{"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/4","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":4,"pages_in_order":249,"rows_per_page":100,"rows":[301,400],"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/3","next":"/method/multi-head-attention/papers/5","papers":[{"paper":null,"slug":"search-wisely-mitigating-sub-optimal-agentic","title":"Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty","date":"2025-05-22","arxiv_id":"2505.17281","n_code_links":0,"syntology":null},{"paper":null,"slug":"swin-transformer-for-robust-cgi-images","title":"Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces","date":"2025-05-22","arxiv_id":"2505.16253","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-polar-express-optimal-matrix-sign-methods","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","date":"2025-05-22","arxiv_id":"2505.16932","n_code_links":0,"syntology":null},{"paper":null,"slug":"three-minds-one-legend-jailbreak-large","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","date":"2025-05-22","arxiv_id":"2505.16241","n_code_links":0,"syntology":null},{"paper":"/paper/training-free-efficient-video-generation-via","slug":"training-free-efficient-video-generation-via","title":"Training-Free Efficient Video Generation via Dynamic Token Carving","date":"2025-05-22","arxiv_id":"2505.16864","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-copilot-learning-from-the-mistake","slug":"transformer-copilot-learning-from-the-mistake","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","date":"2025-05-22","arxiv_id":"2505.16270","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jiaruzouu/transformercopilot"],"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","unlocated"]}}},{"paper":null,"slug":"understanding-differential-transformer","title":"Understanding Differential Transformer Unchains Pretrained Self-Attentions","date":"2025-05-22","arxiv_id":"2505.16333","n_code_links":0,"syntology":null},{"paper":null,"slug":"voxrag-a-step-toward-transcription-free-rag","title":"VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering","date":"2025-05-22","arxiv_id":"2505.17326","n_code_links":0,"syntology":null},{"paper":"/paper/walk-retrieve-simple-yet-effective-zero-shot","slug":"walk-retrieve-simple-yet-effective-zero-shot","title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","date":"2025-05-22","arxiv_id":"2505.16849","n_code_links":1,"syntology":null},{"paper":null,"slug":"adue-improving-uncertainty-estimation-head","title":"AdUE: Improving uncertainty estimation head for LoRA adapters in LLMs","date":"2025-05-21","arxiv_id":"2505.15443","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-private-gpt-never","title":"An Efficient Private GPT Never Autoregressively Decodes","date":"2025-05-21","arxiv_id":"2505.15252","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploratory-approach-towards-investigating","title":"An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection","date":"2025-05-21","arxiv_id":"2505.16039","n_code_links":0,"syntology":null},{"paper":null,"slug":"bountybench-dollar-impact-of-ai-agent","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","date":"2025-05-21","arxiv_id":"2505.15216","n_code_links":0,"syntology":null},{"paper":null,"slug":"br-taxqa-r-a-dataset-for-question-answering","title":"BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law","date":"2025-05-21","arxiv_id":"2505.15916","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-vs-autoregressive-language-models-a","title":"Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective","date":"2025-05-21","arxiv_id":"2505.15045","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-adaptive-skin-lesion-classification","title":"Domain Adaptive Skin Lesion Classification via Conformal Ensemble of Vision Transformers","date":"2025-05-21","arxiv_id":"2505.15997","n_code_links":0,"syntology":null},{"paper":null,"slug":"filtering-learning-histories-enhances-in","title":"Filtering Learning Histories Enhances In-Context Reinforcement Learning","date":"2025-05-21","arxiv_id":"2505.15143","n_code_links":0,"syntology":null},{"paper":"/paper/hdlxgraph-bridging-large-language-models-and","slug":"hdlxgraph-bridging-large-language-models-and","title":"HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases","date":"2025-05-21","arxiv_id":"2505.15701","n_code_links":1,"syntology":null},{"paper":null,"slug":"infodeepseek-benchmarking-agentic-information","title":"InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation","date":"2025-05-21","arxiv_id":"2505.15872","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-foundation-models-for-multimodal","title":"Leveraging Foundation Models for Multimodal Graph-Based Action Recognition","date":"2025-05-21","arxiv_id":"2505.15192","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-command","title":"Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects","date":"2025-05-21","arxiv_id":"2505.15088","n_code_links":0,"syntology":null},{"paper":"/paper/logicase-effective-test-case-generation-from","slug":"logicase-effective-test-case-generation-from","title":"LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming","date":"2025-05-21","arxiv_id":"2505.15039","n_code_links":0,"syntology":{"ran":11,"of":19,"n_ran_checked":5,"n_instrument":6,"unverified":8,"pointer_only":19,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":null,"slug":"maxpoolbert-enhancing-bert-classification-via","title":"MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation","date":"2025-05-21","arxiv_id":"2505.15696","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-insights-into-grokking-from-the","title":"Mechanistic Insights into Grokking from the Embedding Layer","date":"2025-05-21","arxiv_id":"2505.15624","n_code_links":0,"syntology":null},{"paper":null,"slug":"ranking-free-rag-replacing-re-ranking-with","title":"Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains","date":"2025-05-21","arxiv_id":"2505.16014","n_code_links":0,"syntology":null},{"paper":null,"slug":"reranking-with-compressed-document","title":"Reranking with Compressed Document Representation","date":"2025-05-21","arxiv_id":"2505.15394","n_code_links":0,"syntology":null},{"paper":"/paper/rlbenchnet-the-right-network-for-the-right","slug":"rlbenchnet-the-right-network-for-the-right","title":"RLBenchNet: The Right Network for the Right Reinforcement Learning Task","date":"2025-05-21","arxiv_id":"2505.15040","n_code_links":1,"syntology":null},{"paper":null,"slug":"robo-dm-data-management-for-large-robot","title":"Robo-DM: Data Management For Large Robot Datasets","date":"2025-05-21","arxiv_id":"2505.15558","n_code_links":0,"syntology":null},{"paper":"/paper/sama-unet-enhancing-medical-image","slug":"sama-unet-enhancing-medical-image","title":"SAMA-UNet: Enhancing Medical Image Segmentation with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning","date":"2025-05-21","arxiv_id":"2505.15234","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-diffusion-transformers-efficiently","slug":"scaling-diffusion-transformers-efficiently","title":"Scaling Diffusion Transformers Efficiently via $μ$P","date":"2025-05-21","arxiv_id":"2505.15270","n_code_links":1,"syntology":null},{"paper":"/paper/silent-leaks-implicit-knowledge-extraction","slug":"silent-leaks-implicit-knowledge-extraction","title":"Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries","date":"2025-05-21","arxiv_id":"2505.15420","n_code_links":1,"syntology":null},{"paper":null,"slug":"single-llm-multiple-roles-a-unified-retrieval","title":"Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization","date":"2025-05-21","arxiv_id":"2505.15444","n_code_links":0,"syntology":null},{"paper":null,"slug":"small-language-models-in-the-real-world","title":"Small Language Models in the Real World: Insights from Industrial Text Classification","date":"2025-05-21","arxiv_id":"2505.16078","n_code_links":0,"syntology":null},{"paper":"/paper/sonnet-spectral-operator-neural-network-for","slug":"sonnet-spectral-operator-neural-network-for","title":"Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting","date":"2025-05-21","arxiv_id":"2505.15312","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-empowered-channel-estimation-for-block","title":"AI-empowered Channel Estimation for Block-based Active IRS-enhanced Hybrid-field IoT Network","date":"2025-05-20","arxiv_id":"2505.14098","n_code_links":0,"syntology":null},{"paper":"/paper/articulatory-feature-prediction-from-surface","slug":"articulatory-feature-prediction-from-surface","title":"Articulatory Feature Prediction from Surface EMG during Speech Production","date":"2025-05-20","arxiv_id":"2505.13814","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-dataset-generation-for-knowledge","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","date":"2025-05-20","arxiv_id":"2505.14212","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-text-unveiling-privacy-vulnerabilities","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","date":"2025-05-20","arxiv_id":"2505.13957","n_code_links":0,"syntology":null},{"paper":"/paper/breaking-bad-tokens-detoxification-of-llms","slug":"breaking-bad-tokens-detoxification-of-llms","title":"Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders","date":"2025-05-20","arxiv_id":"2505.14536","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/cad-coder-an-open-source-vision-language","slug":"cad-coder-an-open-source-vision-language","title":"CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation","date":"2025-05-20","arxiv_id":"2505.14646","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["anniedoris/cad-coder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"choosing-a-model-shaping-a-future-comparing","title":"Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AI","date":"2025-05-20","arxiv_id":"2505.14435","n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-augmented-monte-carlo-tree-search-for","title":"Cost-Augmented Monte Carlo Tree Search for LLM-Assisted Planning","date":"2025-05-20","arxiv_id":"2505.14656","n_code_links":0,"syntology":null},{"paper":null,"slug":"divide-by-question-conquer-by-agent-split-rag","title":"Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning","date":"2025-05-20","arxiv_id":"2505.13994","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-use-their-depth","slug":"do-language-models-use-their-depth","title":"Do Language Models Use Their Depth Efficiently?","date":"2025-05-20","arxiv_id":"2505.13898","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["robertcsordas/llm_effective_depth"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dsmentor-enhancing-data-science-agents-with","title":"DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation","date":"2025-05-20","arxiv_id":"2505.14163","n_code_links":0,"syntology":null},{"paper":"/paper/eeg-to-text-translation-a-model-for","slug":"eeg-to-text-translation-a-model-for","title":"EEG-to-Text Translation: A Model for Deciphering Human Brain Activity","date":"2025-05-20","arxiv_id":"2505.13936","n_code_links":1,"syntology":null},{"paper":null,"slug":"energy-efficient-deep-reinforcement-learning","title":"Energy-Efficient Deep Reinforcement Learning with Spiking Transformers","date":"2025-05-20","arxiv_id":"2505.14533","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-abstractive-summarization-of","slug":"enhancing-abstractive-summarization-of","title":"Enhancing Abstractive Summarization of Scientific Papers Using Structure Information","date":"2025-05-20","arxiv_id":"2505.14179","n_code_links":1,"syntology":null},{"paper":null,"slug":"every-pixel-tells-a-story-end-to-end-urdu","title":"Every Pixel Tells a Story: End-to-End Urdu Newspaper OCR","date":"2025-05-20","arxiv_id":"2505.13943","n_code_links":0,"syntology":null},{"paper":"/paper/flashkat-understanding-and-addressing","slug":"flashkat-understanding-and-addressing","title":"FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer","date":"2025-05-20","arxiv_id":"2505.13813","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-ai-at-the-crossroads-light-bulb","title":"Generative AI at the Crossroads: Light Bulb, Dynamo, or Microscope?","date":"2025-05-20","arxiv_id":"2505.14588","n_code_links":0,"syntology":null},{"paper":"/paper/informatics-for-food-processing","slug":"informatics-for-food-processing","title":"Informatics for Food Processing","date":"2025-05-20","arxiv_id":"2505.17087","n_code_links":1,"syntology":null},{"paper":"/paper/latent-flow-transformer","slug":"latent-flow-transformer","title":"Latent Flow Transformer","date":"2025-05-20","arxiv_id":"2505.14513","n_code_links":1,"syntology":null},{"paper":"/paper/learning-spatio-temporal-dynamics-for","slug":"learning-spatio-temporal-dynamics-for","title":"Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer","date":"2025-05-20","arxiv_id":"2505.13857","n_code_links":2,"syntology":null},{"paper":null,"slug":"low-cost-flashattention-with-fused","title":"Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators","date":"2025-05-20","arxiv_id":"2505.14314","n_code_links":0,"syntology":null},{"paper":"/paper/modrwkv-transformer-multimodality-in-linear","slug":"modrwkv-transformer-multimodality-in-linear","title":"ModRWKV: Transformer Multimodality in Linear Time","date":"2025-05-20","arxiv_id":"2505.14505","n_code_links":1,"syntology":null},{"paper":null,"slug":"msdformer-multi-scale-discrete-transformer","title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","date":"2025-05-20","arxiv_id":"2505.14202","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-channel-swin-transformer-framework-for","title":"Multi-Channel Swin Transformer Framework for Bearing Remaining Useful Life Prediction","date":"2025-05-20","arxiv_id":"2505.14897","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-rag-driven-anomaly-detection-and","title":"Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models","date":"2025-05-20","arxiv_id":"2505.13828","n_code_links":0,"syntology":null},{"paper":"/paper/omnistyle-filtering-high-quality-style","slug":"omnistyle-filtering-high-quality-style","title":"OmniStyle: Filtering High Quality Style Transfer Data at Scale","date":"2025-05-20","arxiv_id":"2505.14028","n_code_links":1,"syntology":null},{"paper":null,"slug":"out-of-distribution-generalization-of-in","title":"Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective","date":"2025-05-20","arxiv_id":"2505.14808","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-bert-for-german-compound-semantics","title":"Probing BERT for German Compound Semantics","date":"2025-05-20","arxiv_id":"2505.14130","n_code_links":0,"syntology":null},{"paper":"/paper/process-vs-outcome-reward-which-is-better-for","slug":"process-vs-outcome-reward-which-is-better-for","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14069","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wlzhang2020/reasonrag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/reactdiff-latent-diffusion-for-facial","slug":"reactdiff-latent-diffusion-for-facial","title":"ReactDiff: Latent Diffusion for Facial Reaction Generation","date":"2025-05-20","arxiv_id":"2505.14151","n_code_links":1,"syntology":null},{"paper":"/paper/s3-you-don-t-need-that-much-data-to-train-a","slug":"s3-you-don-t-need-that-much-data-to-train-a","title":"s3: You Don't Need That Much Data to Train a Search Agent via RL","date":"2025-05-20","arxiv_id":"2505.14146","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":3,"n_instrument":4,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["pat-jj/s3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sample-and-computationally-efficient-1","slug":"sample-and-computationally-efficient-1","title":"Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation","date":"2025-05-20","arxiv_id":"2505.14821","n_code_links":1,"syntology":null},{"paper":null,"slug":"scaling-laws-for-state-dynamics-in-large","title":"Scaling Laws for State Dynamics in Large Language Models","date":"2025-05-20","arxiv_id":"2505.14892","n_code_links":0,"syntology":null},{"paper":null,"slug":"scan-semantic-document-layout-analysis-for","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","date":"2025-05-20","arxiv_id":"2505.14381","n_code_links":0,"syntology":null},{"paper":null,"slug":"selective-structured-state-space-for","title":"Selective Structured State Space for Multispectral-fused Small Target Detection","date":"2025-05-20","arxiv_id":"2505.14043","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-normalized-cut-problem-with","title":"Normalized Cut with Reinforcement Learning in Constrained Action Space","date":"2025-05-20","arxiv_id":"2505.13986","n_code_links":0,"syntology":null},{"paper":"/paper/ssps-self-supervised-positive-sampling-for","slug":"ssps-self-supervised-positive-sampling-for","title":"SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification","date":"2025-05-20","arxiv_id":"2505.14561","n_code_links":1,"syntology":null},{"paper":null,"slug":"stree-speculative-tree-decoding-for-hybrid","title":"STree: Speculative Tree Decoding for Hybrid State-Space Models","date":"2025-05-20","arxiv_id":"2505.14969","n_code_links":0,"syntology":null},{"paper":null,"slug":"subquadratic-algorithms-and-hardness-for","title":"Subquadratic Algorithms and Hardness for Attention with Any Temperature","date":"2025-05-20","arxiv_id":"2505.14840","n_code_links":0,"syntology":null},{"paper":"/paper/tcsinger-2-customizable-multilingual-zero","slug":"tcsinger-2-customizable-multilingual-zero","title":"TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis","date":"2025-05-20","arxiv_id":"2505.14910","n_code_links":1,"syntology":null},{"paper":null,"slug":"a3-an-analytical-low-rank-approximation","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","date":"2025-05-19","arxiv_id":"2505.12942","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-adaptive-retrieval-augmented","title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","date":"2025-05-19","arxiv_id":"2505.12731","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-testing-in-llms-insights-into","title":"Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities","date":"2025-05-19","arxiv_id":"2505.13195","n_code_links":0,"syntology":null},{"paper":null,"slug":"amaqa-a-metadata-based-qa-dataset-for-rag","title":"AMAQA: A Metadata-based QA Dataset for RAG Systems","date":"2025-05-19","arxiv_id":"2505.13557","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-good-at-detecting","title":"Are Large Language Models Good at Detecting Propaganda?","date":"2025-05-19","arxiv_id":"2505.13706","n_code_links":0,"syntology":null},{"paper":"/paper/climate-research-domain-berts-pretraining","slug":"climate-research-domain-berts-pretraining","title":"Climate Research Domain BERTs: Pretraining, Adaptation, and Evaluation","date":"2025-05-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cmlformer-a-dual-decoder-transformer-with","title":"CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling","date":"2025-05-19","arxiv_id":"2505.12587","n_code_links":0,"syntology":null},{"paper":null,"slug":"eavit-efficient-and-accurate-human-value","title":"EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs","date":"2025-05-19","arxiv_id":"2505.12792","n_code_links":0,"syntology":null},{"paper":"/paper/effective-and-transparent-rag-adaptive-reward","slug":"effective-and-transparent-rag-adaptive-reward","title":"Effective and Transparent RAG: Adaptive-Reward Reinforcement Learning for Decision Traceability","date":"2025-05-19","arxiv_id":"2505.13258","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-latent-computation-in-transformers","title":"Enhancing Latent Computation in Transformers with Latent Tokens","date":"2025-05-19","arxiv_id":"2505.12629","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-rag-methods-for","title":"Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain","date":"2025-05-19","arxiv_id":"2505.13006","n_code_links":0,"syntology":null},{"paper":null,"slug":"guidedmorph-two-stage-deformable-registration","title":"GuidedMorph: Two-Stage Deformable Registration for Breast MRI","date":"2025-05-19","arxiv_id":"2505.13414","n_code_links":0,"syntology":null},{"paper":"/paper/know-or-not-a-library-for-evaluating-out-of","slug":"know-or-not-a-library-for-evaluating-out-of","title":"Know Or Not: a library for evaluating out-of-knowledge base robustness","date":"2025-05-19","arxiv_id":"2505.13545","n_code_links":1,"syntology":null},{"paper":"/paper/know3-rag-a-knowledge-aware-rag-framework","slug":"know3-rag-a-knowledge-aware-rag-framework","title":"Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering","date":"2025-05-19","arxiv_id":"2505.12662","n_code_links":1,"syntology":null},{"paper":null,"slug":"lidar-mot-detr-a-lidar-based-two-stage","title":"LiDAR MOT-DETR: A LiDAR-based Two-Stage Transformer for 3D Multiple Object Tracking","date":"2025-05-19","arxiv_id":"2505.12753","n_code_links":0,"syntology":null},{"paper":"/paper/msvit-improving-spiking-vision-transformer","slug":"msvit-improving-spiking-vision-transformer","title":"MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion","date":"2025-05-19","arxiv_id":"2505.14719","n_code_links":1,"syntology":null},{"paper":"/paper/multi-head-temporal-latent-attention","slug":"multi-head-temporal-latent-attention","title":"Multi-head Temporal Latent Attention","date":"2025-05-19","arxiv_id":"2505.13544","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":["d-keqi/mlta"],"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":"omgpt-a-sequence-modeling-framework-for-data","title":"OMGPT: A Sequence Modeling Framework for Data-driven Operational Decision Making","date":"2025-05-19","arxiv_id":"2505.13580","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-retrieval-augmented-generation-for","title":"Optimizing Retrieval Augmented Generation for Object Constraint Language","date":"2025-05-19","arxiv_id":"2505.13129","n_code_links":0,"syntology":null},{"paper":"/paper/pptnet-a-hybrid-periodic-pattern-transformer","slug":"pptnet-a-hybrid-periodic-pattern-transformer","title":"PPTNet: A Hybrid Periodic Pattern-Transformer Architecture for Traffic Flow Prediction and Congestion Identification","date":"2025-05-19","arxiv_id":"2505.13047","n_code_links":1,"syntology":null},{"paper":null,"slug":"pyramid-sparse-transformer-enhancing-multi","title":"Pyramid Sparse Transformer: Enhancing Multi-Scale Feature Fusion with Dynamic Token Selection","date":"2025-05-19","arxiv_id":"2505.12772","n_code_links":0,"syntology":null},{"paper":null,"slug":"rar-setting-knowledge-tripwires-for-retrieval","title":"RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection","date":"2025-05-19","arxiv_id":"2505.13581","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplicity-is-key-an-unsupervised-pretraining","title":"Simplicity is Key: An Unsupervised Pretraining Approach for Sparse Radio Channels","date":"2025-05-19","arxiv_id":"2505.13055","n_code_links":0,"syntology":null},{"paper":null,"slug":"soundit-geo-contextual-soundscape-to","title":"SounDiT: Geo-Contextual Soundscape-to-Landscape Generation","date":"2025-05-19","arxiv_id":"2505.12734","n_code_links":0,"syntology":null},{"paper":null,"slug":"suicide-risk-assessment-using-multimodal","title":"Suicide Risk Assessment Using Multimodal Speech Features: A Study on the SW1 Challenge Dataset","date":"2025-05-19","arxiv_id":"2505.13069","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-hidden-structure-improving-legal-document","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","date":"2025-05-19","arxiv_id":"2505.12837","n_code_links":0,"syntology":null}],"record_sha256":"717bec2c03a583b4d6e8d69b5579f2ed62e5e7958a6c10516139ad9967078572","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}