{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/attention/papers/13","list_of":"/method/attention","method":"Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":13,"pages_in_order":316,"rows_per_page":100,"rows":[1201,1300],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention","prev":"/method/attention/papers/12","next":"/method/attention/papers/14","papers":[{"paper":null,"slug":"knowledge-informed-deep-learning-for","title":"Knowledge-Informed Deep Learning for Irrigation Type Mapping from Remote Sensing","date":"2025-05-13","arxiv_id":"2505.08302","n_code_links":0,"syntology":null},{"paper":null,"slug":"ladi-wm-a-latent-diffusion-based-world-model","title":"LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation","date":"2025-05-13","arxiv_id":"2505.11528","n_code_links":0,"syntology":null},{"paper":null,"slug":"lie-group-symmetry-discovery-and-enforcement","title":"Lie Group Symmetry Discovery and Enforcement Using Vector Fields","date":"2025-05-13","arxiv_id":"2505.08219","n_code_links":0,"syntology":null},{"paper":"/paper/lost-in-transmission-when-and-why-llms-fail","slug":"lost-in-transmission-when-and-why-llms-fail","title":"Lost in Transmission: When and Why LLMs Fail to Reason Globally","date":"2025-05-13","arxiv_id":"2505.08140","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"memorization-compression-cycles-improve","title":"Memorization-Compression Cycles Improve Generalization","date":"2025-05-13","arxiv_id":"2505.08727","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-fusion-of-glucose-monitoring-and","title":"Multimodal Fusion of Glucose Monitoring and Food Imagery for Caloric Content Prediction","date":"2025-05-13","arxiv_id":"2505.09018","n_code_links":0,"syntology":null},{"paper":"/paper/openthinkimg-learning-to-think-with-images","slug":"openthinkimg-learning-to-think-with-images","title":"OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08617","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-retrieval-augmented-generation-1","title":"Optimizing Retrieval-Augmented Generation: Analysis of Hyperparameter Impact on Performance and Efficiency","date":"2025-05-13","arxiv_id":"2505.08445","n_code_links":0,"syntology":null},{"paper":"/paper/probability-consistency-in-large-language","slug":"probability-consistency-in-large-language","title":"Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies","date":"2025-05-13","arxiv_id":"2505.08739","n_code_links":1,"syntology":null},{"paper":null,"slug":"sar-gtr-attributed-scattering-information","title":"SAR-GTR: Attributed Scattering Information Guided SAR Graph Transformer Recognition Algorithm","date":"2025-05-13","arxiv_id":"2505.08547","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-context-not-parameters-training-a","title":"Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing","date":"2025-05-13","arxiv_id":"2505.08651","n_code_links":0,"syntology":null},{"paper":null,"slug":"securing-rag-a-risk-assessment-and-mitigation","title":"Securing RAG: A Risk Assessment and Mitigation Framework","date":"2025-05-13","arxiv_id":"2505.08728","n_code_links":0,"syntology":null},{"paper":"/paper/skeleton-guided-diffusion-model-for-accurate","slug":"skeleton-guided-diffusion-model-for-accurate","title":"Skeleton-Guided Diffusion Model for Accurate Foot X-ray Synthesis in Hallux Valgus Diagnosis","date":"2025-05-13","arxiv_id":"2505.08247","n_code_links":1,"syntology":null},{"paper":null,"slug":"small-but-significant-on-the-promise-of-small","title":"Small but Significant: On the Promise of Small Language Models for Accessible AIED","date":"2025-05-13","arxiv_id":"2505.08588","n_code_links":0,"syntology":null},{"paper":null,"slug":"spat-sensitivity-based-multihead-attention","title":"SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models","date":"2025-05-13","arxiv_id":"2505.08768","n_code_links":0,"syntology":null},{"paper":"/paper/structural-temporal-coupling-anomaly","slug":"structural-temporal-coupling-anomaly","title":"Structural-Temporal Coupling Anomaly Detection with Dynamic Graph Transformer","date":"2025-05-13","arxiv_id":"2505.08330","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-truth-becomes-clearer-through-debate","title":"The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News","date":"2025-05-13","arxiv_id":"2505.08532","n_code_links":0,"syntology":null},{"paper":"/paper/thermal-detection-of-people-with-mobility","slug":"thermal-detection-of-people-with-mobility","title":"Thermal Detection of People with Mobility Restrictions for Barrier Reduction at Traffic Lights Controlled Intersections","date":"2025-05-13","arxiv_id":"2505.08568","n_code_links":1,"syntology":null},{"paper":"/paper/timo-spatiotemporal-foundation-model-for","slug":"timo-spatiotemporal-foundation-model-for","title":"TiMo: Spatiotemporal Foundation Model for Satellite Image Time Series","date":"2025-05-13","arxiv_id":"2505.08723","n_code_links":1,"syntology":null},{"paper":null,"slug":"ultrasound-report-generation-with-multimodal","title":"Ultrasound Report Generation with Multimodal Large Language Models for Standardized Texts","date":"2025-05-13","arxiv_id":"2505.08838","n_code_links":0,"syntology":null},{"paper":"/paper/waveguard-robust-deepfake-detection-and","slug":"waveguard-robust-deepfake-detection-and","title":"WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks","date":"2025-05-13","arxiv_id":"2505.08614","n_code_links":1,"syntology":null},{"paper":null,"slug":"wixqa-a-multi-dataset-benchmark-for","title":"WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generation","date":"2025-05-13","arxiv_id":"2505.08643","n_code_links":0,"syntology":null},{"paper":"/paper/a-comparative-study-of-transformer-based-2","slug":"a-comparative-study-of-transformer-based-2","title":"A Comparative Study of Transformer-Based Models for Multi-Horizon Blood Glucose Prediction","date":"2025-05-12","arxiv_id":"2505.08821","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-generative-re-ranking-model-for-list-level","title":"A Generative Re-ranking Model for List-level Multi-objective Optimization at Taobao","date":"2025-05-12","arxiv_id":"2505.07197","n_code_links":0,"syntology":null},{"paper":"/paper/a-multi-dimensional-constraint-framework-for","slug":"a-multi-dimensional-constraint-framework-for","title":"A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models","date":"2025-05-12","arxiv_id":"2505.07591","n_code_links":1,"syntology":null},{"paper":"/paper/ais-data-driven-maritime-monitoring-based-on","slug":"ais-data-driven-maritime-monitoring-based-on","title":"AIS Data-Driven Maritime Monitoring Based on Transformer: A Comprehensive Review","date":"2025-05-12","arxiv_id":"2505.07374","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-extra-rmsnorm-is-all-you-need-for-fine","title":"An Extra RMSNorm is All You Need for Fine Tuning to 1.58 Bits","date":"2025-05-12","arxiv_id":"2505.08823","n_code_links":0,"syntology":null},{"paper":"/paper/anatomical-attention-alignment-representation","slug":"anatomical-attention-alignment-representation","title":"Anatomical Attention Alignment representation for Radiology Report Generation","date":"2025-05-12","arxiv_id":"2505.07689","n_code_links":1,"syntology":null},{"paper":null,"slug":"attentioninfluence-adopting-attention-head","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","date":"2025-05-12","arxiv_id":"2505.07293","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-visual-attention-detection-using","title":"Automated Visual Attention Detection using Mobile Eye Tracking in Behavioral Classroom Studies","date":"2025-05-12","arxiv_id":"2505.07552","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-retrieval-augmented-generation-2","title":"Benchmarking Retrieval-Augmented Generation for Chemistry","date":"2025-05-12","arxiv_id":"2505.07671","n_code_links":0,"syntology":null},{"paper":null,"slug":"breast-cancer-classification-in-deep","title":"Breast Cancer Classification in Deep Ultraviolet Fluorescence Images Using a Patch-Level Vision Transformer Framework","date":"2025-05-12","arxiv_id":"2505.07654","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-sentiment-analysis-of-public","title":"Comparative sentiment analysis of public perception: Monkeypox vs. COVID-19 behavioral insights","date":"2025-05-12","arxiv_id":"2505.07430","n_code_links":0,"syntology":null},{"paper":"/paper/dynamicrag-leveraging-outputs-of-large","slug":"dynamicrag-leveraging-outputs-of-large","title":"DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation","date":"2025-05-12","arxiv_id":"2505.07233","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-and-reproducible-biomedical","slug":"efficient-and-reproducible-biomedical","title":"Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented Generation","date":"2025-05-12","arxiv_id":"2505.07917","n_code_links":1,"syntology":null},{"paper":null,"slug":"examining-the-role-of-llm-driven-interactions","title":"Examining the Role of LLM-Driven Interactions on Attention and Cognitive Engagement in Virtual Classrooms","date":"2025-05-12","arxiv_id":"2505.07377","n_code_links":0,"syntology":null},{"paper":"/paper/fused3s-fast-sparse-attention-on-tensor-cores","slug":"fused3s-fast-sparse-attention-on-tensor-cores","title":"Fused3S: Fast Sparse Attention on Tensor Cores","date":"2025-05-12","arxiv_id":"2505.08098","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-pre-trained-autoregressive","title":"Generative Pre-trained Autoregressive Diffusion Transformer","date":"2025-05-12","arxiv_id":"2505.07344","n_code_links":0,"syntology":null},{"paper":null,"slug":"gifstream-4d-gaussian-based-immersive-video","title":"GIFStream: 4D Gaussian-based Immersive Video with Feature Stream","date":"2025-05-12","arxiv_id":"2505.07539","n_code_links":0,"syntology":null},{"paper":"/paper/grada-graph-based-reranker-against","slug":"grada-graph-based-reranker-against","title":"GRADA: Graph-based Reranker against Adversarial Documents Attack","date":"2025-05-12","arxiv_id":"2505.07546","n_code_links":1,"syntology":null},{"paper":"/paper/halo-half-life-based-outdated-fact-filtering","slug":"halo-half-life-based-outdated-fact-filtering","title":"HALO: Half Life-Based Outdated Fact Filtering in Temporal Knowledge Graphs","date":"2025-05-12","arxiv_id":"2505.07509","n_code_links":1,"syntology":null},{"paper":null,"slug":"hamlet-healthcare-focused-adaptive","title":"HAMLET: Healthcare-focused Adaptive Multilingual Learning Embedding-based Topic Modeling","date":"2025-05-12","arxiv_id":"2505.07157","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-sparse-attention-framework-for","title":"Hierarchical Sparse Attention Framework for Computationally Efficient Classification of Biological Cells","date":"2025-05-12","arxiv_id":"2505.07661","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-spiking-vision-transformer-for-object","title":"Hybrid Spiking Vision Transformer for Object Detection with Event Cameras","date":"2025-05-12","arxiv_id":"2505.07715","n_code_links":0,"syntology":null},{"paper":null,"slug":"kaqg-a-knowledge-graph-enhanced-rag-for","title":"KAQG: A Knowledge-Graph-Enhanced RAG for Difficulty-Controlled Question Generation","date":"2025-05-12","arxiv_id":"2505.07618","n_code_links":0,"syntology":null},{"paper":"/paper/lagrange-oscillatory-neural-networks-for","slug":"lagrange-oscillatory-neural-networks-for","title":"Lagrange Oscillatory Neural Networks for Constraint Satisfaction and Optimization","date":"2025-05-12","arxiv_id":"2505.07179","n_code_links":1,"syntology":null},{"paper":null,"slug":"lamm-vit-ai-face-detection-via-layer-aware","title":"LAMM-ViT: AI Face Detection via Layer-Aware Modulation of Region-Guided Attention","date":"2025-05-12","arxiv_id":"2505.07734","n_code_links":0,"syntology":null},{"paper":null,"slug":"mais-memory-attention-for-interactive","title":"MAIS: Memory-Attention for Interactive Segmentation","date":"2025-05-12","arxiv_id":"2505.07511","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-plane-vision-transformer-for-hemorrhage","title":"Multi-Plane Vision Transformer for Hemorrhage Classification Using Axial and Sagittal MRI Data","date":"2025-05-12","arxiv_id":"2505.07349","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-assessment-of-classroom-discourse","title":"Multimodal Assessment of Classroom Discourse Quality: A Text-Centered Attention-Based Multi-Task Learning Approach","date":"2025-05-12","arxiv_id":"2505.07902","n_code_links":0,"syntology":null},{"paper":null,"slug":"no-query-no-access","title":"No Query, No Access","date":"2025-05-12","arxiv_id":"2505.07258","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-vs-fine-tuning-a-reproducibility","slug":"pre-training-vs-fine-tuning-a-reproducibility","title":"Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition","date":"2025-05-12","arxiv_id":"2505.07166","n_code_links":1,"syntology":null},{"paper":null,"slug":"rdd-robust-feature-detector-and-descriptor","title":"RDD: Robust Feature Detector and Descriptor using Deformable Transformer","date":"2025-05-12","arxiv_id":"2505.08013","n_code_links":0,"syntology":null},{"paper":"/paper/recdap-relation-based-conditional-diffusion","slug":"recdap-relation-based-conditional-diffusion","title":"ReCDAP: Relation-Based Conditional Diffusion with Attention Pooling for Few-Shot Knowledge Graph Completion","date":"2025-05-12","arxiv_id":"2505.07171","n_code_links":1,"syntology":null},{"paper":"/paper/representation-learning-with-mutual-influence","slug":"representation-learning-with-mutual-influence","title":"Representation Learning with Mutual Influence of Modalities for Node Classification in Multi-Modal Heterogeneous Networks","date":"2025-05-12","arxiv_id":"2505.07895","n_code_links":1,"syntology":null},{"paper":null,"slug":"seredeep-hallucination-detection-in-retrieval","title":"SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion","date":"2025-05-12","arxiv_id":"2505.07528","n_code_links":0,"syntology":null},{"paper":null,"slug":"shotadapter-text-to-multi-shot-video","title":"ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models","date":"2025-05-12","arxiv_id":"2505.07652","n_code_links":0,"syntology":null},{"paper":null,"slug":"sleep-position-classification-using-transfer","title":"Sleep Position Classification using Transfer Learning for Bed-based Pressure Sensors","date":"2025-05-12","arxiv_id":"2505.08111","n_code_links":0,"syntology":null},{"paper":null,"slug":"statistical-csi-based-distributed-precoding","title":"Statistical CSI-Based Distributed Precoding Design for OFDM-Cooperative Multi-Satellite Systems","date":"2025-05-12","arxiv_id":"2505.08038","n_code_links":0,"syntology":null},{"paper":null,"slug":"task-adaptive-semantic-communications-with","title":"Task-Adaptive Semantic Communications with Controllable Diffusion-based Data Regeneration","date":"2025-05-12","arxiv_id":"2505.07980","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-geography-of-transportation-cybersecurity","title":"The Geography of Transportation Cybersecurity: Visitor Flows, Industry Clusters, and Spatial Dynamics","date":"2025-05-12","arxiv_id":"2505.08822","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-influence-of-the-memory-capacity-of","title":"The Influence of the Memory Capacity of Neural DDEs on the Universal Approximation Property","date":"2025-05-12","arxiv_id":"2505.07244","n_code_links":0,"syntology":null},{"paper":"/paper/topology-guided-knowledge-distillation-for","slug":"topology-guided-knowledge-distillation-for","title":"Topology-Guided Knowledge Distillation for Efficient Point Cloud Processing","date":"2025-05-12","arxiv_id":"2505.08101","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-requirements-engineering-for-rag","title":"Towards Requirements Engineering for RAG Systems","date":"2025-05-12","arxiv_id":"2505.07553","n_code_links":0,"syntology":null},{"paper":null,"slug":"umoe-unifying-attention-and-ffn-with-shared","title":"UMoE: Unifying Attention and FFN with Shared Experts","date":"2025-05-12","arxiv_id":"2505.07260","n_code_links":0,"syntology":null},{"paper":null,"slug":"wasserstein-distributionally-robust-7","title":"Wasserstein Distributionally Robust Nonparametric Regression","date":"2025-05-12","arxiv_id":"2505.07967","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-uncertainty-estimation-methods-fall-short","title":"Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis","date":"2025-05-12","arxiv_id":"2505.07459","n_code_links":0,"syntology":null},{"paper":"/paper/2025-tgrs-a-self-supervised-method-for","slug":"2025-tgrs-a-self-supervised-method-for","title":"2025 TGRS A Self-Supervised Method for Seismic Random Noise Attenuation under Non-Pixelwise Independent Assumption","date":"2025-05-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-self-supervised-method-for-attenuating","slug":"a-self-supervised-method-for-attenuating","title":"A Self-Supervised Method for Attenuating Seismic Random and Tracewise Coherent Noise under the Non-Pixelwise Independence Assumption","date":"2025-05-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-self-supervised-method-for-attenuating-1","slug":"a-self-supervised-method-for-attenuating-1","title":"A Self-Supervised Method for Attenuating Seismic Random and Tracewise Coherent Noise under the Non-Pixelwise Independence Assumption","date":"2025-05-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-systematic-review-of-challenges-and","title":"A systematic review of challenges and proposed solutions in modeling multimodal data","date":"2025-05-11","arxiv_id":"2505.06945","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridgeiv-bridging-customized-image-and-video","title":"BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation","date":"2025-05-11","arxiv_id":"2505.06985","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-and-robust-multidimensional","title":"Efficient and Robust Multidimensional Attention in Remote Physiological Sensing through Target Signal Constrained Factorization","date":"2025-05-11","arxiv_id":"2505.07013","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-reasoning-llms-for-suicide","slug":"evaluating-reasoning-llms-for-suicide","title":"Evaluating Reasoning LLMs for Suicide Screening with the Columbia-Suicide Severity Rating Scale","date":"2025-05-11","arxiv_id":"2505.13480","n_code_links":1,"syntology":null},{"paper":null,"slug":"explainable-artificial-intelligence-9","title":"Explainable Artificial Intelligence Techniques for Software Development Lifecycle: A Phase-specific Survey","date":"2025-05-11","arxiv_id":"2505.07058","n_code_links":0,"syntology":null},{"paper":null,"slug":"im-bert-enhancing-robustness-of-bert-through","title":"IM-BERT: Enhancing Robustness of BERT through the Implicit Euler Method","date":"2025-05-11","arxiv_id":"2505.06889","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-classification-using-a-diffusion-model","title":"Image Classification Using a Diffusion Model as a Pre-Training Model","date":"2025-05-11","arxiv_id":"2505.06890","n_code_links":0,"syntology":null},{"paper":null,"slug":"matrix-is-all-you-need","title":"Matrix Is All You Need","date":"2025-05-11","arxiv_id":"2506.01966","n_code_links":0,"syntology":null},{"paper":null,"slug":"neurn-neuro-inspired-domain-generalization","title":"NeuRN: Neuro-inspired Domain Generalization for Image Classification","date":"2025-05-11","arxiv_id":"2505.06881","n_code_links":0,"syntology":null},{"paper":null,"slug":"refpentester-a-knowledge-informed-self","title":"RefPentester: A Knowledge-Informed Self-Reflective Penetration Testing Framework Based on Large Language Models","date":"2025-05-11","arxiv_id":"2505.07089","n_code_links":0,"syntology":null},{"paper":null,"slug":"technical-report-for-icra-2025-goose-2d","title":"Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding","date":"2025-05-11","arxiv_id":"2505.06991","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-distracting-effect-understanding","title":"The Distracting Effect: Understanding Irrelevant Passages in RAG","date":"2025-05-11","arxiv_id":"2505.06914","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-dual-optical-attention","slug":"transformer-based-dual-optical-attention","title":"Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network","date":"2025-05-11","arxiv_id":"2505.06937","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-is-not-all-you-need-the-importance","title":"Attention Is Not All You Need: The Importance of Feedforward Networks in Transformer Models","date":"2025-05-10","arxiv_id":"2505.06633","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-mechanisms-in-dynamical-systems-a","title":"Attention Mechanisms in Dynamical Systems: A Case Study with Predator-Prey Models","date":"2025-05-10","arxiv_id":"2505.06503","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-neural-language-inference-via","title":"Boosting Neural Language Inference via Cascaded Interactive Reasoning","date":"2025-05-10","arxiv_id":"2505.06607","n_code_links":0,"syntology":null},{"paper":null,"slug":"e2e-fanet-a-highly-generalizable-framework","title":"E2E-FANet: A Highly Generalizable Framework for Waves prediction Behind Floating Breakwaters via Exogenous-to-Endogenous Variable Attention","date":"2025-05-10","arxiv_id":"2505.06690","n_code_links":0,"syntology":null},{"paper":"/paper/gated-attention-for-large-language-models-non","slug":"gated-attention-for-large-language-models-non","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","date":"2025-05-10","arxiv_id":"2505.06708","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qiuzh20/gated_attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/macrag-compress-slice-and-scale-up-for-multi","slug":"macrag-compress-slice-and-scale-up-for-multi","title":"MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG","date":"2025-05-10","arxiv_id":"2505.06569","n_code_links":1,"syntology":null},{"paper":null,"slug":"multitaskvif-segmentation-oriented-visible","title":"MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning","date":"2025-05-10","arxiv_id":"2505.06665","n_code_links":0,"syntology":null},{"paper":"/paper/omgm-orchestrate-multiple-granularities-and","slug":"omgm-orchestrate-multiple-granularities-and","title":"OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval","date":"2025-05-10","arxiv_id":"2505.07879","n_code_links":0,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"optigait-lgbm-an-efficient-approach-of-gait","title":"OptiGait-LGBM: An Efficient Approach of Gait-based Person Re-identification in Non-Overlapping Regions","date":"2025-05-10","arxiv_id":"2505.08801","n_code_links":0,"syntology":null},{"paper":"/paper/probing-in-context-learning-impact-of-task","slug":"probing-in-context-learning-impact-of-task","title":"Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and Efficiency","date":"2025-05-10","arxiv_id":"2505.06475","n_code_links":1,"syntology":null},{"paper":null,"slug":"profashion-prototype-guided-fashion-video","title":"ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images","date":"2025-05-10","arxiv_id":"2505.06537","n_code_links":0,"syntology":null},{"paper":null,"slug":"qos-efficient-serving-of-multiple-mixture-of","title":"QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration","date":"2025-05-10","arxiv_id":"2505.06481","n_code_links":0,"syntology":null},{"paper":null,"slug":"refine-af-a-task-agnostic-framework-to-align","title":"REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback","date":"2025-05-10","arxiv_id":"2505.06548","n_code_links":0,"syntology":null},{"paper":null,"slug":"rulegenie-siem-detection-rule-set","title":"RuleGenie: SIEM Detection Rule Set Optimization","date":"2025-05-10","arxiv_id":"2505.06701","n_code_links":0,"syntology":null},{"paper":"/paper/tacfn-transformer-based-adaptive-cross-modal","slug":"tacfn-transformer-based-adaptive-cross-modal","title":"TACFN: Transformer-based Adaptive Cross-modal Fusion Network for Multimodal Emotion Recognition","date":"2025-05-10","arxiv_id":"2505.06536","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-sound-of-populism-distinct-linguistic","title":"The Sound of Populism: Distinct Linguistic Features Across Populist Variants","date":"2025-05-10","arxiv_id":"2505.07874","n_code_links":0,"syntology":null},{"paper":null,"slug":"underwater-object-detection-in-sonar-imagery","title":"Underwater object detection in sonar imagery with detection transformer and Zero-shot neural architecture search","date":"2025-05-10","arxiv_id":"2505.06694","n_code_links":0,"syntology":null}],"record_sha256":"b7ae005125b7db9a3fc785d0284638e375d2a005770d6ba7117b98d1f168ba7f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}