{"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/45","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":45,"pages_in_order":249,"rows_per_page":100,"rows":[4401,4500],"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/44","next":"/method/multi-head-attention/papers/46","papers":[{"paper":"/paper/rationalyst-pre-training-process-supervision","slug":"rationalyst-pre-training-process-supervision","title":"RATIONALYST: Pre-training Process-Supervision for Improving Reasoning","date":"2024-10-01","arxiv_id":"2410.01044","n_code_links":1,"syntology":null},{"paper":"/paper/robust-traffic-forecasting-against-spatial","slug":"robust-traffic-forecasting-against-spatial","title":"Robust Traffic Forecasting against Spatial Shift over Years","date":"2024-10-01","arxiv_id":"2410.00373","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dreamzz5/st-expert"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/sparse-attention-decomposition-applied-to","slug":"sparse-attention-decomposition-applied-to","title":"Sparse Attention Decomposition Applied to Circuit Tracing","date":"2024-10-01","arxiv_id":"2410.00340","n_code_links":1,"syntology":null},{"paper":"/paper/stgformer-efficient-spatiotemporal-graph","slug":"stgformer-efficient-spatiotemporal-graph","title":"STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting","date":"2024-10-01","arxiv_id":"2410.00385","n_code_links":1,"syntology":null},{"paper":"/paper/tfct-i2p-three-stream-fusion-network-with","slug":"tfct-i2p-three-stream-fusion-network-with","title":"TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration","date":"2024-10-01","arxiv_id":"2410.00360","n_code_links":1,"syntology":null},{"paper":"/paper/transresnet-integrating-the-strengths-of-vits","slug":"transresnet-integrating-the-strengths-of-vits","title":"TransResNet: Integrating the Strengths of ViTs and CNNs for High Resolution Medical Image Segmentation via Feature Grafting","date":"2024-10-01","arxiv_id":"2410.00986","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-looming-replication-crisis-in-evaluating","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","date":"2024-09-30","arxiv_id":"2409.20303","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-methodology-for-explainable-large-language","title":"A Methodology for Explainable Large Language Models with Integrated Gradients and Linguistic Analysis in Text Classification","date":"2024-09-30","arxiv_id":"2410.00250","n_code_links":0,"syntology":null},{"paper":null,"slug":"ace-all-round-creator-and-editor-following","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","date":"2024-09-30","arxiv_id":"2410.00086","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-llms-for-the-medical-domain-in","title":"Adapting LLMs for the Medical Domain in Portuguese: A Study on Fine-Tuning and Model Evaluation","date":"2024-09-30","arxiv_id":"2410.00163","n_code_links":0,"syntology":null},{"paper":"/paper/asquery-a-query-based-model-for-action","slug":"asquery-a-query-based-model-for-action","title":"ASQuery: A Query-based Model for Action Segmentation","date":"2024-09-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bsharedrag-backbone-shared-retrieval","title":"BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain","date":"2024-09-30","arxiv_id":"2409.20075","n_code_links":0,"syntology":null},{"paper":null,"slug":"cbam-swint-bl-small-rail-surface-detect","title":"CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement","date":"2024-09-30","arxiv_id":"2409.20113","n_code_links":0,"syntology":null},{"paper":"/paper/climb-an-ai-enabled-partner-for-clinical","slug":"climb-an-ai-enabled-partner-for-clinical","title":"CliMB: An AI-enabled Partner for Clinical Predictive Modeling","date":"2024-09-30","arxiv_id":"2410.03736","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":["vanderschaarlab/climb"],"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":"depression-detection-in-social-media-posts-1","title":"Depression detection in social media posts using transformer-based models and auxiliary features","date":"2024-09-30","arxiv_id":"2409.20048","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-fairness-of-task-adaptive","slug":"evaluating-the-fairness-of-task-adaptive","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","date":"2024-09-30","arxiv_id":"2410.00179","n_code_links":1,"syntology":null},{"paper":null,"slug":"gtranspdm-a-graph-embedded-transformer-with","title":"GTransPDM: A Graph-embedded Transformer with Positional Decoupling for Pedestrian Crossing Intention Prediction","date":"2024-09-30","arxiv_id":"2409.20223","n_code_links":0,"syntology":null},{"paper":null,"slug":"ingest-and-ground-dispelling-hallucinations","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","date":"2024-09-30","arxiv_id":"2410.02825","n_code_links":0,"syntology":null},{"paper":null,"slug":"maskmamba-a-hybrid-mamba-transformer-model","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","date":"2024-09-30","arxiv_id":"2409.19937","n_code_links":0,"syntology":null},{"paper":null,"slug":"modelando-procesos-cognitivos-de-la-lectura","title":"Modelando procesos cognitivos de la lectura natural con GPT-2","date":"2024-09-30","arxiv_id":"2409.20174","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-large-uni-and-multi-modal-models-for","title":"Exploring Social Media Image Categorization Using Large Models with Different Adaptation Methods: A Case Study on Cultural Nature's Contributions to People","date":"2024-09-30","arxiv_id":"2410.00275","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-planning-abilities-of-openai-s-o1","slug":"on-the-planning-abilities-of-openai-s-o1","title":"On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability","date":"2024-09-30","arxiv_id":"2409.19924","n_code_links":2,"syntology":null},{"paper":"/paper/qaencoder-towards-aligned-representation","slug":"qaencoder-towards-aligned-representation","title":"QAEncoder: Towards Aligned Representation Learning in Question Answering System","date":"2024-09-30","arxiv_id":"2409.20434","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-open-vocabulary-semantic-segmentation","title":"Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels","date":"2024-09-30","arxiv_id":"2409.19846","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-low-resourced","title":"Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers","date":"2024-09-29","arxiv_id":"2409.19566","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-examples-for-dna-classification","title":"Adversarial Examples for DNA Classification","date":"2024-09-29","arxiv_id":"2409.19788","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-models-learn-skill-composition-from","title":"Can Models Learn Skill Composition from Examples?","date":"2024-09-29","arxiv_id":"2409.19808","n_code_links":0,"syntology":null},{"paper":null,"slug":"discerning-the-chaos-detecting-adversarial","title":"Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises","date":"2024-09-29","arxiv_id":"2409.19619","n_code_links":0,"syntology":null},{"paper":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gentel-safe-a-unified-benchmark-and-shielding","title":"GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks","date":"2024-09-29","arxiv_id":"2409.19521","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-is-all-you-need-gradient-based","slug":"gradient-is-all-you-need-gradient-based","title":"DATransNet: Dynamic Attention Transformer Network for Infrared Small Target Detection","date":"2024-09-29","arxiv_id":"2409.19599","n_code_links":1,"syntology":null},{"paper":null,"slug":"infantcrynet-a-data-driven-framework-for","title":"InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries","date":"2024-09-29","arxiv_id":"2409.19689","n_code_links":0,"syntology":null},{"paper":null,"slug":"medhalu-hallucinations-in-responses-to","title":"MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models","date":"2024-09-29","arxiv_id":"2409.19492","n_code_links":0,"syntology":null},{"paper":null,"slug":"pear-position-embedding-agnostic-attention-re","title":"PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead","date":"2024-09-29","arxiv_id":"2409.19745","n_code_links":0,"syntology":null},{"paper":null,"slug":"see-then-tell-enhancing-key-information","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","date":"2024-09-29","arxiv_id":"2409.19573","n_code_links":0,"syntology":null},{"paper":"/paper/spiking-transformer-with-spatial-temporal","slug":"spiking-transformer-with-spatial-temporal","title":"Spiking Transformer with Spatial-Temporal Attention","date":"2024-09-29","arxiv_id":"2409.19764","n_code_links":1,"syntology":null},{"paper":"/paper/analog-in-memory-computing-attention","slug":"analog-in-memory-computing-attention","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","date":"2024-09-28","arxiv_id":"2409.19315","n_code_links":1,"syntology":null},{"paper":null,"slug":"deneb-a-hallucination-robust-automatic","title":"DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning","date":"2024-09-28","arxiv_id":"2409.19255","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-federated-intrusion-detection-in-5g","slug":"efficient-federated-intrusion-detection-in-5g","title":"Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based model","date":"2024-09-28","arxiv_id":"2409.19390","n_code_links":1,"syntology":null},{"paper":"/paper/insightbuddy-ai-medication-extraction-and","slug":"insightbuddy-ai-medication-extraction-and","title":"INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning","date":"2024-09-28","arxiv_id":"2409.19467","n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-atlas-brain-network-classification","title":"Multi-Atlas Brain Network Classification through Consistency Distillation and Complementary Information Fusion","date":"2024-09-28","arxiv_id":"2410.08228","n_code_links":0,"syntology":null},{"paper":null,"slug":"unveil-benign-overfitting-for-transformer-in","title":"Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization","date":"2024-09-28","arxiv_id":"2409.19345","n_code_links":0,"syntology":null},{"paper":null,"slug":"aipatient-simulating-patients-with-ehrs-and","title":"AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow","date":"2024-09-27","arxiv_id":"2409.18924","n_code_links":0,"syntology":null},{"paper":null,"slug":"charting-the-future-using-chart-question","title":"Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations","date":"2024-09-27","arxiv_id":"2409.18764","n_code_links":0,"syntology":null},{"paper":"/paper/cottention-linear-transformers-with-cosine","slug":"cottention-linear-transformers-with-cosine","title":"Cottention: Linear Transformers With Cosine Attention","date":"2024-09-27","arxiv_id":"2409.18747","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gmongaras/Cottention_Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"experimental-evaluation-of-machine-learning","title":"Experimental Evaluation of Machine Learning Models for Goal-oriented Customer Service Chatbot with Pipeline Architecture","date":"2024-09-27","arxiv_id":"2409.18568","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-effective-is-pre-training-of-large-masked","title":"How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?","date":"2024-09-27","arxiv_id":"2409.18536","n_code_links":0,"syntology":null},{"paper":"/paper/improving-visual-object-tracking-through","slug":"improving-visual-object-tracking-through","title":"Improving Visual Object Tracking through Visual Prompting","date":"2024-09-27","arxiv_id":"2409.18901","n_code_links":1,"syntology":null},{"paper":"/paper/lml-language-model-learning-a-dataset-for","slug":"lml-language-model-learning-a-dataset-for","title":"LML-DAP: Language Model Learning a Dataset for Data-Augmented Prediction","date":"2024-09-27","arxiv_id":"2409.18957","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-rtl-reinforcement-based-meta-transfer","title":"Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense Reasoning","date":"2024-09-27","arxiv_id":"2409.19075","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-source-hard-and-soft-information-fusion","title":"Multi-Source Hard and Soft Information Fusion Approach for Accurate Cryptocurrency Price Movement Prediction","date":"2024-09-27","arxiv_id":"2409.18895","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-the-silver-bullet-llm-enhanced","title":"Not the Silver Bullet: LLM-enhanced Programming Error Messages are Ineffective in Practice","date":"2024-09-27","arxiv_id":"2409.18661","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-power-of-decision-trees-in-auto","title":"On the Power of Decision Trees in Auto-Regressive Language Modeling","date":"2024-09-27","arxiv_id":"2409.19150","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-nav-exploring-zero-shot-vision-and","title":"Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs","date":"2024-09-27","arxiv_id":"2409.18794","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-then-reweighting-towards-data","slug":"pruning-then-reweighting-towards-data","title":"Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models","date":"2024-09-27","arxiv_id":"2409.19128","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-matching-for-spatio-temporal-action","title":"Query matching for spatio-temporal action detection with query-based object detector","date":"2024-09-27","arxiv_id":"2409.18408","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-mamba-long-context-speech-recognition","title":"Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models","date":"2024-09-27","arxiv_id":"2409.18654","n_code_links":0,"syntology":null},{"paper":null,"slug":"suicide-phenotyping-from-clinical-notes-in","title":"Suicide Phenotyping from Clinical Notes in Safety-Net Psychiatric Hospital Using Multi-Label Classification with Pre-Trained Language Models","date":"2024-09-27","arxiv_id":"2409.18878","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-fuzzy-based-approach-to-predict-human","title":"A Fuzzy-based Approach to Predict Human Interaction by Functional Near-Infrared Spectroscopy","date":"2024-09-26","arxiv_id":"2409.17661","n_code_links":0,"syntology":null},{"paper":"/paper/agmtr-agent-mining-transformer-for-few-shot","slug":"agmtr-agent-mining-transformer-for-few-shot","title":"AgMTR: Agent Mining Transformer for Few-shot Segmentation in Remote Sensing","date":"2024-09-26","arxiv_id":"2409.17453","n_code_links":1,"syntology":null},{"paper":null,"slug":"caspformer-trajectory-prediction-from-bev","title":"CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention","date":"2024-09-26","arxiv_id":"2409.17790","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-unidirectional-bidirectional-and","title":"Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code","date":"2024-09-26","arxiv_id":"2409.17513","n_code_links":0,"syntology":null},{"paper":null,"slug":"dare-diverse-visual-question-answering-with","title":"DARE: Diverse Visual Question Answering with Robustness Evaluation","date":"2024-09-26","arxiv_id":"2409.18023","n_code_links":0,"syntology":null},{"paper":null,"slug":"developing-a-dual-stage-vision-transformer","title":"Developing a Dual-Stage Vision Transformer Model for Lung Disease Classification","date":"2024-09-26","arxiv_id":"2409.18257","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-subframe-splitting-and-spatio","title":"Dynamic Subframe Splitting and Spatio-Temporal Motion Entangled Sparse Attention for RGB-E Tracking","date":"2024-09-26","arxiv_id":"2409.17560","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-in-domain-question-answering-for","title":"Efficient In-Domain Question Answering for Resource-Constrained Environments","date":"2024-09-26","arxiv_id":"2409.17648","n_code_links":0,"syntology":null},{"paper":"/paper/em-net-efficient-channel-and-frequency","slug":"em-net-efficient-channel-and-frequency","title":"EM-Net: Efficient Channel and Frequency Learning with Mamba for 3D Medical Image Segmentation","date":"2024-09-26","arxiv_id":"2409.17675","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zang0902/EM-Net"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"embodied-rag-general-non-parametric-embodied","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","date":"2024-09-26","arxiv_id":"2409.18313","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-tourism-recommender-systems-for","title":"Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generation","date":"2024-09-26","arxiv_id":"2409.18003","n_code_links":0,"syntology":null},{"paper":"/paper/hydravit-stacking-heads-for-a-scalable-vit","slug":"hydravit-stacking-heads-for-a-scalable-vit","title":"HydraViT: Stacking Heads for a Scalable ViT","date":"2024-09-26","arxiv_id":"2409.17978","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":14,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ds-kiel/hydravit"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"just-say-what-you-want-only-prompting-self","title":"Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization","date":"2024-09-26","arxiv_id":"2409.17534","n_code_links":0,"syntology":null},{"paper":"/paper/maskllm-learnable-semi-structured-sparsity","slug":"maskllm-learnable-semi-structured-sparsity","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","date":"2024-09-26","arxiv_id":"2409.17481","n_code_links":1,"syntology":{"ran":5,"of":16,"n_ran_checked":5,"n_instrument":0,"unverified":11,"pointer_only":16,"phrase":"5 ran (of which 1 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) · 11 unverified","official":{"repos":["nvlabs/maskllm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":"/paper/multiclimate-multimodal-stance-detection-on","slug":"multiclimate-multimodal-stance-detection-on","title":"MultiClimate: Multimodal Stance Detection on Climate Change Videos","date":"2024-09-26","arxiv_id":"2409.18346","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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["werywjw/multiclimate"],"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/neuropath-a-neural-pathway-transformer-for","slug":"neuropath-a-neural-pathway-transformer-for","title":"NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomes","date":"2024-09-26","arxiv_id":"2409.17510","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Chrisa142857/neuro_detour"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ophthalmic-biomarker-detection-with-parallel","title":"Ophthalmic Biomarker Detection with Parallel Prediction of Transformer and Convolutional Architecture","date":"2024-09-26","arxiv_id":"2409.17788","n_code_links":0,"syntology":null},{"paper":null,"slug":"pedro-parameter-efficient-fine-tuning-with","title":"PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification","date":"2024-09-26","arxiv_id":"2409.17834","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-anchored-text-from-translation","title":"Predicting Anchored Text from Translation Memories for Machine Translation Using Deep Learning Methods","date":"2024-09-26","arxiv_id":"2409.17939","n_code_links":0,"syntology":null},{"paper":"/paper/retrospective-comparative-analysis-of","slug":"retrospective-comparative-analysis-of","title":"Retrospective Comparative Analysis of Prostate Cancer In-Basket Messages: Responses from Closed-Domain LLM vs. Clinical Teams","date":"2024-09-26","arxiv_id":"2409.18290","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-monocular-depth-estimation-6","title":"Self-supervised Monocular Depth Estimation with Large Kernel Attention","date":"2024-09-26","arxiv_id":"2409.17895","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-pretraining-for-1","slug":"self-supervised-pretraining-for-1","title":"Self-supervised Pretraining for Cardiovascular Magnetic Resonance Cine Segmentation","date":"2024-09-26","arxiv_id":"2409.18100","n_code_links":1,"syntology":null},{"paper":null,"slug":"t3-a-novel-zero-shot-transfer-learning","title":"T3: A Novel Zero-shot Transfer Learning Framework Iteratively Training on an Assistant Task for a Target Task","date":"2024-09-26","arxiv_id":"2409.17640","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-application-of-gpt-4-in-grading-design","title":"The application of GPT-4 in grading design university students' assignment and providing feedback: An exploratory study","date":"2024-09-26","arxiv_id":"2409.17698","n_code_links":0,"syntology":null},{"paper":"/paper/unifying-dimensions-a-linear-adaptive","slug":"unifying-dimensions-a-linear-adaptive","title":"Unifying Dimensions: A Linear Adaptive Approach to Lightweight Image Super-Resolution","date":"2024-09-26","arxiv_id":"2409.17597","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-prompting-based-representation-learning","title":"A Prompting-Based Representation Learning Method for Recommendation with Large Language Models","date":"2024-09-25","arxiv_id":"2409.16674","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-turing-test-can-gpt-4-sway-experts","title":"Beyond Turing Test: Can GPT-4 Sway Experts' Decisions?","date":"2024-09-25","arxiv_id":"2409.16710","n_code_links":0,"syntology":null},{"paper":null,"slug":"block-expanded-dinoret-adapting-natural","title":"Block Expanded DINORET: Adapting Natural Domain Foundation Models for Retinal Imaging Without Catastrophic Forgetting","date":"2024-09-25","arxiv_id":"2409.17332","n_code_links":0,"syntology":null},{"paper":"/paper/codeinsight-a-curated-dataset-of-practical","slug":"codeinsight-a-curated-dataset-of-practical","title":"CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow","date":"2024-09-25","arxiv_id":"2409.16819","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-and-machine-learning-advancing","title":"Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Handy Appetizer","date":"2024-09-25","arxiv_id":"2409.17120","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-automatic-keyphrase-labelling-with","title":"Enhancing Automatic Keyphrase Labelling with Text-to-Text Transfer Transformer (T5) Architecture: A Framework for Keyphrase Generation and Filtering","date":"2024-09-25","arxiv_id":"2409.16760","n_code_links":0,"syntology":null},{"paper":null,"slug":"going-beyond-u-net-assessing-vision","title":"Going Beyond U-Net: Assessing Vision Transformers for Semantic Segmentation in Microscopy Image Analysis","date":"2024-09-25","arxiv_id":"2409.16940","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-boosting-decision-trees-on-medical","slug":"gradient-boosting-decision-trees-on-medical","title":"Gradient Boosting Decision Trees on Medical Diagnosis over Tabular Data","date":"2024-09-25","arxiv_id":"2410.03705","n_code_links":1,"syntology":null},{"paper":"/paper/hvt-a-comprehensive-vision-framework-for","slug":"hvt-a-comprehensive-vision-framework-for","title":"HVT: A Comprehensive Vision Framework for Learning in Non-Euclidean Space","date":"2024-09-25","arxiv_id":"2409.16897","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-ocr-sensitive-neurons-to","slug":"investigating-ocr-sensitive-neurons-to","title":"Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical Documents","date":"2024-09-25","arxiv_id":"2409.16934","n_code_links":1,"syntology":null},{"paper":null,"slug":"llama-sciq-an-educational-chatbot-for","title":"LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ","date":"2024-09-25","arxiv_id":"2409.16779","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-stationary-bert-exploring-augmented-imu","title":"Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition","date":"2024-09-25","arxiv_id":"2409.16730","n_code_links":0,"syntology":null},{"paper":"/paper/post-hoc-reward-calibration-a-case-study-on","slug":"post-hoc-reward-calibration-a-case-study-on","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","date":"2024-09-25","arxiv_id":"2409.17407","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":["zeroyuhuang/reward-calibration"],"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":"pre-trained-graphformer-based-ranking-at-web","title":"Pre-trained Graphformer-based Ranking at Web-scale Search (Extended Abstract)","date":"2024-09-25","arxiv_id":"2409.16590","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-omissions-and-distortions-in","title":"Probing Omissions and Distortions in Transformer-based RDF-to-Text Models","date":"2024-09-25","arxiv_id":"2409.16707","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantum-classical-sentiment-analysis","title":"Quantum-Classical Sentiment Analysis","date":"2024-09-25","arxiv_id":"2409.16928","n_code_links":0,"syntology":null},{"paper":null,"slug":"severity-prediction-in-mental-health-llm","title":"Severity Prediction in Mental Health: LLM-based Creation, Analysis, Evaluation of a Novel Multilingual Dataset","date":"2024-09-25","arxiv_id":"2409.17397","n_code_links":0,"syntology":null}],"record_sha256":"c3b67148cb25a3350aeb9b85567e80cc1b3a95b16e703ac560863e7bc5e73ad9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}