{"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/82","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":82,"pages_in_order":316,"rows_per_page":100,"rows":[8101,8200],"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/81","next":"/method/attention/papers/83","papers":[{"paper":null,"slug":"sad-state-action-distillation-for-in-context","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","date":"2024-10-25","arxiv_id":"2410.19982","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-survey-of-time-series","title":"A Comprehensive Survey of Time Series Forecasting: Architectural Diversity and Open Challenges","date":"2024-10-24","arxiv_id":"2411.05793","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-contrastive-learning-approach-for-auditory","title":"A contrastive-learning approach for auditory attention detection","date":"2024-10-24","arxiv_id":"2410.18395","n_code_links":0,"syntology":null},{"paper":null,"slug":"agentstore-scalable-integration-of","title":"AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant","date":"2024-10-24","arxiv_id":"2410.18603","n_code_links":0,"syntology":null},{"paper":null,"slug":"aggregated-knowledge-model-enhancing-domain","title":"Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models","date":"2024-10-24","arxiv_id":"2410.18344","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-codellms-with-direct-preference","title":"Aligning CodeLLMs with Direct Preference Optimization","date":"2024-10-24","arxiv_id":"2410.18585","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-the-creativity-of-llms-in-proposing","slug":"assessing-the-creativity-of-llms-in-proposing","title":"Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems","date":"2024-10-24","arxiv_id":"2410.18336","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["junyiye/creativemath"],"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":"attention-based-citywide-electric-vehicle","title":"Citywide Electric Vehicle Charging Demand Prediction Approach Considering Urban Region and Dynamic Influences","date":"2024-10-24","arxiv_id":"2410.18766","n_code_links":0,"syntology":null},{"paper":null,"slug":"baton-enhancing-batch-wise-inference","title":"BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching","date":"2024-10-24","arxiv_id":"2410.18701","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-multiple-choice-accuracy-real-world","title":"Beyond Multiple-Choice Accuracy: Real-World Challenges of Implementing Large Language Models in Healthcare","date":"2024-10-24","arxiv_id":"2410.18460","n_code_links":0,"syntology":null},{"paper":null,"slug":"bielik-7b-v0-1-a-polish-language-model","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","date":"2024-10-24","arxiv_id":"2410.18565","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomistral-nlu-towards-more-generalizable","title":"BioMistral-NLU: Towards More Generalizable Medical Language Understanding through Instruction Tuning","date":"2024-10-24","arxiv_id":"2410.18955","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-dialogue-understanding-models-for","title":"Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch","date":"2024-10-24","arxiv_id":"2410.18430","n_code_links":0,"syntology":null},{"paper":"/paper/camel-bench-a-comprehensive-arabic-lmm","slug":"camel-bench-a-comprehensive-arabic-lmm","title":"CAMEL-Bench: A Comprehensive Arabic LMM Benchmark","date":"2024-10-24","arxiv_id":"2410.18976","n_code_links":1,"syntology":null},{"paper":null,"slug":"causal-order-discovery-based-on-monotonic","title":"Causal Order Discovery based on Monotonic SCMs","date":"2024-10-24","arxiv_id":"2410.19870","n_code_links":0,"syntology":null},{"paper":null,"slug":"dct-histotransformer-efficient-lightweight","title":"DCT-HistoTransformer: Efficient Lightweight Vision Transformer with DCT Integration for histopathological image analysis","date":"2024-10-24","arxiv_id":"2410.19166","n_code_links":0,"syntology":null},{"paper":"/paper/decore-decoding-by-contrasting-retrieval","slug":"decore-decoding-by-contrasting-retrieval","title":"DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations","date":"2024-10-24","arxiv_id":"2410.18860","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-insights-into-cognitive-decline-a-survey","title":"Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques","date":"2024-10-24","arxiv_id":"2410.18972","n_code_links":0,"syntology":null},{"paper":"/paper/difficult-for-whom-a-study-of-japanese","slug":"difficult-for-whom-a-study-of-japanese","title":"Difficult for Whom? A Study of Japanese Lexical Complexity","date":"2024-10-24","arxiv_id":"2410.18567","n_code_links":1,"syntology":null},{"paper":"/paper/dreamclear-high-capacity-real-world-image","slug":"dreamclear-high-capacity-real-world-image","title":"DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation","date":"2024-10-24","arxiv_id":"2410.18666","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"8 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["shallowdream204/dreamclear"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-graph-attention-neural-network","title":"Enhancing Graph Attention Neural Network Performance for Marijuana Consumption Classification through Large-scale Augmented Granger Causality (lsAGC) Analysis of Functional MR Images","date":"2024-10-24","arxiv_id":"2410.18506","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairqueue-rethinking-prompt-learning-for-fair","title":"FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation","date":"2024-10-24","arxiv_id":"2410.18615","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedbaf-federated-learning-aggregation-biased","title":"FedBaF: Federated Learning Aggregation Biased by a Foundation Model","date":"2024-10-24","arxiv_id":"2410.18352","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-multimodal-llms-with-semantic","title":"Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification","date":"2024-10-24","arxiv_id":"2410.18686","n_code_links":0,"syntology":null},{"paper":"/paper/highly-efficient-non-rigid-registration-in-k","slug":"highly-efficient-non-rigid-registration-in-k","title":"Highly efficient non-rigid registration in k-space with application to cardiac Magnetic Resonance Imaging","date":"2024-10-24","arxiv_id":"2410.18834","n_code_links":1,"syntology":null},{"paper":"/paper/homomorphism-counts-as-structural-encodings","slug":"homomorphism-counts-as-structural-encodings","title":"Homomorphism Counts as Structural Encodings for Graph Learning","date":"2024-10-24","arxiv_id":"2410.18676","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"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":["linusbao/MoSE"],"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":"integrating-canonical-neural-units-and-multi","title":"Integrating Canonical Neural Units and Multi-Scale Training for Handwritten Text Recognition","date":"2024-10-24","arxiv_id":"2410.18374","n_code_links":0,"syntology":null},{"paper":"/paper/iterative-self-tuning-llms-for-enhanced","slug":"iterative-self-tuning-llms-for-enhanced","title":"Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities","date":"2024-10-24","arxiv_id":"2410.18469","n_code_links":1,"syntology":null},{"paper":"/paper/kvsharer-efficient-inference-via-layer-wise","slug":"kvsharer-efficient-inference-via-layer-wise","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","date":"2024-10-24","arxiv_id":"2410.18517","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":["yangyifei729/kvsharer"],"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":null,"slug":"learning-global-object-centric","title":"Learning Global Object-Centric Representations via Disentangled Slot Attention","date":"2024-10-24","arxiv_id":"2410.18809","n_code_links":0,"syntology":null},{"paper":"/paper/little-giants-synthesizing-high-quality","slug":"little-giants-synthesizing-high-quality","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","date":"2024-10-24","arxiv_id":"2410.18634","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["haon-chen/SPEED"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"local-and-global-graph-modeling-with-edge","title":"Local and Global Graph Modeling with Edge-weighted Graph Attention Network for Handwritten Mathematical Expression Recognition","date":"2024-10-24","arxiv_id":"2410.18555","n_code_links":0,"syntology":null},{"paper":"/paper/logo-long-context-alignment-via-efficient","slug":"logo-long-context-alignment-via-efficient","title":"LOGO -- Long cOntext aliGnment via efficient preference Optimization","date":"2024-10-24","arxiv_id":"2410.18533","n_code_links":1,"syntology":null},{"paper":null,"slug":"motionclr-motion-generation-and-training-free","title":"Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing","date":"2024-10-24","arxiv_id":"2410.18977","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-objective-optimization-in-cpu-design","title":"Multi-objective Optimization in CPU Design Space Exploration: Attention is All You Need","date":"2024-10-24","arxiv_id":"2410.18368","n_code_links":0,"syntology":null},{"paper":null,"slug":"no-argument-left-behind-overlapping-chunks","title":"No Argument Left Behind: Overlapping Chunks for Faster Processing of Arbitrarily Long Legal Texts","date":"2024-10-24","arxiv_id":"2410.19184","n_code_links":0,"syntology":null},{"paper":"/paper/on-explaining-with-attention-matrices","slug":"on-explaining-with-attention-matrices","title":"On Explaining with Attention Matrices","date":"2024-10-24","arxiv_id":"2410.18541","n_code_links":1,"syntology":null},{"paper":"/paper/pdl-a-declarative-prompt-programming-language","slug":"pdl-a-declarative-prompt-programming-language","title":"PDL: A Declarative Prompt Programming Language","date":"2024-10-24","arxiv_id":"2410.19135","n_code_links":1,"syntology":null},{"paper":null,"slug":"pesformer-boosting-macro-and-micro-expression","title":"PESFormer: Boosting Macro- and Micro-expression Spotting with Direct Timestamp Encoding","date":"2024-10-24","arxiv_id":"2410.18695","n_code_links":0,"syntology":null},{"paper":"/paper/pixelgaussian-generalizable-3d-gaussian","slug":"pixelgaussian-generalizable-3d-gaussian","title":"PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views","date":"2024-10-24","arxiv_id":"2410.18979","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":["barrybarry-smith/pixelgaussian"],"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":"probing-ranking-llms-mechanistic","title":"Understanding Ranking LLMs: A Mechanistic Analysis for Information Retrieval","date":"2024-10-24","arxiv_id":"2410.18527","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-and-fine-tuning-of-small-llms-for","title":"Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization","date":"2024-10-24","arxiv_id":"2410.18624","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-softmax-self-attention-with","title":"Rethinking Attention: Polynomial Alternatives to Softmax in Transformers","date":"2024-10-24","arxiv_id":"2410.18613","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieving-implicit-and-explicit-emotional","title":"Retrieving Implicit and Explicit Emotional Events Using Large Language Models","date":"2024-10-24","arxiv_id":"2410.19128","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-up-masked-diffusion-models-on-text","slug":"scaling-up-masked-diffusion-models-on-text","title":"Scaling up Masked Diffusion Models on Text","date":"2024-10-24","arxiv_id":"2410.18514","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["ml-gsai/smdm"],"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":null,"slug":"sfb-net-for-cardiac-segmentation-bridging-the","title":"SFB-net for cardiac segmentation: Bridging the semantic gap with attention","date":"2024-10-24","arxiv_id":"2410.18503","n_code_links":0,"syntology":null},{"paper":null,"slug":"sort-free-gaussian-splatting-via-weighted-sum","title":"Sort-free Gaussian Splatting via Weighted Sum Rendering","date":"2024-10-24","arxiv_id":"2410.18931","n_code_links":0,"syntology":null},{"paper":null,"slug":"speed-a-multilingual-event-extraction","title":"SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness","date":"2024-10-24","arxiv_id":"2410.18393","n_code_links":0,"syntology":null},{"paper":null,"slug":"taipan-efficient-and-expressive-state-space","title":"Taipan: Efficient and Expressive State Space Language Models with Selective Attention","date":"2024-10-24","arxiv_id":"2410.18572","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nature-of-mathematical-modeling-and","title":"The Nature of Mathematical Modeling and Probabilistic Optimization Engineering in Generative AI","date":"2024-10-24","arxiv_id":"2410.18441","n_code_links":0,"syntology":null},{"paper":null,"slug":"toolflow-boosting-llm-tool-calling-through","title":"ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis","date":"2024-10-24","arxiv_id":"2410.18447","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-players-as-if-they-are-talking","title":"Understanding Players as if They Are Talking to the Game in a Customized Language: A Pilot Study","date":"2024-10-24","arxiv_id":"2410.18605","n_code_links":0,"syntology":null},{"paper":"/paper/waffle-multi-modal-model-for-automated-front","slug":"waffle-multi-modal-model-for-automated-front","title":"WAFFLE: Finetuning Multi-Modal Model for Automated Front-End Development","date":"2024-10-24","arxiv_id":"2410.18362","n_code_links":1,"syntology":null},{"paper":null,"slug":"where-am-i-and-what-will-i-see-an-auto","title":"Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction","date":"2024-10-24","arxiv_id":"2410.18962","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-does-the-effective-context-length-of-llms","title":"Why Does the Effective Context Length of LLMs Fall Short?","date":"2024-10-24","arxiv_id":"2410.18745","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-methodology-for-transformer-ratio","title":"A Methodology for Transformer Ratio Adjustment in Small-Size Rotary Transformers","date":"2024-10-23","arxiv_id":"2410.18217","n_code_links":0,"syntology":null},{"paper":"/paper/adem-vl-adaptive-and-embedded-fusion-for","slug":"adem-vl-adaptive-and-embedded-fusion-for","title":"ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning","date":"2024-10-23","arxiv_id":"2410.17779","n_code_links":1,"syntology":null},{"paper":"/paper/alta-compiler-based-analysis-of-transformers","slug":"alta-compiler-based-analysis-of-transformers","title":"ALTA: Compiler-Based Analysis of Transformers","date":"2024-10-23","arxiv_id":"2410.18077","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["google-deepmind/alta"],"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":"/paper/an-adaptive-framework-for-generating","slug":"an-adaptive-framework-for-generating","title":"An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms","date":"2024-10-23","arxiv_id":"2410.17694","n_code_links":1,"syntology":null},{"paper":null,"slug":"anomaly-resilient-temporal-qos-prediction","title":"Anomaly Resilient Temporal QoS Prediction using Hypergraph Convoluted Transformer Network","date":"2024-10-23","arxiv_id":"2410.17762","n_code_links":0,"syntology":null},{"paper":"/paper/att2cpc-attention-guided-lossy-attribute","slug":"att2cpc-attention-guided-lossy-attribute","title":"Att2CPC: Attention-Guided Lossy Attribute Compression of Point Clouds","date":"2024-10-23","arxiv_id":"2410.17823","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-position-how-rotary-embeddings-shape","title":"Beyond Position: the emergence of wavelet-like properties in Transformers","date":"2024-10-23","arxiv_id":"2410.18067","n_code_links":0,"syntology":null},{"paper":null,"slug":"clr-bench-evaluating-large-language-models-in","title":"CLR-Bench: Evaluating Large Language Models in College-level Reasoning","date":"2024-10-23","arxiv_id":"2410.17558","n_code_links":0,"syntology":null},{"paper":null,"slug":"congestion-forecast-for-trains-with-railroad","title":"Congestion Forecast for Trains with Railroad-Graph-based Semi-Supervised Learning using Sparse Passenger Reports","date":"2024-10-23","arxiv_id":"2410.17510","n_code_links":0,"syntology":null},{"paper":"/paper/differentially-private-learning-needs-better","slug":"differentially-private-learning-needs-better","title":"Differentially Private Learning Needs Better Model Initialization and Self-Distillation","date":"2024-10-23","arxiv_id":"2410.17566","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-priors-for-variational-likelihood","slug":"diffusion-priors-for-variational-likelihood","title":"Diffusion Priors for Variational Likelihood Estimation and Image Denoising","date":"2024-10-23","arxiv_id":"2410.17521","n_code_links":1,"syntology":null},{"paper":"/paper/disengcd-a-meta-multigraph-assisted","slug":"disengcd-a-meta-multigraph-assisted","title":"DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis","date":"2024-10-23","arxiv_id":"2410.17564","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"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) · 2 unverified","official":{"repos":["bimk/intelligent-education"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"double-banking-on-knowledge-customized","title":"Double Banking on Knowledge: Customized Modulation and Prototypes for Multi-Modality Semi-supervised Medical Image Segmentation","date":"2024-10-23","arxiv_id":"2410.17565","n_code_links":0,"syntology":null},{"paper":"/paper/dreb-net-dual-stream-restoration-embedding","slug":"dreb-net-dual-stream-restoration-embedding","title":"DREB-Net: Dual-stream Restoration Embedding Blur-feature Fusion Network for High-mobility UAV Object Detection","date":"2024-10-23","arxiv_id":"2410.17822","n_code_links":1,"syntology":null},{"paper":null,"slug":"e-values-for-real-time-residential","title":"e-Values for Real-Time Residential Electricity Demand Forecast Model Selection","date":"2024-10-23","arxiv_id":"2410.17800","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-recognition-with-facial-attention-and","title":"Emotion Recognition with Facial Attention and Objective Activation Functions","date":"2024-10-23","arxiv_id":"2410.17740","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-gans-with-mmd-neural-architecture","slug":"enhancing-gans-with-mmd-neural-architecture","title":"Enhancing GANs with MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition","date":"2024-10-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/escaping-the-forest-sparse-interpretable","slug":"escaping-the-forest-sparse-interpretable","title":"Escaping the Forest: Sparse Interpretable Neural Networks for Tabular Data","date":"2024-10-23","arxiv_id":"2410.17758","n_code_links":1,"syntology":null},{"paper":"/paper/federated-transformer-multi-party-vertical","slug":"federated-transformer-multi-party-vertical","title":"Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data","date":"2024-10-23","arxiv_id":"2410.17986","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["xtra-computing/fet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fiper-generalizable-factorized-fields-for","title":"FIPER: Generalizable Factorized Features for Robust Low-Level Vision Models","date":"2024-10-23","arxiv_id":"2410.18083","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-pdfs-to-structured-data-utilizing-llm","title":"From PDFs to Structured Data: Utilizing LLM Analysis in Sports Database Management","date":"2024-10-23","arxiv_id":"2410.17619","n_code_links":0,"syntology":null},{"paper":null,"slug":"future-token-prediction-causal-language","title":"Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction","date":"2024-10-23","arxiv_id":"2410.18160","n_code_links":0,"syntology":null},{"paper":null,"slug":"gazelle-an-instruction-dataset-for-arabic","title":"Gazelle: An Instruction Dataset for Arabic Writing Assistance","date":"2024-10-23","arxiv_id":"2410.18163","n_code_links":0,"syntology":null},{"paper":null,"slug":"gendp-3d-semantic-fields-for-category-level","title":"GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy","date":"2024-10-23","arxiv_id":"2410.17488","n_code_links":0,"syntology":null},{"paper":"/paper/hcdn-a-change-detection-network-for","slug":"hcdn-a-change-detection-network-for","title":"HCDN: A Change Detection Network for Construction Housekeeping Using Feature Fusion and Large Vision Models","date":"2024-10-23","arxiv_id":"2410.17513","n_code_links":1,"syntology":null},{"paper":null,"slug":"holistic-structure-of-neural-pathways","title":"Holistic structure of neural pathways underlies brain perceptual rivalry: Physical mechanism of auditory stream segregation","date":"2024-10-23","arxiv_id":"2410.17620","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-continually-adapt-text-to-image","slug":"how-to-continually-adapt-text-to-image","title":"How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?","date":"2024-10-23","arxiv_id":"2410.17594","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-the-domain-adaptation-of-retrieval","title":"Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination","date":"2024-10-23","arxiv_id":"2410.17783","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-neural-app-control","title":"Lightweight Neural App Control","date":"2024-10-23","arxiv_id":"2410.17883","n_code_links":0,"syntology":null},{"paper":null,"slug":"locating-information-in-large-language-models","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","date":"2024-10-23","arxiv_id":"2410.17770","n_code_links":0,"syntology":null},{"paper":"/paper/longrag-a-dual-perspective-retrieval","slug":"longrag-a-dual-perspective-retrieval","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","date":"2024-10-23","arxiv_id":"2410.18050","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qingfei1/longrag"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mcubert-memory-efficient-bert-inference-on","title":"MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers","date":"2024-10-23","arxiv_id":"2410.17957","n_code_links":0,"syntology":null},{"paper":"/paper/mia-dpo-multi-image-augmented-direct","slug":"mia-dpo-multi-image-augmented-direct","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models","date":"2024-10-23","arxiv_id":"2410.17637","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":7,"n_instrument":3,"unverified":1,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["liuziyu77/mia-dpo"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"milora-efficient-mixture-of-low-rank","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","date":"2024-10-23","arxiv_id":"2410.18035","n_code_links":0,"syntology":null},{"paper":null,"slug":"mojobench-language-modeling-and-benchmarks","title":"MojoBench: Language Modeling and Benchmarks for Mojo","date":"2024-10-23","arxiv_id":"2410.17736","n_code_links":0,"syntology":null},{"paper":"/paper/multi-scale-feature-reconstruction-network","slug":"multi-scale-feature-reconstruction-network","title":"Multi-scale feature reconstruction network for industrial anomaly detection","date":"2024-10-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"nexusindex-integrating-advanced-vector","title":"NexusIndex: Integrating Advanced Vector Indexing and Multi-Model Embeddings for Robust Fake News Detection","date":"2024-10-23","arxiv_id":"2410.18294","n_code_links":0,"syntology":null},{"paper":"/paper/omniflatten-an-end-to-end-gpt-model-for","slug":"omniflatten-an-end-to-end-gpt-model-for","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","date":"2024-10-23","arxiv_id":"2410.17799","n_code_links":1,"syntology":null},{"paper":null,"slug":"petah-parameter-efficient-task-adaptation-for","title":"PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context","date":"2024-10-23","arxiv_id":"2410.17661","n_code_links":0,"syntology":null},{"paper":null,"slug":"pgdiffseg-prior-guided-denoising-diffusion","title":"PGDiffSeg: Prior-Guided Denoising Diffusion Model with Parameter-Shared Attention for Breast Cancer Segmentation","date":"2024-10-23","arxiv_id":"2410.17812","n_code_links":0,"syntology":null},{"paper":"/paper/pod-attention-unlocking-full-prefill-decode","slug":"pod-attention-unlocking-full-prefill-decode","title":"POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","date":"2024-10-23","arxiv_id":"2410.18038","n_code_links":1,"syntology":null},{"paper":null,"slug":"simrag-self-improving-retrieval-augmented","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","date":"2024-10-23","arxiv_id":"2410.17952","n_code_links":0,"syntology":null},{"paper":"/paper/spiking-graph-neural-network-on-riemannian","slug":"spiking-graph-neural-network-on-riemannian","title":"Spiking Graph Neural Network on Riemannian Manifolds","date":"2024-10-23","arxiv_id":"2410.17941","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhenhHuang/MSG"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/stick-breaking-attention","slug":"stick-breaking-attention","title":"Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study","date":"2024-10-23","arxiv_id":"2410.17980","n_code_links":2,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ibm/dolomite-engine","shawntan/stickbreaking-attention"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/surgical-scene-segmentation-by-transformer","slug":"surgical-scene-segmentation-by-transformer","title":"Surgical Scene Segmentation by Transformer With Asymmetric Feature Enhancement","date":"2024-10-23","arxiv_id":"2410.17642","n_code_links":1,"syntology":null}],"record_sha256":"9e0f3a61c8ea4f8571304294e5d8b986a55671e40d4e21a99affad9a1be155aa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}