{"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/14","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":14,"pages_in_order":249,"rows_per_page":100,"rows":[1301,1400],"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/13","next":"/method/multi-head-attention/papers/15","papers":[{"paper":null,"slug":"shushing-let-s-imagine-an-authentic-speech","title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video","date":"2025-03-19","arxiv_id":"2503.14928","n_code_links":0,"syntology":null},{"paper":null,"slug":"trove-a-challenge-for-fine-grained-text","title":"TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification","date":"2025-03-19","arxiv_id":"2503.15289","n_code_links":0,"syntology":null},{"paper":null,"slug":"truthlens-a-training-free-paradigm-for","title":"TruthLens:A Training-Free Paradigm for DeepFake Detection","date":"2025-03-19","arxiv_id":"2503.15342","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-the-generalization-of-in","slug":"understanding-the-generalization-of-in","title":"Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study","date":"2025-03-19","arxiv_id":"2503.15579","n_code_links":1,"syntology":null},{"paper":"/paper/a-score-attention-based-scene-coordinate","slug":"a-score-attention-based-scene-coordinate","title":"A-SCoRe: Attention-based Scene Coordinate Regression for wide-ranging scenarios","date":"2025-03-18","arxiv_id":"2503.13982","n_code_links":1,"syntology":null},{"paper":null,"slug":"binary-addivortes-bayesian-additive-voronoi","title":"Binary AddiVortes: (Bayesian) Additive Voronoi Tessellations for Binary Classification with an application to Predicting Home Mortgage Application Outcomes","date":"2025-03-18","arxiv_id":"2503.21792","n_code_links":0,"syntology":null},{"paper":"/paper/burtorch-revisiting-training-from-first","slug":"burtorch-revisiting-training-from-first","title":"BurTorch: Revisiting Training from First Principles by Coupling Autodiff, Math Optimization, and Systems","date":"2025-03-18","arxiv_id":"2503.13795","n_code_links":1,"syntology":null},{"paper":null,"slug":"ctsac-curriculum-based-transformer-soft-actor","title":"CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot Exploration","date":"2025-03-18","arxiv_id":"2503.14254","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-accumulated-attention-map-for","slug":"dynamic-accumulated-attention-map-for","title":"Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer","date":"2025-03-18","arxiv_id":"2503.14640","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-llm-generation-with-knowledge","title":"Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine","date":"2025-03-18","arxiv_id":"2503.16530","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-autoregressive-video-generation-with","title":"Fast Autoregressive Video Generation with Diagonal Decoding","date":"2025-03-18","arxiv_id":"2503.14070","n_code_links":0,"syntology":null},{"paper":null,"slug":"good-evil-reputation-judgment-of-celebrities","title":"Good/Evil Reputation Judgment of Celebrities by LLMs via Retrieval Augmented Generation","date":"2025-03-18","arxiv_id":"2503.14382","n_code_links":0,"syntology":null},{"paper":"/paper/gricean-norms-as-a-basis-for-effective","slug":"gricean-norms-as-a-basis-for-effective","title":"Gricean Norms as a Basis for Effective Collaboration","date":"2025-03-18","arxiv_id":"2503.14484","n_code_links":1,"syntology":null},{"paper":"/paper/judge-benchmarking-judgment-document","slug":"judge-benchmarking-judgment-document","title":"JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System","date":"2025-03-18","arxiv_id":"2503.14258","n_code_links":1,"syntology":null},{"paper":null,"slug":"kg-irag-a-knowledge-graph-based-iterative","title":"Beyond Single Pass, Looping Through Time: KG-IRAG with Iterative Knowledge Retrieval","date":"2025-03-18","arxiv_id":"2503.14234","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-virtual-human","title":"Large Language Models for Virtual Human Gesture Selection","date":"2025-03-18","arxiv_id":"2503.14408","n_code_links":0,"syntology":null},{"paper":"/paper/mdocagent-a-multi-modal-multi-agent-framework","slug":"mdocagent-a-multi-modal-multi-agent-framework","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","date":"2025-03-18","arxiv_id":"2503.13964","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aiming-lab/mdocagent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mok-rag-mixture-of-knowledge-paths-enhanced","title":"MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI Environments","date":"2025-03-18","arxiv_id":"2503.13882","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-feature-driven-deep-learning-for","title":"Multimodal Feature-Driven Deep Learning for the Prediction of Duck Body Dimensions and Weight","date":"2025-03-18","arxiv_id":"2503.14001","n_code_links":0,"syntology":null},{"paper":"/paper/pencil-long-thoughts-with-short-memory","slug":"pencil-long-thoughts-with-short-memory","title":"PENCIL: Long Thoughts with Short Memory","date":"2025-03-18","arxiv_id":"2503.14337","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chr26195/pencil"],"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":null,"slug":"predicting-human-choice-between-textually","title":"Predicting Human Choice Between Textually Described Lotteries","date":"2025-03-18","arxiv_id":"2503.14004","n_code_links":0,"syntology":null},{"paper":"/paper/rago-systematic-performance-optimization-for","slug":"rago-systematic-performance-optimization-for","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","date":"2025-03-18","arxiv_id":"2503.14649","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-guided-image-invariant-feature-learning","title":"Text-Guided Image Invariant Feature Learning for Robust Image Watermarking","date":"2025-03-18","arxiv_id":"2503.13805","n_code_links":0,"syntology":null},{"paper":null,"slug":"theoretical-foundation-of-flow-based-time","title":"Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency","date":"2025-03-18","arxiv_id":"2503.14076","n_code_links":0,"syntology":null},{"paper":null,"slug":"xoxo-stealthy-cross-origin-context-poisoning","title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","date":"2025-03-18","arxiv_id":"2503.14281","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-reinforcement-learning-driven-transformer","title":"A Reinforcement Learning-Driven Transformer GAN for Molecular Generation","date":"2025-03-17","arxiv_id":"2503.12796","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-transformer-context-extension","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","date":"2025-03-17","arxiv_id":"2503.13299","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-chronic-tuberculosis-diagnostics","title":"Advancing Chronic Tuberculosis Diagnostics Using Vision-Language Models: A Multi modal Framework for Precision Analysis","date":"2025-03-17","arxiv_id":"2503.14536","n_code_links":0,"syntology":null},{"paper":"/paper/an-interpretable-approach-to-automating-the","slug":"an-interpretable-approach-to-automating-the","title":"An interpretable approach to automating the assessment of biofouling in video footage","date":"2025-03-17","arxiv_id":"2503.12875","n_code_links":1,"syntology":null},{"paper":null,"slug":"are-llms-really-ideological-an-irt-based","title":"Are LLMs (Really) Ideological? An IRT-based Analysis and Alignment Tool for Perceived Socio-Economic Bias in LLMs","date":"2025-03-17","arxiv_id":"2503.13149","n_code_links":0,"syntology":null},{"paper":"/paper/can-language-models-follow-multiple-turns-of","slug":"can-language-models-follow-multiple-turns-of","title":"Can Language Models Follow Multiple Turns of Entangled Instructions?","date":"2025-03-17","arxiv_id":"2503.13222","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-extraction-and-analysis-for-gpt","title":"Feature Extraction and Analysis for GPT-Generated Text","date":"2025-03-17","arxiv_id":"2503.13687","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-for-software-architecture","title":"Generative AI for Software Architecture. Applications, Trends, Challenges, and Future Directions","date":"2025-03-17","arxiv_id":"2503.13310","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanoid-policy-human-policy","title":"Humanoid Policy ~ Human Policy","date":"2025-03-17","arxiv_id":"2503.13441","n_code_links":0,"syntology":null},{"paper":"/paper/in-context-linear-regression-demystified","slug":"in-context-linear-regression-demystified","title":"In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention","date":"2025-03-17","arxiv_id":"2503.12734","n_code_links":1,"syntology":null},{"paper":"/paper/mes-rag-bringing-multi-modal-entity-storage","slug":"mes-rag-bringing-multi-modal-entity-storage","title":"MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG","date":"2025-03-17","arxiv_id":"2503.13563","n_code_links":1,"syntology":null},{"paper":null,"slug":"oscar-online-soft-compression-and-reranking","title":"OSCAR: Online Soft Compression And Reranking","date":"2025-03-17","arxiv_id":"2504.07109","n_code_links":0,"syntology":null},{"paper":"/paper/pause-low-latency-and-privacy-aware-active","slug":"pause-low-latency-and-privacy-aware-active","title":"PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning","date":"2025-03-17","arxiv_id":"2503.13173","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-aware-rag-secure-and-isolated","title":"Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval","date":"2025-03-17","arxiv_id":"2503.15548","n_code_links":0,"syntology":null},{"paper":null,"slug":"seisrdt-latent-diffusion-model-based-on","title":"SeisRDT: Latent Diffusion Model Based On Representation Learning For Seismic Data Interpolation And Reconstruction","date":"2025-03-17","arxiv_id":"2503.21791","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-scalable-foundation-model-for-multi","title":"Towards Scalable Foundation Model for Multi-modal and Hyperspectral Geospatial Data","date":"2025-03-17","arxiv_id":"2503.12843","n_code_links":0,"syntology":null},{"paper":"/paper/fourier-based-3d-multistage-transformer-for","slug":"fourier-based-3d-multistage-transformer-for","title":"Fourier-Based 3D Multistage Transformer for Aberration Correction in Multicellular Specimens","date":"2025-03-16","arxiv_id":"2503.12593","n_code_links":2,"syntology":null},{"paper":null,"slug":"fragile-mastery-are-domain-specific-trade","title":"Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?","date":"2025-03-16","arxiv_id":"2503.22698","n_code_links":0,"syntology":null},{"paper":null,"slug":"grapheval-a-lightweight-graph-based-llm","title":"GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation","date":"2025-03-16","arxiv_id":"2503.12600","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-matters-multimodal-features-for","title":"Semantic Matters: Multimodal Features for Affective Analysis","date":"2025-03-16","arxiv_id":"2504.11460","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bubble-cluster-federated-learning-framework","title":"PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data","date":"2025-03-15","arxiv_id":"2503.12220","n_code_links":0,"syntology":null},{"paper":null,"slug":"changing-base-without-losing-pace-a-gpu","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","date":"2025-03-15","arxiv_id":"2503.12211","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-critical-clearing-time-calculation-for","title":"Fast Critical Clearing Time Calculation for Power Systems with Synchronous and Asynchronous Generation","date":"2025-03-15","arxiv_id":"2503.12132","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-chain-of-thought-and-retrieval","title":"Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes","date":"2025-03-15","arxiv_id":"2503.12286","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-for-automated-classification","title":"Language Models for Automated Classification of Brain MRI Reports and Growth Chart Generation","date":"2025-03-15","arxiv_id":"2503.12143","n_code_links":0,"syntology":null},{"paper":"/paper/llm-hpc-benchmarking-deepseek-s-performance","slug":"llm-hpc-benchmarking-deepseek-s-performance","title":"LLM & HPC:Benchmarking DeepSeek's Performance in High-Performance Computing Tasks","date":"2025-03-15","arxiv_id":"2504.03665","n_code_links":1,"syntology":null},{"paper":null,"slug":"maritime-mission-planning-for-unmanned","title":"Maritime Mission Planning for Unmanned Surface Vessel using Large Language Model","date":"2025-03-15","arxiv_id":"2503.12065","n_code_links":0,"syntology":null},{"paper":null,"slug":"addressing-information-loss-and-interaction","title":"Addressing Information Loss and Interaction Collapse: A Dual Enhanced Attention Framework for Feature Interaction","date":"2025-03-14","arxiv_id":"2503.11233","n_code_links":0,"syntology":null},{"paper":null,"slug":"alzheimer-s-disease-classification-using","title":"Alzheimer's Disease Classification Using Retinal OCT: TransnetOCT and Swin Transformer Models","date":"2025-03-14","arxiv_id":"2503.11511","n_code_links":0,"syntology":null},{"paper":null,"slug":"asynchronous-sharpness-aware-minimization-for","title":"Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning","date":"2025-03-14","arxiv_id":"2503.11147","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-image-annotation-a-human-lmm","title":"Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation","date":"2025-03-14","arxiv_id":"2503.11096","n_code_links":0,"syntology":null},{"paper":"/paper/bevdiffloc-end-to-end-lidar-global","slug":"bevdiffloc-end-to-end-lidar-global","title":"BEVDiffLoc: End-to-End LiDAR Global Localization in BEV View based on Diffusion Model","date":"2025-03-14","arxiv_id":"2503.11372","n_code_links":1,"syntology":null},{"paper":"/paper/combining-causal-models-for-more-accurate","slug":"combining-causal-models-for-more-accurate","title":"Combining Causal Models for More Accurate Abstractions of Neural Networks","date":"2025-03-14","arxiv_id":"2503.11429","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["marapislar/combining-causal-models-for-accurate-nn-abstractions"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"context-aware-rule-mining-using-a-dynamic","title":"Context-Aware Rule Mining Using a Dynamic Transformer-Based Framework","date":"2025-03-14","arxiv_id":"2503.11125","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynrsl-vlm-enhancing-autonomous-driving","title":"DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models","date":"2025-03-14","arxiv_id":"2503.11265","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-potential-of-large-multimodal","title":"Exploring the Potential of Large Multimodal Models as Effective Alternatives for Pronunciation Assessment","date":"2025-03-14","arxiv_id":"2503.11229","n_code_links":0,"syntology":null},{"paper":null,"slug":"limits-of-kv-cache-compression-for-tensor","title":"Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding","date":"2025-03-14","arxiv_id":"2503.11108","n_code_links":0,"syntology":null},{"paper":null,"slug":"meet-a-million-scale-dataset-for-fine-grained","title":"MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery","date":"2025-03-14","arxiv_id":"2503.11219","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-sentiment-the-catalyst-for-llm-change","title":"Prompt Sentiment: The Catalyst for LLM Change","date":"2025-03-14","arxiv_id":"2503.13510","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-kg-il-a-multi-agent-hybrid-framework-for","title":"RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration","date":"2025-03-14","arxiv_id":"2503.13514","n_code_links":0,"syntology":null},{"paper":"/paper/relevance-isn-t-all-you-need-scaling-rag","slug":"relevance-isn-t-all-you-need-scaling-rag","title":"Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking","date":"2025-03-14","arxiv_id":"2504.07104","n_code_links":2,"syntology":null},{"paper":null,"slug":"response-benchmarking-the-ability-of-language","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","date":"2025-03-14","arxiv_id":"2503.11348","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-and-contextual-modeling-for","title":"Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTM","date":"2025-03-14","arxiv_id":"2503.11084","n_code_links":0,"syntology":null},{"paper":null,"slug":"solution-for-8th-competition-on-affective","title":"Solution for 8th Competition on Affective & Behavior Analysis in-the-wild","date":"2025-03-14","arxiv_id":"2503.11115","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-compression-for-efficient-language","title":"Text Compression for Efficient Language Generation","date":"2025-03-14","arxiv_id":"2503.11426","n_code_links":0,"syntology":null},{"paper":null,"slug":"transit-transient-transformer-for-non-line-of","title":"TransiT: Transient Transformer for Non-line-of-sight Videography","date":"2025-03-14","arxiv_id":"2503.11328","n_code_links":0,"syntology":null},{"paper":"/paper/treemeshgpt-artistic-mesh-generation-with","slug":"treemeshgpt-artistic-mesh-generation-with","title":"TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing","date":"2025-03-14","arxiv_id":"2503.11629","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 6 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/treemeshgpt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/when-do-transformers-outperform-feedforward","slug":"when-do-transformers-outperform-feedforward","title":"When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective","date":"2025-03-14","arxiv_id":"2503.11272","n_code_links":1,"syntology":null},{"paper":"/paper/a-frustratingly-simple-yet-highly-effective","slug":"a-frustratingly-simple-yet-highly-effective","title":"A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1","date":"2025-03-13","arxiv_id":"2503.10635","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vila-lab/m-attack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-hybrid-architecture-with-efficient-fine","title":"A Hybrid Architecture with Efficient Fine Tuning for Abstractive Patent Document Summarization","date":"2025-03-13","arxiv_id":"2503.10354","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-tool-learning-and-selection-system","title":"Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM","date":"2025-03-13","arxiv_id":"2503.10071","n_code_links":0,"syntology":null},{"paper":null,"slug":"arled-leveraging-led-based-arman-model-for","title":"ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents","date":"2025-03-13","arxiv_id":"2503.10233","n_code_links":0,"syntology":null},{"paper":null,"slug":"attentionrag-attention-guided-context-pruning","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","date":"2025-03-13","arxiv_id":"2503.10720","n_code_links":0,"syntology":null},{"paper":null,"slug":"audiox-diffusion-transformer-for-anything-to","title":"AudioX: Diffusion Transformer for Anything-to-Audio Generation","date":"2025-03-13","arxiv_id":"2503.10522","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-encounters-morphing-attack-detection","title":"ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision Models","date":"2025-03-13","arxiv_id":"2503.10937","n_code_links":0,"syntology":null},{"paper":null,"slug":"cocmt-communication-efficient-cross-modal","title":"CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception","date":"2025-03-13","arxiv_id":"2503.13504","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-mental-llm-leveraging-reasoning-in","slug":"cognitive-mental-llm-leveraging-reasoning-in","title":"Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text","date":"2025-03-13","arxiv_id":"2503.10095","n_code_links":1,"syntology":null},{"paper":null,"slug":"compositional-subspace-representation-fine","title":"Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models","date":"2025-03-13","arxiv_id":"2503.10617","n_code_links":0,"syntology":null},{"paper":null,"slug":"cosh-dit-co-speech-gesture-video-synthesis","title":"Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers","date":"2025-03-13","arxiv_id":"2503.09942","n_code_links":0,"syntology":null},{"paper":null,"slug":"countpath-automating-fragment-counting-in","title":"CountPath: Automating Fragment Counting in Digital Pathology","date":"2025-03-13","arxiv_id":"2503.10520","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-i-look-like-a-cat-n-01-to-you-a-taxonomy","title":"Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark","date":"2025-03-13","arxiv_id":"2503.10357","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-fog-computing-enabled-eeg-data","title":"Edge-Fog Computing-Enabled EEG Data Compression via Asymmetrical Variational Discrete Cosine Transform Network","date":"2025-03-13","arxiv_id":"2503.09961","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-recognition-with-clip-and-sequential","title":"Emotion Recognition with CLIP and Sequential Learning","date":"2025-03-13","arxiv_id":"2503.09929","n_code_links":0,"syntology":null},{"paper":"/paper/fg-rag-enhancing-query-focused-summarization","slug":"fg-rag-enhancing-query-focused-summarization","title":"FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG","date":"2025-03-13","arxiv_id":"2504.07103","n_code_links":1,"syntology":null},{"paper":null,"slug":"fixed-point-rnns-from-diagonal-to-dense-in-a","title":"Fixed-Point RNNs: From Diagonal to Dense in a Few Iterations","date":"2025-03-13","arxiv_id":"2503.10799","n_code_links":0,"syntology":null},{"paper":"/paper/gumiho-a-hybrid-architecture-to-prioritize","slug":"gumiho-a-hybrid-architecture-to-prioritize","title":"Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding","date":"2025-03-13","arxiv_id":"2503.10135","n_code_links":0,"syntology":{"ran":12,"of":15,"n_ran_checked":8,"n_instrument":4,"unverified":3,"pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"it-is-too-many-options-pitfalls-of-multiple","title":"It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education","date":"2025-03-13","arxiv_id":"2503.13508","n_code_links":0,"syntology":null},{"paper":null,"slug":"kv-distill-nearly-lossless-learnable-context","title":"KV-Distill: Nearly Lossless Learnable Context Compression for LLMs","date":"2025-03-13","arxiv_id":"2503.10337","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-domain-biometric-recognition-using-body","title":"Multi-Domain Biometric Recognition using Body Embeddings","date":"2025-03-13","arxiv_id":"2503.10931","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-stock-movement-with-bertweet-and","title":"Predicting Stock Movement with BERTweet and Transformers","date":"2025-03-13","arxiv_id":"2503.10957","n_code_links":0,"syntology":null},{"paper":"/paper/radar-fast-long-context-decoding-for-any","slug":"radar-fast-long-context-decoding-for-any","title":"Radar: Fast Long-Context Decoding for Any Transformer","date":"2025-03-13","arxiv_id":"2503.10571","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["BorealisAI/radar-decoding"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/retrieval-augmented-generation-with-1","slug":"retrieval-augmented-generation-with-1","title":"Retrieval-Augmented Generation with Hierarchical Knowledge","date":"2025-03-13","arxiv_id":"2503.10150","n_code_links":1,"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":{"repos":["hhy-huang/HiRAG"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/robustness-tokens-towards-adversarial","slug":"robustness-tokens-towards-adversarial","title":"Robustness Tokens: Towards Adversarial Robustness of Transformers","date":"2025-03-13","arxiv_id":"2503.10191","n_code_links":1,"syntology":null},{"paper":null,"slug":"siege-autonomous-multi-turn-jailbreaking-of","title":"Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search","date":"2025-03-13","arxiv_id":"2503.10619","n_code_links":0,"syntology":null},{"paper":null,"slug":"tacticexpert-spatial-temporal-graph-language","title":"TacticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics","date":"2025-03-13","arxiv_id":"2503.10722","n_code_links":0,"syntology":null}],"record_sha256":"f0c43e3a0bf25a0d62895dcee7bfa2e6fb00d1901aa51879d6ed8e616959be5f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}