{"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/28","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":28,"pages_in_order":249,"rows_per_page":100,"rows":[2701,2800],"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/27","next":"/method/multi-head-attention/papers/29","papers":[{"paper":null,"slug":"leveraging-convolutional-neural-network","title":"Leveraging Convolutional Neural Network-Transformer Synergy for Predictive Modeling in Risk-Based Applications","date":"2024-12-24","arxiv_id":"2412.18222","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-deep-learning-with-multi-head","title":"Leveraging Deep Learning with Multi-Head Attention for Accurate Extraction of Medicine from Handwritten Prescriptions","date":"2024-12-24","arxiv_id":"2412.18199","n_code_links":0,"syntology":null},{"paper":null,"slug":"molly-making-large-language-model-agents","title":"Molly: Making Large Language Model Agents Solve Python Problem More Logically","date":"2024-12-24","arxiv_id":"2412.18093","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-mathematical-reasoning-advancing","slug":"multilingual-mathematical-reasoning-advancing","title":"Multilingual Mathematical Reasoning: Advancing Open-Source LLMs in Hindi and English","date":"2024-12-24","arxiv_id":"2412.18415","n_code_links":1,"syntology":null},{"paper":null,"slug":"pirates-of-the-rag-adaptively-attacking-llms","title":"Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases","date":"2024-12-24","arxiv_id":"2412.18295","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-the-proximity-relationships-of","title":"Research on the Proximity Relationships of Psychosomatic Disease Knowledge Graph Modules Extracted by Large Language Models","date":"2024-12-24","arxiv_id":"2412.18419","n_code_links":0,"syntology":null},{"paper":"/paper/segment-based-attention-masking-for-gpts","slug":"segment-based-attention-masking-for-gpts","title":"Segment-Based Attention Masking for GPTs","date":"2024-12-24","arxiv_id":"2412.18487","n_code_links":1,"syntology":null},{"paper":"/paper/tab-transformer-attention-bottlenecks-enable","slug":"tab-transformer-attention-bottlenecks-enable","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","date":"2024-12-24","arxiv_id":"2412.18675","n_code_links":1,"syntology":null},{"paper":null,"slug":"timelyllm-segmented-llm-serving-system-for","title":"TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications","date":"2024-12-24","arxiv_id":"2412.18695","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-the-potential-of-multiple-bert","title":"Unlocking the Potential of Multiple BERT Models for Bangla Question Answering in NCTB Textbooks","date":"2024-12-24","arxiv_id":"2412.18440","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-query-optimization-in-large","title":"A Survey of Query Optimization in Large Language Models","date":"2024-12-23","arxiv_id":"2412.17558","n_code_links":0,"syntology":null},{"paper":"/paper/citebart-learning-to-generate-citations-for","slug":"citebart-learning-to-generate-citations-for","title":"CiteBART: Learning to Generate Citations for Local Citation Recommendation","date":"2024-12-23","arxiv_id":"2412.17534","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["eyclk/citationrecommendation"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"comparative-analysis-of-document-level","title":"Comparative Analysis of Document-Level Embedding Methods for Similarity Scoring on Shakespeare Sonnets and Taylor Swift Lyrics","date":"2024-12-23","arxiv_id":"2412.17552","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-multi-modal-prototypes-are","slug":"comprehensive-multi-modal-prototypes-are","title":"Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection","date":"2024-12-23","arxiv_id":"2412.17800","n_code_links":1,"syntology":null},{"paper":"/paper/diffformer-a-differential-spatial-spectral","slug":"diffformer-a-differential-spatial-spectral","title":"DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification","date":"2024-12-23","arxiv_id":"2412.17350","n_code_links":1,"syntology":null},{"paper":null,"slug":"edge-ai-for-agriculture-lightweight-vision","title":"Edge-AI for Agriculture: Lightweight Vision Models for Disease Detection in Resource-Limited Settings","date":"2024-12-23","arxiv_id":"2412.18635","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-fine-tuning-methodology-of-text","slug":"efficient-fine-tuning-methodology-of-text","title":"Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)","date":"2024-12-23","arxiv_id":"2412.17364","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-gradient-computation-for-rope-attention","title":"Fast Gradient Computation for RoPE Attention in Almost Linear Time","date":"2024-12-23","arxiv_id":"2412.17316","n_code_links":0,"syntology":null},{"paper":"/paper/layerdropback-a-universally-applicable","slug":"layerdropback-a-universally-applicable","title":"LayerDropBack: A Universally Applicable Approach for Accelerating Training of Deep Networks","date":"2024-12-23","arxiv_id":"2412.18027","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-preference-data-synthetic","slug":"multimodal-preference-data-synthetic","title":"Multimodal Preference Data Synthetic Alignment with Reward Model","date":"2024-12-23","arxiv_id":"2412.17417","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-satisfied-user-and-machine-ratio","title":"Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach","date":"2024-12-23","arxiv_id":"2412.17477","n_code_links":0,"syntology":null},{"paper":"/paper/steinformer-spatial-temporal-interaction","slug":"steinformer-spatial-temporal-interaction","title":"STeInFormer: Spatial-Temporal Interaction Transformer Architecture for Remote Sensing Change Detection","date":"2024-12-23","arxiv_id":"2412.17247","n_code_links":1,"syntology":null},{"paper":null,"slug":"theoretical-constraints-on-the-expressive","title":"Theoretical Constraints on the Expressive Power of $\\mathsf{RoPE}$-based Tensor Attention Transformers","date":"2024-12-23","arxiv_id":"2412.18040","n_code_links":0,"syntology":null},{"paper":"/paper/token-statistics-transformer-linear-time","slug":"token-statistics-transformer-linear-time","title":"Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction","date":"2024-12-23","arxiv_id":"2412.17810","n_code_links":1,"syntology":null},{"paper":null,"slug":"uroadnet-dual-sparse-attentive-u-net-for","title":"URoadNet: Dual Sparse Attentive U-Net for Multiscale Road Network Extraction","date":"2024-12-23","arxiv_id":"2412.17573","n_code_links":0,"syntology":null},{"paper":"/paper/a-reality-check-on-context-utilisation-for","slug":"a-reality-check-on-context-utilisation-for","title":"A Reality Check on Context Utilisation for Retrieval-Augmented Generation","date":"2024-12-22","arxiv_id":"2412.17031","n_code_links":1,"syntology":null},{"paper":"/paper/an-openmind-for-3d-medical-vision-self","slug":"an-openmind-for-3d-medical-vision-self","title":"An OpenMind for 3D medical vision self-supervised learning","date":"2024-12-22","arxiv_id":"2412.17041","n_code_links":1,"syntology":null},{"paper":null,"slug":"bridging-auditory-perception-and-language","title":"Bridging Auditory Perception and Language Comprehension through MEG-Driven Encoding Models","date":"2024-12-22","arxiv_id":"2501.03246","n_code_links":0,"syntology":null},{"paper":null,"slug":"dr-encoder-encode-low-rank-gradients-with","title":"DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately","date":"2024-12-22","arxiv_id":"2412.17053","n_code_links":0,"syntology":null},{"paper":"/paper/multifaceted-user-modeling-in-recommendation","slug":"multifaceted-user-modeling-in-recommendation","title":"Multifaceted User Modeling in Recommendation: A Federated Foundation Models Approach","date":"2024-12-22","arxiv_id":"2412.16969","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-fusing-chatgpt-and-ensemble-learning-in","title":"On Fusing ChatGPT and Ensemble Learning in Discon-tinuous Named Entity Recognition in Health Corpora","date":"2024-12-22","arxiv_id":"2412.16976","n_code_links":0,"syntology":null},{"paper":"/paper/psychadapter-adapting-llm-transformers-to","slug":"psychadapter-adapting-llm-transformers-to","title":"PsychAdapter: Adapting LLM Transformers to Reflect Traits, Personality and Mental Health","date":"2024-12-22","arxiv_id":"2412.16882","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconsidering-smt-over-nmt-for-closely","title":"Reconsidering SMT Over NMT for Closely Related Languages: A Case Study of Persian-Hindi Pair","date":"2024-12-22","arxiv_id":"2412.16877","n_code_links":0,"syntology":null},{"paper":null,"slug":"robustness-of-large-language-models-against","title":"Robustness of Large Language Models Against Adversarial Attacks","date":"2024-12-22","arxiv_id":"2412.17011","n_code_links":0,"syntology":null},{"paper":null,"slug":"substationai-multimodal-large-model-based","title":"SubstationAI: Multimodal Large Model-Based Approaches for Analyzing Substation Equipment Faults","date":"2024-12-22","arxiv_id":"2412.17077","n_code_links":0,"syntology":null},{"paper":"/paper/survey-on-abstractive-text-summarization","slug":"survey-on-abstractive-text-summarization","title":"Survey on Abstractive Text Summarization: Dataset, Models, and Metrics","date":"2024-12-22","arxiv_id":"2412.17165","n_code_links":2,"syntology":null},{"paper":null,"slug":"tar3d-creating-high-quality-3d-assets-via","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","date":"2024-12-22","arxiv_id":"2412.16919","n_code_links":0,"syntology":null},{"paper":null,"slug":"alzheimerrag-multimodal-retrieval-augmented","title":"AlzheimerRAG: Multimodal Retrieval Augmented Generation for PubMed articles","date":"2024-12-21","arxiv_id":"2412.16701","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-social-alignment-do-personality","title":"Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?","date":"2024-12-21","arxiv_id":"2412.16772","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-large-language-models-for-1","title":"Distilling Large Language Models for Efficient Clinical Information Extraction","date":"2024-12-21","arxiv_id":"2501.00031","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-contrastive-learning-inspired-by","slug":"enhancing-contrastive-learning-inspired-by","title":"Enhancing Contrastive Learning Inspired by the Philosophy of \"The Blind Men and the Elephant\"","date":"2024-12-21","arxiv_id":"2412.16522","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-large-language-4","title":"Evaluating the Performance of Large Language Models in Scientific Claim Detection and Classification","date":"2024-12-21","arxiv_id":"2412.16486","n_code_links":0,"syntology":null},{"paper":"/paper/flash3d-super-scaling-point-transformers","slug":"flash3d-super-scaling-point-transformers","title":"Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry Locality","date":"2024-12-21","arxiv_id":"2412.16481","n_code_links":1,"syntology":null},{"paper":null,"slug":"formal-language-knowledge-corpus-for","title":"Formal Language Knowledge Corpus for Retrieval Augmented Generation","date":"2024-12-21","arxiv_id":"2412.16689","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-histopathology-images-to-cell-clouds","title":"From Histopathology Images to Cell Clouds: Learning Slide Representations with Hierarchical Cell Transformer","date":"2024-12-21","arxiv_id":"2412.16715","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-cyberbullying-roles-in-social","title":"Identifying Cyberbullying Roles in Social Media","date":"2024-12-21","arxiv_id":"2412.16417","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-fim-code-completions-via-context","title":"Improving FIM Code Completions via Context & Curriculum Based Learning","date":"2024-12-21","arxiv_id":"2412.16589","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-compression-via-low","title":"Lillama: Large Language Models Compression via Low-Rank Feature Distillation","date":"2024-12-21","arxiv_id":"2412.16719","n_code_links":0,"syntology":null},{"paper":null,"slug":"object-detection-approaches-to-identifying","title":"Object Detection Approaches to Identifying Hand Images with High Forensic Values","date":"2024-12-21","arxiv_id":"2412.16431","n_code_links":0,"syntology":null},{"paper":null,"slug":"paraformer-parameterization-of-sub-grid-scale","title":"Paraformer: Parameterization of Sub-grid Scale Processes Using Transformers","date":"2024-12-21","arxiv_id":"2412.16763","n_code_links":0,"syntology":null},{"paper":"/paper/quantum-like-contextuality-in-large-language","slug":"quantum-like-contextuality-in-large-language","title":"Quantum-Like Contextuality in Large Language Models","date":"2024-12-21","arxiv_id":"2412.16806","n_code_links":1,"syntology":null},{"paper":null,"slug":"research-on-violent-text-detection-system","title":"Research on Violent Text Detection System Based on BERT-fasttext Model","date":"2024-12-21","arxiv_id":"2412.16455","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensitive-image-classification-by-vision","title":"Sensitive Image Classification by Vision Transformers","date":"2024-12-21","arxiv_id":"2412.16446","n_code_links":0,"syntology":null},{"paper":"/paper/stkdrec-spatial-temporal-knowledge","slug":"stkdrec-spatial-temporal-knowledge","title":"STKDRec: Spatial-Temporal Knowledge Distillation for Takeaway Recommendation","date":"2024-12-21","arxiv_id":"2412.16502","n_code_links":1,"syntology":null},{"paper":null,"slug":"timerag-boosting-llm-time-series-forecasting","title":"TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation","date":"2024-12-21","arxiv_id":"2412.16643","n_code_links":0,"syntology":null},{"paper":"/paper/towards-more-robust-retrieval-augmented","slug":"towards-more-robust-retrieval-augmented","title":"Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks","date":"2024-12-21","arxiv_id":"2412.16708","n_code_links":1,"syntology":null},{"paper":null,"slug":"vsformer-value-and-shape-aware-transformer","title":"VSFormer: Value and Shape-Aware Transformer with Prior-Enhanced Self-Attention for Multivariate Time Series Classification","date":"2024-12-21","arxiv_id":"2412.16515","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptable-and-precise-enterprise-scenario-llm","title":"Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipeline","date":"2024-12-20","arxiv_id":"2412.15660","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-robustness-through-dynamic","title":"Adversarial Robustness through Dynamic Ensemble Learning","date":"2024-12-20","arxiv_id":"2412.16254","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-llms-and-slms-for-patient","title":"Benchmarking LLMs and SLMs for patient reported outcomes","date":"2024-12-20","arxiv_id":"2412.16291","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-obfuscate-code-a-systematic-analysis","title":"Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation","date":"2024-12-20","arxiv_id":"2412.16135","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-linguistic-nuances-in-mental-health","title":"Decoding Linguistic Nuances in Mental Health Text Classification Using Expressive Narrative Stories","date":"2024-12-20","arxiv_id":"2412.16302","n_code_links":0,"syntology":null},{"paper":null,"slug":"demystifying-the-potential-of-chatgpt-4","title":"Demystifying the Potential of ChatGPT-4 Vision for Construction Progress Monitoring","date":"2024-12-20","arxiv_id":"2412.16108","n_code_links":0,"syntology":null},{"paper":"/paper/don-t-do-rag-when-cache-augmented-generation","slug":"don-t-do-rag-when-cache-augmented-generation","title":"Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks","date":"2024-12-20","arxiv_id":"2412.15605","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["hhhuang/cag"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"explainable-ai-for-multivariate-time-series","title":"Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics with Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis","date":"2024-12-20","arxiv_id":"2412.16098","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-readable-adversarial-prompts-an","title":"Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context","date":"2024-12-20","arxiv_id":"2412.16359","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanlike-cognitive-patterns-as-emergent","title":"Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models","date":"2024-12-20","arxiv_id":"2412.15501","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybgrag-hybrid-retrieval-augmented-generation","title":"HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases","date":"2024-12-20","arxiv_id":"2412.16311","n_code_links":0,"syntology":null},{"paper":"/paper/linguistic-features-extracted-by-gpt-4","slug":"linguistic-features-extracted-by-gpt-4","title":"Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech","date":"2024-12-20","arxiv_id":"2412.15772","n_code_links":1,"syntology":null},{"paper":"/paper/multi-dimensional-visual-prompt-enhanced","slug":"multi-dimensional-visual-prompt-enhanced","title":"Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer Aggregation","date":"2024-12-20","arxiv_id":"2412.15845","n_code_links":1,"syntology":null},{"paper":null,"slug":"promptoptme-error-aware-prompt-compression","title":"PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics","date":"2024-12-20","arxiv_id":"2412.16120","n_code_links":0,"syntology":null},{"paper":null,"slug":"seagrassfinder-deep-learning-for-eelgrass","title":"SeagrassFinder: Deep Learning for Eelgrass Detection and Coverage Estimation in the Wild","date":"2024-12-20","arxiv_id":"2412.16147","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-first-multilingual-model-for-the","title":"The First Multilingual Model For The Detection of Suicide Texts","date":"2024-12-20","arxiv_id":"2412.15498","n_code_links":0,"syntology":null},{"paper":"/paper/towards-interpretable-radiology-report","slug":"towards-interpretable-radiology-report","title":"Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG","date":"2024-12-20","arxiv_id":"2412.16086","n_code_links":1,"syntology":null},{"paper":"/paper/xrag-examining-the-core-benchmarking","slug":"xrag-examining-the-core-benchmarking","title":"XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation","date":"2024-12-20","arxiv_id":"2412.15529","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["docailab/xrag"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"a-full-transformer-based-framework-for","title":"A Full Transformer-based Framework for Automatic Pain Estimation using Videos","date":"2024-12-19","arxiv_id":"2412.15095","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-rwkv","slug":"a-survey-of-rwkv","title":"A Survey of RWKV","date":"2024-12-19","arxiv_id":"2412.14847","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-prompt-tuning-vision-guided-prompt","title":"Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning","date":"2024-12-19","arxiv_id":"2412.14640","n_code_links":0,"syntology":null},{"paper":null,"slug":"analysis-and-visualization-of-linguistic","title":"Analysis and Visualization of Linguistic Structures in Large Language Models: Neural Representations of Verb-Particle Constructions in BERT","date":"2024-12-19","arxiv_id":"2412.14670","n_code_links":0,"syntology":null},{"paper":"/paper/associative-memory-inspires-improvements-for","slug":"associative-memory-inspires-improvements-for","title":"Associative memory inspires improvements for in-context learning using a novel attention residual stream architecture","date":"2024-12-19","arxiv_id":"2412.15113","n_code_links":1,"syntology":null},{"paper":"/paper/can-we-get-rid-of-handcrafted-feature","slug":"can-we-get-rid-of-handcrafted-feature","title":"Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer","date":"2024-12-19","arxiv_id":"2412.14598","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":["scu-zjz/sparsevit"],"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":"cord-balancing-consistency-and-rank","title":"CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation","date":"2024-12-19","arxiv_id":"2412.14581","n_code_links":0,"syntology":null},{"paper":null,"slug":"decade-of-natural-language-processing-in","title":"Decade of Natural Language Processing in Chronic Pain: A Systematic Review","date":"2024-12-19","arxiv_id":"2412.15360","n_code_links":0,"syntology":null},{"paper":null,"slug":"dehallucinating-parallel-context-extension","title":"Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation","date":"2024-12-19","arxiv_id":"2412.14905","n_code_links":0,"syntology":null},{"paper":"/paper/diffsim-taming-diffusion-models-for","slug":"diffsim-taming-diffusion-models-for","title":"DiffSim: Taming Diffusion Models for Evaluating Visual Similarity","date":"2024-12-19","arxiv_id":"2412.14580","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamickv-task-aware-adaptive-kv-cache","title":"DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs","date":"2024-12-19","arxiv_id":"2412.14838","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-masked-time-series-modeling-via","slug":"enhancing-masked-time-series-modeling-via","title":"Enhancing Masked Time-Series Modeling via Dropping Patches","date":"2024-12-19","arxiv_id":"2412.15315","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-convolutional-networks-named-entity","title":"Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering","date":"2024-12-19","arxiv_id":"2412.14867","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-good-is-gpt-at-writing-political-speeches","title":"How good is GPT at writing political speeches for the White House?","date":"2024-12-19","arxiv_id":"2412.14617","n_code_links":0,"syntology":null},{"paper":null,"slug":"jet-a-modern-transformer-based-normalizing","title":"Jet: A Modern Transformer-Based Normalizing Flow","date":"2024-12-19","arxiv_id":"2412.15129","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-models-for-handling-non-ignorable","title":"Joint Models for Handling Non-Ignorable Missing Data using Bayesian Additive Regression Trees: Application to Leaf Photosynthetic Traits Data","date":"2024-12-19","arxiv_id":"2412.14946","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-injection-via-prompt-distillation","title":"Knowledge Injection via Prompt Distillation","date":"2024-12-19","arxiv_id":"2412.14964","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-as-mediators-can-they-diagnose-conflicts","title":"LLMs as mediators: Can they diagnose conflicts accurately?","date":"2024-12-19","arxiv_id":"2412.14675","n_code_links":0,"syntology":null},{"paper":null,"slug":"mention-attention-for-pronoun-translation","title":"Mention Attention for Pronoun Translation","date":"2024-12-19","arxiv_id":"2412.14829","n_code_links":0,"syntology":null},{"paper":"/paper/miett-multi-instance-encrypted-traffic","slug":"miett-multi-instance-encrypted-traffic","title":"MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification","date":"2024-12-19","arxiv_id":"2412.15306","n_code_links":1,"syntology":null},{"paper":"/paper/msa-gcn-exploiting-multi-scale-temporal","slug":"msa-gcn-exploiting-multi-scale-temporal","title":"MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition","date":"2024-12-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/pa-rag-rag-alignment-via-multi-perspective","slug":"pa-rag-rag-alignment-via-multi-perspective","title":"PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization","date":"2024-12-19","arxiv_id":"2412.14510","n_code_links":1,"syntology":null},{"paper":null,"slug":"qua-2-sedimo-quantifiable-quantization","title":"Qua$^2$SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models","date":"2024-12-19","arxiv_id":"2412.14628","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-pipeline-optimization-for-cancer","title":"Query pipeline optimization for cancer patient question answering systems","date":"2024-12-19","arxiv_id":"2412.14751","n_code_links":0,"syntology":null},{"paper":null,"slug":"relational-programming-with-foundation-models","title":"Relational Programming with Foundation Models","date":"2024-12-19","arxiv_id":"2412.14515","n_code_links":0,"syntology":null}],"record_sha256":"8b1cf3f1d3abcb935e84460f51b777ea5230f3003b3f1770c1b13739cb3a6d90","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}