id":"2409.00084","n_code_links":1,"syntology":null},{"paper":"/paper/a-law-of-next-token-prediction-in-large","slug":"a-law-of-next-token-prediction-in-large","title":"A Law of Next-Token Prediction in Large Language Models","date":"2024-08-24","arxiv_id":"2408.13442","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hornhehhf/llm-ell"],"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":["official"]}}},{"paper":null,"slug":"cost-aware-uncertainty-reduction-in-schema","title":"Prompt-Matcher: Leveraging Large Models to Reduce Uncertainty in Schema Matching Results","date":"2024-08-24","arxiv_id":"2408.14507","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-multi-head-convolutional-encoders","title":"Integrating Multi-Head Convolutional Encoders with Cross-Attention for Improved SPARQL Query Translation","date":"2024-08-24","arxiv_id":"2408.13432","n_code_links":0,"syntology":null},{"paper":null,"slug":"iqa-eval-automatic-evaluation-of-human-model","title":"IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering","date":"2024-08-24","arxiv_id":"2408.13545","n_code_links":0,"syntology":null},{"paper":"/paper/pandora-s-box-or-aladdin-s-lamp-a","slug":"pandora-s-box-or-aladdin-s-lamp-a","title":"Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models","date":"2024-08-24","arxiv_id":"2408.13533","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jinyangwu/NoiserBench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"probing-the-robustness-of-vision-language","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","date":"2024-08-24","arxiv_id":"2408.13461","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-video-deblurring-with-wavelet","slug":"rethinking-video-deblurring-with-wavelet","title":"Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model","date":"2024-08-24","arxiv_id":"2408.13459","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["chen-rao/vd-diff"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"topological-gcn-for-improving-detection-of","title":"Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images","date":"2024-08-24","arxiv_id":"2408.13495","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilizing-large-language-models-for-named","title":"Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative Study","date":"2024-08-24","arxiv_id":"2408.13501","n_code_links":0,"syntology":null},{"paper":"/paper/variational-autoencoder-for-anomaly-detection","slug":"variational-autoencoder-for-anomaly-detection","title":"Variational Autoencoder for Anomaly Detection: A Comparative Study","date":"2024-08-24","arxiv_id":"2408.13561","n_code_links":1,"syntology":null},{"paper":null,"slug":"accuracy-improvement-of-cell-image","title":"Accuracy Improvement of Cell Image Segmentation Using Feedback Former","date":"2024-08-23","arxiv_id":"2408.12974","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-exposure-from-llm-apps-an-in-depth","title":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","date":"2024-08-23","arxiv_id":"2408.13247","n_code_links":0,"syntology":null},{"paper":null,"slug":"eavit-external-attention-vision-transformer","title":"EAViT: External Attention Vision Transformer for Audio Classification","date":"2024-08-23","arxiv_id":"2408.13201","n_code_links":0,"syntology":null},{"paper":"/paper/image-segmentation-in-foundation-model-era-a","slug":"image-segmentation-in-foundation-model-era-a","title":"Image Segmentation in Foundation Model Era: A Survey","date":"2024-08-23","arxiv_id":"2408.12957","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-graph-modeling-driven-large","title":"Knowledge Graph Modeling-Driven Large Language Model Operating System (LLM OS) for Task Automation in Process Engineering Problem-Solving","date":"2024-08-23","arxiv_id":"2408.14494","n_code_links":0,"syntology":null},{"paper":null,"slug":"qd-vmr-query-debiasing-with-contextual","title":"QD-VMR: Query Debiasing with Contextual Understanding Enhancement for Video Moment Retrieval","date":"2024-08-23","arxiv_id":"2408.12981","n_code_links":0,"syntology":null},{"paper":null,"slug":"state-of-the-art-fails-in-the-art-of-damage","title":"State-of-the-Art Fails in the Art of Damage Detection","date":"2024-08-23","arxiv_id":"2408.12953","n_code_links":0,"syntology":null},{"paper":"/paper/systematic-evaluation-of-llm-as-a-judge-in","slug":"systematic-evaluation-of-llm-as-a-judge-in","title":"Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates","date":"2024-08-23","arxiv_id":"2408.13006","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"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) · 1 unverified","official":{"repos":["shenghh2015/llm-judge-eval"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vfm-det-towards-high-performance-vehicle","slug":"vfm-det-towards-high-performance-vehicle","title":"VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models","date":"2024-08-23","arxiv_id":"2408.13031","n_code_links":1,"syntology":null},{"paper":null,"slug":"zeoformer-coarse-grained-periodic-graph","title":"PDDFormer: Pairwise Distance Distribution Graph Transformer for Crystal Material Property Prediction","date":"2024-08-23","arxiv_id":"2408.12984","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-driven-transformer-model-for-fault","title":"AI-driven Transformer Model for Fault Prediction in Non-Linear Dynamic Automotive System","date":"2024-08-22","arxiv_id":"2408.12638","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-understand-social-norms-in","title":"Can LLMs Understand Social Norms in Autonomous Driving Games?","date":"2024-08-22","arxiv_id":"2408.12680","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-infield-agriculture-with","title":"Enhanced Infield Agriculture with Interpretable Machine Learning Approaches for Crop Classification","date":"2024-08-22","arxiv_id":"2408.12426","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-based-automated-program-repair","title":"Enhancing Automated Program Repair with Solution Design","date":"2024-08-22","arxiv_id":"2408.12056","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-multi-hop-reasoning-through","title":"Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing","date":"2024-08-22","arxiv_id":"2408.12456","n_code_links":0,"syntology":null},{"paper":"/paper/graph-retrieval-augmented-trustworthiness","slug":"graph-retrieval-augmented-trustworthiness","title":"GRATR: Zero-Shot Evidence Graph Retrieval-Augmented Trustworthiness Reasoning","date":"2024-08-22","arxiv_id":"2408.12333","n_code_links":1,"syntology":null},{"paper":"/paper/jamba-1-5-hybrid-transformer-mamba-models-at","slug":"jamba-1-5-hybrid-transformer-mamba-models-at","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","date":"2024-08-22","arxiv_id":"2408.12570","n_code_links":2,"syntology":null},{"paper":null,"slug":"large-language-models-as-foundations-for-next","title":"Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment","date":"2024-08-22","arxiv_id":"2408.12194","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-are-not-zero-shot-reasoners-for","title":"LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction","date":"2024-08-22","arxiv_id":"2408.12249","n_code_links":0,"syntology":null},{"paper":null,"slug":"meddit-a-knowledge-controlled-diffusion","title":"MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient","date":"2024-08-22","arxiv_id":"2408.12236","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-performance-how-compact-models","title":"Optimizing Performance: How Compact Models Match or Exceed GPT's Classification Capabilities through Fine-Tuning","date":"2024-08-22","arxiv_id":"2409.11408","n_code_links":0,"syntology":null},{"paper":null,"slug":"rulealign-making-large-language-models-better","title":"RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment","date":"2024-08-22","arxiv_id":"2408.12579","n_code_links":0,"syntology":null},{"paper":"/paper/sapiens-foundation-for-human-vision-models","slug":"sapiens-foundation-for-human-vision-models","title":"Sapiens: Foundation for Human Vision Models","date":"2024-08-22","arxiv_id":"2408.12569","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/towards-evaluating-and-building-versatile","slug":"towards-evaluating-and-building-versatile","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","date":"2024-08-22","arxiv_id":"2408.12547","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"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) · 0 unverified","official":{"repos":["magic-ai4med/meds-ins"],"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":"transformers-as-approximations-of-solomonoff","title":"Transformers As Approximations of Solomonoff Induction","date":"2024-08-22","arxiv_id":"2408.12065","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlearning-trojans-in-large-language-models-a","title":"Unlearning Trojans in Large Language Models: A Comparison Between Natural Language and Source Code","date":"2024-08-22","arxiv_id":"2408.12416","n_code_links":0,"syntology":null},{"paper":null,"slug":"xgen-videosyn-1-high-fidelity-text-to-video","title":"xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations","date":"2024-08-22","arxiv_id":"2408.12590","n_code_links":0,"syntology":null},{"paper":"/paper/a-quick-trustworthy-spectral-detection-q-a","slug":"a-quick-trustworthy-spectral-detection-q-a","title":"A Quick, trustworthy spectral knowledge Q&A system leveraging retrieval-augmented generation on LLM","date":"2024-08-21","arxiv_id":"2408.11557","n_code_links":1,"syntology":null},{"paper":"/paper/ancient-wisdom-modern-tools-exploring","slug":"ancient-wisdom-modern-tools-exploring","title":"Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian Philosophy","date":"2024-08-21","arxiv_id":"2408.11903","n_code_links":1,"syntology":null},{"paper":null,"slug":"applying-and-evaluating-large-language-models","title":"Applying and Evaluating Large Language Models in Mental Health Care: A Scoping Review of Human-Assessed Generative Tasks","date":"2024-08-21","arxiv_id":"2408.11288","n_code_links":0,"syntology":null},{"paper":null,"slug":"burextract-llama-an-llm-for-clinical-concept","title":"BURExtract-Llama: An LLM for Clinical Concept Extraction in Breast Ultrasound Reports","date":"2024-08-21","arxiv_id":"2408.11334","n_code_links":0,"syntology":null},{"paper":null,"slug":"d-rmgpt-robot-assisted-collaborative-tasks","title":"D-RMGPT: Robot-assisted collaborative tasks driven by large multimodal models","date":"2024-08-21","arxiv_id":"2408.11761","n_code_links":0,"syntology":null},{"paper":"/paper/dabench-a-benchmark-dataset-for-data-driven","slug":"dabench-a-benchmark-dataset-for-data-driven","title":"A Benchmark for AI-based Weather Data Assimilation","date":"2024-08-21","arxiv_id":"2408.11438","n_code_links":1,"syntology":null},{"paper":"/paper/doctabqa-answering-questions-from-long","slug":"doctabqa-answering-questions-from-long","title":"DocTabQA: Answering Questions from Long Documents Using Tables","date":"2024-08-21","arxiv_id":"2408.11490","n_code_links":1,"syntology":null},{"paper":null,"slug":"energy-estimation-of-last-mile-electric","title":"Energy Estimation of Last Mile Electric Vehicle Routes","date":"2024-08-21","arxiv_id":"2408.12006","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-feature","title":"Exploring Large Language Models for Feature Selection: A Data-centric Perspective","date":"2024-08-21","arxiv_id":"2408.12025","n_code_links":0,"syntology":null},{"paper":"/paper/fate-focal-modulated-attention-encoder-for","slug":"fate-focal-modulated-attention-encoder-for","title":"FATE: Focal-modulated Attention Encoder for Temperature Prediction","date":"2024-08-21","arxiv_id":"2408.11336","n_code_links":1,"syntology":null},{"paper":"/paper/hmt-unet-a-hybird-mamba-transformer-vision","slug":"hmt-unet-a-hybird-mamba-transformer-vision","title":"HMT-UNet: A hybird Mamba-Transformer Vision UNet for Medical Image Segmentation","date":"2024-08-21","arxiv_id":"2408.11289","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-fine-tuned-retrieval-augmented","slug":"leveraging-fine-tuned-retrieval-augmented","title":"Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards","date":"2024-08-21","arxiv_id":"2408.11775","n_code_links":1,"syntology":null},{"paper":null,"slug":"macformer-transformer-with-random-maclaurin","title":"Macformer: Transformer with Random Maclaurin Feature Attention","date":"2024-08-21","arxiv_id":"2408.11656","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixed-sparsity-training-achieving-4-times","title":"Mixed Sparsity Training: Achieving 4$\\times$ FLOP Reduction for Transformer Pretraining","date":"2024-08-21","arxiv_id":"2408.11746","n_code_links":0,"syntology":null},{"paper":"/paper/oapt-offset-aware-partition-transformer-for","slug":"oapt-offset-aware-partition-transformer-for","title":"OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal","date":"2024-08-21","arxiv_id":"2408.11480","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":7,"n_instrument":1,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["qmoq/oapt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-learnable-parameters-of-optimal-and","title":"On Learnable Parameters of Optimal and Suboptimal Deep Learning Models","date":"2024-08-21","arxiv_id":"2408.11720","n_code_links":0,"syntology":null},{"paper":null,"slug":"permitqa-a-benchmark-for-retrieval-augmented","title":"WeQA: A Benchmark for Retrieval Augmented Generation in Wind Energy Domain","date":"2024-08-21","arxiv_id":"2408.11800","n_code_links":0,"syntology":null},{"paper":"/paper/positional-prompt-tuning-for-efficient-3d","slug":"positional-prompt-tuning-for-efficient-3d","title":"Positional Prompt Tuning for Efficient 3D Representation Learning","date":"2024-08-21","arxiv_id":"2408.11567","n_code_links":1,"syntology":null},{"paper":null,"slug":"rag-optimized-tibetan-tourism-llms-enhancing","title":"RAG-Optimized Tibetan Tourism LLMs: Enhancing Accuracy and Personalization","date":"2024-08-21","arxiv_id":"2408.12003","n_code_links":0,"syntology":null},{"paper":"/paper/raglab-a-modular-and-research-oriented","slug":"raglab-a-modular-and-research-oriented","title":"RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation","date":"2024-08-21","arxiv_id":"2408.11381","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-self-contained-negation-test-set","title":"The Self-Contained Negation Test Set","date":"2024-08-21","arxiv_id":"2408.11469","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-evaluating-large-language-models-on","title":"SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding","date":"2024-08-21","arxiv_id":"2408.11319","n_code_links":0,"syntology":null},{"paper":"/paper/unlocking-adversarial-suffix-optimization","slug":"unlocking-adversarial-suffix-optimization","title":"Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer","date":"2024-08-21","arxiv_id":"2408.11313","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":["lenijwp/eclipse"],"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":null,"slug":"classification-of-endoscopy-and-video-capsule","title":"Classification of Endoscopy and Video Capsule Images using CNN-Transformer Model","date":"2024-08-20","arxiv_id":"2408.10733","n_code_links":0,"syntology":null},{"paper":null,"slug":"crafting-tomorrow-s-headlines-neural-news","title":"Crafting Tomorrow's Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian","date":"2024-08-20","arxiv_id":"2408.10724","n_code_links":0,"syntology":null},{"paper":null,"slug":"ctp-llm-clinical-trial-phase-transition","title":"CTP-LLM: Clinical Trial Phase Transition Prediction Using Large Language Models","date":"2024-08-20","arxiv_id":"2408.10995","n_code_links":0,"syntology":null},{"paper":null,"slug":"dr-academy-a-benchmark-for-evaluating","title":"Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models","date":"2024-08-20","arxiv_id":"2408.10947","n_code_links":0,"syntology":null},{"paper":"/paper/edgenat-transformer-for-efficient-edge","slug":"edgenat-transformer-for-efficient-edge","title":"EdgeNAT: Transformer for Efficient Edge Detection","date":"2024-08-20","arxiv_id":"2408.10527","n_code_links":1,"syntology":null},{"paper":"/paper/hired-attention-guided-token-dropping-for","slug":"hired-attention-guided-token-dropping-for","title":"HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models","date":"2024-08-20","arxiv_id":"2408.10945","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["hasanar1f/hired"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-well-do-large-language-models-serve-as","title":"How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python?","date":"2024-08-20","arxiv_id":"2408.10495","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-multi-modal-input-token-mixer","title":"Integrating Multi-Modal Input Token Mixer Into Mamba-Based Decision Models: Decision MetaMamba","date":"2024-08-20","arxiv_id":"2408.10517","n_code_links":0,"syntology":null},{"paper":"/paper/language-modeling-on-tabular-data-a-survey-of","slug":"language-modeling-on-tabular-data-a-survey-of","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","date":"2024-08-20","arxiv_id":"2408.10548","n_code_links":1,"syntology":null},{"paper":"/paper/mambaevt-event-stream-based-visual-object","slug":"mambaevt-event-stream-based-visual-object","title":"MambaEVT: Event Stream based Visual Object Tracking using State Space Model","date":"2024-08-20","arxiv_id":"2408.10487","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["event-ahu/mambaevt"],"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":["official"]}}},{"paper":"/paper/navigating-spatio-temporal-heterogeneity-a","slug":"navigating-spatio-temporal-heterogeneity-a","title":"Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting","date":"2024-08-20","arxiv_id":"2408.10822","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-potential-of-open-vocabulary-models","title":"On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes","date":"2024-08-20","arxiv_id":"2408.11221","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-finllms-open-multimodal-large-language","title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","date":"2024-08-20","arxiv_id":"2408.11878","n_code_links":0,"syntology":null},{"paper":"/paper/out-of-distribution-detection-with-attention","slug":"out-of-distribution-detection-with-attention","title":"Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification","date":"2024-08-20","arxiv_id":"2408.11237","n_code_links":1,"syntology":null}],"record_sha256":"fb0fafc0089901fe31d30429fa4a8633d23e6b3ebc551800cdd86c7872924a6e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}