{"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/31","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":31,"pages_in_order":249,"rows_per_page":100,"rows":[3001,3100],"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/30","next":"/method/multi-head-attention/papers/32","papers":[{"paper":null,"slug":"zerokey-point-level-reasoning-and-zero-shot","title":"ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models","date":"2024-12-09","arxiv_id":"2412.06292","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-collaborative-multi-agent-approach-to","title":"A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data","date":"2024-12-08","arxiv_id":"2412.05838","n_code_links":0,"syntology":null},{"paper":"/paper/are-clinical-t5-models-better-for-clinical","slug":"are-clinical-t5-models-better-for-clinical","title":"Are Clinical T5 Models Better for Clinical Text?","date":"2024-12-08","arxiv_id":"2412.05845","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-computationally-efficient-long-lora","title":"Enhanced Computationally Efficient Long LoRA Inspired Perceiver Architectures for Auto-Regressive Language Modeling","date":"2024-12-08","arxiv_id":"2412.06106","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-content-representation-for-ar-image","title":"Enhancing Content Representation for AR Image Quality Assessment Using Knowledge Distillation","date":"2024-12-08","arxiv_id":"2412.06003","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-robustness-of-llms-on-crisis","title":"Evaluating Robustness of LLMs on Crisis-Related Microblogs across Events, Information Types, and Linguistic Features","date":"2024-12-08","arxiv_id":"2412.10413","n_code_links":0,"syntology":null},{"paper":"/paper/fully-open-source-moxin-7b-technical-report","slug":"fully-open-source-moxin-7b-technical-report","title":"Fully Open Source Moxin-7B Technical Report","date":"2024-12-08","arxiv_id":"2412.06845","n_code_links":1,"syntology":null},{"paper":null,"slug":"kite-ddi-a-knowledge-graph-integrated","title":"KITE-DDI: A Knowledge graph Integrated Transformer Model for accurately predicting Drug-Drug Interaction Events from Drug SMILES and Biomedical Knowledge Graph","date":"2024-12-08","arxiv_id":"2412.05770","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-guided-image-tokenization-for","title":"Language-Guided Image Tokenization for Generation","date":"2024-12-08","arxiv_id":"2412.05796","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-correction-explainable-feedback","slug":"learning-to-correction-explainable-feedback","title":"Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor","date":"2024-12-08","arxiv_id":"2412.07801","n_code_links":1,"syntology":null},{"paper":"/paper/m-3-20m-a-large-scale-multi-modal-molecule","slug":"m-3-20m-a-large-scale-multi-modal-molecule","title":"M$^{3}$-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery","date":"2024-12-08","arxiv_id":"2412.06847","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixture-of-pageranks-replacing-long-context","title":"Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAG","date":"2024-12-08","arxiv_id":"2412.06078","n_code_links":0,"syntology":null},{"paper":null,"slug":"paddy-disease-detection-and-classification","title":"Paddy Disease Detection and Classification Using Computer Vision Techniques: A Mobile Application to Detect Paddy Disease","date":"2024-12-08","arxiv_id":"2412.05996","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-based-semantic","title":"Vision Transformer-based Semantic Communications With Importance-Aware Quantization","date":"2024-12-08","arxiv_id":"2412.06038","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-code-generation-with","title":"A Comparative Study on Code Generation with Transformers","date":"2024-12-07","arxiv_id":"2412.05749","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertcaps-bert-capsule-for-persian-multi","title":"BERTCaps: BERT Capsule for Persian Multi-Domain Sentiment Analysis","date":"2024-12-07","arxiv_id":"2412.05591","n_code_links":0,"syntology":null},{"paper":"/paper/characterbox-evaluating-the-role-playing","slug":"characterbox-evaluating-the-role-playing","title":"CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds","date":"2024-12-07","arxiv_id":"2412.05631","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["paitesanshi/characterbox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-use-of-llms-for-sql-equivalence","title":"Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking","date":"2024-12-07","arxiv_id":"2412.05561","n_code_links":0,"syntology":null},{"paper":null,"slug":"innovative-sentiment-analysis-and-prediction","title":"Innovative Sentiment Analysis and Prediction of Stock Price Using FinBERT, GPT-4 and Logistic Regression: A Data-Driven Approach","date":"2024-12-07","arxiv_id":"2412.06837","n_code_links":0,"syntology":null},{"paper":"/paper/kg-retriever-efficient-knowledge-indexing-for","slug":"kg-retriever-efficient-knowledge-indexing-for","title":"KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models","date":"2024-12-07","arxiv_id":"2412.05547","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["bai-lab/kg-retriever"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/m-3-pc-test-time-model-predictive-control-for","slug":"m-3-pc-test-time-model-predictive-control-for","title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","date":"2024-12-07","arxiv_id":"2412.05675","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 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["wkh923/m3pc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/privagent-agentic-based-red-teaming-for-llm","slug":"privagent-agentic-based-red-teaming-for-llm","title":"PrivAgent: Agentic-based Red-teaming for LLM Privacy Leakage","date":"2024-12-07","arxiv_id":"2412.05734","n_code_links":1,"syntology":null},{"paper":null,"slug":"refsam3d-adapting-sam-with-cross-modal","title":"RefSAM3D: Adapting SAM with Cross-modal Reference for 3D Medical Image Segmentation","date":"2024-12-07","arxiv_id":"2412.05605","n_code_links":0,"syntology":null},{"paper":null,"slug":"shifting-ner-into-high-gear-the-auto-adver","title":"Shifting NER into High Gear: The Auto-AdvER Approach","date":"2024-12-07","arxiv_id":"2412.05655","n_code_links":0,"syntology":null},{"paper":null,"slug":"sla-management-in-reconfigurable-multi-agent","title":"SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering","date":"2024-12-07","arxiv_id":"2412.06832","n_code_links":0,"syntology":null},{"paper":"/paper/stonet-a-novel-neural-operator-for-modeling","slug":"stonet-a-novel-neural-operator-for-modeling","title":"STONet: A novel neural operator for modeling solute transport in micro-cracked reservoirs","date":"2024-12-07","arxiv_id":"2412.05576","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-3d-acceleration-for-low-power-mixture","title":"Towards 3D Acceleration for low-power Mixture-of-Experts and Multi-Head Attention Spiking Transformers","date":"2024-12-07","arxiv_id":"2412.05540","n_code_links":0,"syntology":null},{"paper":"/paper/towards-learning-to-reason-comparing-llms","slug":"towards-learning-to-reason-comparing-llms","title":"Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning","date":"2024-12-07","arxiv_id":"2412.05586","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ibm/raven-large-language-models"],"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","unlocated"]}}},{"paper":null,"slug":"100-hallucination-elimination-using-acurai","title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","date":"2024-12-06","arxiv_id":"2412.05223","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-based-approach-for-conversational-ai","title":"TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG","date":"2024-12-06","arxiv_id":"2412.05447","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-frontier-large-language-models-suitable","title":"Are Frontier Large Language Models Suitable for Q&A in Science Centres?","date":"2024-12-06","arxiv_id":"2412.05200","n_code_links":0,"syntology":null},{"paper":null,"slug":"beexformer-a-fast-inferencing-transformer","title":"BEExformer: A Fast Inferencing Transformer Architecture via Binarization with Multiple Early Exits","date":"2024-12-06","arxiv_id":"2412.05225","n_code_links":0,"syntology":null},{"paper":null,"slug":"dhil-gt-scalable-graph-transformer-with","title":"DHIL-GT: Scalable Graph Transformer with Decoupled Hierarchy Labeling","date":"2024-12-06","arxiv_id":"2412.04738","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-cross-language-code-translation-via","title":"Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation","date":"2024-12-06","arxiv_id":"2412.05159","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llms-for-impression-generation-in","title":"Enhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent System","date":"2024-12-06","arxiv_id":"2412.06828","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-group-tabular-transformer-a-novel","title":"Feature Group Tabular Transformer: A Novel Approach to Traffic Crash Modeling and Causality Analysis","date":"2024-12-06","arxiv_id":"2412.06825","n_code_links":0,"syntology":null},{"paper":null,"slug":"iternorm-fast-iterative-normalization","title":"IterL2Norm: Fast Iterative L2-Normalization","date":"2024-12-06","arxiv_id":"2412.04778","n_code_links":0,"syntology":null},{"paper":"/paper/nlp-adbench-nlp-anomaly-detection-benchmark","slug":"nlp-adbench-nlp-anomaly-detection-benchmark","title":"NLP-ADBench: NLP Anomaly Detection Benchmark","date":"2024-12-06","arxiv_id":"2412.04784","n_code_links":1,"syntology":null},{"paper":null,"slug":"pctrees-3d-point-cloud-tree-species","title":"PCTreeS: 3D Point Cloud Tree Species Classification Using Airborne LiDAR Images","date":"2024-12-06","arxiv_id":"2412.04714","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-preserving-retrieval-augmented","title":"Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy","date":"2024-12-06","arxiv_id":"2412.04697","n_code_links":0,"syntology":null},{"paper":null,"slug":"queen-a-large-language-model-for-quechua","title":"QueEn: A Large Language Model for Quechua-English Translation","date":"2024-12-06","arxiv_id":"2412.05184","n_code_links":0,"syntology":null},{"paper":"/paper/superpixel-tokenization-for-vision","slug":"superpixel-tokenization-for-vision","title":"Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens","date":"2024-12-06","arxiv_id":"2412.04680","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jangsoohyuk/SuiT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"addressing-hallucinations-with-rag-and-nmiss","title":"Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots","date":"2024-12-05","arxiv_id":"2412.04235","n_code_links":0,"syntology":null},{"paper":null,"slug":"artefact-benchmarking-segmentation-models-on","title":"ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage","date":"2024-12-05","arxiv_id":"2412.04580","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-latex-code-generation-from","title":"Automated LaTeX Code Generation from Handwritten Math Expressions Using Vision Transformer","date":"2024-12-05","arxiv_id":"2412.03853","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-audio-query-handling-system","title":"Comprehensive Audio Query Handling System with Integrated Expert Models and Contextual Understanding","date":"2024-12-05","arxiv_id":"2412.03980","n_code_links":0,"syntology":null},{"paper":"/paper/cubify-anything-scaling-indoor-3d-object","slug":"cubify-anything-scaling-indoor-3d-object","title":"Cubify Anything: Scaling Indoor 3D Object Detection","date":"2024-12-05","arxiv_id":"2412.04458","n_code_links":1,"syntology":null},{"paper":"/paper/deim-detr-with-improved-matching-for-fast","slug":"deim-detr-with-improved-matching-for-fast","title":"DEIM: DETR with Improved Matching for Fast Convergence","date":"2024-12-05","arxiv_id":"2412.04234","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shihuahuang95/deim"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamic-graph-representation-with-contrastive","slug":"dynamic-graph-representation-with-contrastive","title":"Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations","date":"2024-12-05","arxiv_id":"2412.04034","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-ai-text-generation-retrieval","title":"Exploring AI Text Generation, Retrieval-Augmented Generation, and Detection Technologies: a Comprehensive Overview","date":"2024-12-05","arxiv_id":"2412.03933","n_code_links":0,"syntology":null},{"paper":"/paper/florence-vl-enhancing-vision-language-models","slug":"florence-vl-enhancing-vision-language-models","title":"Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion","date":"2024-12-05","arxiv_id":"2412.04424","n_code_links":1,"syntology":null},{"paper":"/paper/heal-hierarchical-embedding-alignment-loss","slug":"heal-hierarchical-embedding-alignment-loss","title":"HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning","date":"2024-12-05","arxiv_id":"2412.04661","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-good-is-chatgpt-in-giving-adaptive","title":"How Good is ChatGPT in Giving Adaptive Guidance Using Knowledge Graphs in E-Learning Environments?","date":"2024-12-05","arxiv_id":"2412.03856","n_code_links":0,"syntology":null},{"paper":"/paper/transadapter-vision-transformer-for-feature","slug":"transadapter-vision-transformer-for-feature","title":"TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation","date":"2024-12-05","arxiv_id":"2412.04073","n_code_links":1,"syntology":null},{"paper":null,"slug":"uniform-discretized-integrated-gradients-an","title":"Uniform Discretized Integrated Gradients: An effective attribution based method for explaining large language models","date":"2024-12-05","arxiv_id":"2412.03886","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-water-efficiency-dataset-for-african-data","title":"A Water Efficiency Dataset for African Data Centers","date":"2024-12-04","arxiv_id":"2412.03716","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-risk-prediction-and-stability","title":"Advanced Risk Prediction and Stability Assessment of Banks Using Time Series Transformer Models","date":"2024-12-04","arxiv_id":"2412.03606","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-conversational-psychotherapy","title":"Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Models","date":"2024-12-04","arxiv_id":"2412.02987","n_code_links":0,"syntology":null},{"paper":null,"slug":"antlm-bridging-causal-and-masked-language","title":"AntLM: Bridging Causal and Masked Language Models","date":"2024-12-04","arxiv_id":"2412.03275","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-the-mutation-in-large-language","title":"Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms","date":"2024-12-04","arxiv_id":"2412.03250","n_code_links":0,"syntology":null},{"paper":null,"slug":"dive-taming-dino-for-subject-driven-video","title":"DIVE: Taming DINO for Subject-Driven Video Editing","date":"2024-12-04","arxiv_id":"2412.03347","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-safety-training-of-llms-generalize-to","title":"Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?","date":"2024-12-04","arxiv_id":"2412.03235","n_code_links":0,"syntology":null},{"paper":"/paper/empath-mediapipe-aided-ensemble-learning-with","slug":"empath-mediapipe-aided-ensemble-learning-with","title":"EMPATH: MediaPipe-Aided Ensemble Learning with Attention-Based Transformers for Accurate Recognition of Bangla Word-Level Sign Language","date":"2024-12-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fanal-financial-activity-news-alerting","title":"FANAL -- Financial Activity News Alerting Language Modeling Framework","date":"2024-12-04","arxiv_id":"2412.03527","n_code_links":0,"syntology":null},{"paper":"/paper/grapix-exploring-graph-modularity","slug":"grapix-exploring-graph-modularity","title":"GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel Clustering","date":"2024-12-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/interpreting-transformers-for-jet-tagging","slug":"interpreting-transformers-for-jet-tagging","title":"Interpreting Transformers for Jet Tagging","date":"2024-12-04","arxiv_id":"2412.03673","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["aaronw5/Interpreting-Transformers-for-Jet-Tagging"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"materialpicker-multi-modal-material","title":"MaterialPicker: Multi-Modal Material Generation with Diffusion Transformers","date":"2024-12-04","arxiv_id":"2412.03225","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-branch-mutual-distillation-transformer","title":"Multi-Branch Mutual-Distillation Transformer for EEG-Based Seizure Subtype Classification","date":"2024-12-04","arxiv_id":"2412.15224","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-sentiment-analysis-based-on-bert","title":"Multimodal Sentiment Analysis Based on BERT and ResNet","date":"2024-12-04","arxiv_id":"2412.03625","n_code_links":0,"syntology":null},{"paper":"/paper/navigation-world-models","slug":"navigation-world-models","title":"Navigation World Models","date":"2024-12-04","arxiv_id":"2412.03572","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"seeing-beyond-views-multi-view-driving-scene","title":"Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention","date":"2024-12-04","arxiv_id":"2412.03520","n_code_links":0,"syntology":null},{"paper":"/paper/theoretical-limitations-of-multi-layer","slug":"theoretical-limitations-of-multi-layer","title":"Theoretical limitations of multi-layer Transformer","date":"2024-12-04","arxiv_id":"2412.02975","n_code_links":1,"syntology":null},{"paper":null,"slug":"achieving-semantic-consistency-using-bert","title":"Achieving Semantic Consistency: Contextualized Word Representations for Political Text Analysis","date":"2024-12-03","arxiv_id":"2412.04505","n_code_links":0,"syntology":null},{"paper":null,"slug":"caisson-concept-augmented-inference-suite-of","title":"CAISSON: Concept-Augmented Inference Suite of Self-Organizing Neural Networks","date":"2024-12-03","arxiv_id":"2412.02835","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-kv-cache-for-long-context-llm","title":"Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity","date":"2024-12-03","arxiv_id":"2412.02252","n_code_links":0,"syntology":null},{"paper":null,"slug":"cptquant-a-novel-mixed-precision-post","title":"CPTQuant -- A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models","date":"2024-12-03","arxiv_id":"2412.03599","n_code_links":0,"syntology":null},{"paper":"/paper/dp-2stage-adapting-language-models-as","slug":"dp-2stage-adapting-language-models-as","title":"DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators","date":"2024-12-03","arxiv_id":"2412.02467","n_code_links":1,"syntology":null},{"paper":null,"slug":"fcl-vit-task-aware-attention-tuning-for","title":"FCL-ViT: Task-Aware Attention Tuning for Continual Learning","date":"2024-12-03","arxiv_id":"2412.02509","n_code_links":0,"syntology":null},{"paper":null,"slug":"flattering-to-deceive-the-impact-of","title":"Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model","date":"2024-12-03","arxiv_id":"2412.02802","n_code_links":0,"syntology":null},{"paper":null,"slug":"gqwformer-a-quantum-based-transformer-for","title":"GQWformer: A Quantum-based Transformer for Graph Representation Learning","date":"2024-12-03","arxiv_id":"2412.02285","n_code_links":0,"syntology":null},{"paper":"/paper/gracefully-filtering-backdoor-samples-for","slug":"gracefully-filtering-backdoor-samples-for","title":"Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining","date":"2024-12-03","arxiv_id":"2412.02454","n_code_links":1,"syntology":null},{"paper":null,"slug":"impact-of-data-snooping-on-deep-learning","title":"Impact of Data Snooping on Deep Learning Models for Locating Vulnerabilities in Lifted Code","date":"2024-12-03","arxiv_id":"2412.02048","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-20","title":"Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms","date":"2024-12-03","arxiv_id":"2412.02149","n_code_links":0,"syntology":null},{"paper":"/paper/magma-manifold-regularization-for-maes","slug":"magma-manifold-regularization-for-maes","title":"MAGMA: Manifold Regularization for MAEs","date":"2024-12-03","arxiv_id":"2412.02871","n_code_links":1,"syntology":null},{"paper":null,"slug":"metashadow-object-centered-shadow-detection","title":"MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis","date":"2024-12-03","arxiv_id":"2412.02635","n_code_links":0,"syntology":null},{"paper":"/paper/ocr-hinders-rag-evaluating-the-cascading","slug":"ocr-hinders-rag-evaluating-the-cascading","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","date":"2024-12-03","arxiv_id":"2412.02592","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimization-of-transformer-heart-disease","title":"Optimization of Transformer heart disease prediction model based on particle swarm optimization algorithm","date":"2024-12-03","arxiv_id":"2412.02801","n_code_links":0,"syntology":null},{"paper":null,"slug":"patent-cr-a-dataset-for-patent-claim-revision","title":"Patent-CR: A Dataset for Patent Claim Revision","date":"2024-12-03","arxiv_id":"2412.02549","n_code_links":0,"syntology":null},{"paper":"/paper/rare-retrieval-augmented-reasoning","slug":"rare-retrieval-augmented-reasoning","title":"RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models","date":"2024-12-03","arxiv_id":"2412.02830","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-the-initial-steps-in-adaptive","title":"Revisiting the Initial Steps in Adaptive Gradient Descent Optimization","date":"2024-12-03","arxiv_id":"2412.02153","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-bert-models-for-turkish-automatic","title":"Scaling BERT Models for Turkish Automatic Punctuation and Capitalization Correction","date":"2024-12-03","arxiv_id":"2412.02698","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-tokens-in-retrieval-augmented","title":"Semantic Tokens in Retrieval Augmented Generation","date":"2024-12-03","arxiv_id":"2412.02563","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-asymptotic-behavior-of-attention-in","title":"The Asymptotic Behavior of Attention in Transformers","date":"2024-12-03","arxiv_id":"2412.02682","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-metric-loss-for-cnn-based-face","slug":"transformer-metric-loss-for-cnn-based-face","title":"Transformer-Based Auxiliary Loss for Face Recognition Across Age Variations","date":"2024-12-03","arxiv_id":"2412.02198","n_code_links":0,"syntology":null},{"paper":null,"slug":"uniform-a-reuse-attention-mechanism-optimized","title":"UniForm: A Reuse Attention Mechanism Optimized for Efficient Vision Transformers on Edge Devices","date":"2024-12-03","arxiv_id":"2412.02344","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-extraction-of-acronym-expansion","title":"Automated Extraction of Acronym-Expansion Pairs from Scientific Papers","date":"2024-12-02","arxiv_id":"2412.01093","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-toll-management-system-using-rfid","title":"Automated Toll Management System Using RFID and Image Processing","date":"2024-12-02","arxiv_id":"2412.01728","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-transformer-neural","title":"Convolutional Transformer Neural Collaborative Filtering","date":"2024-12-02","arxiv_id":"2412.01376","n_code_links":0,"syntology":null},{"paper":null,"slug":"cpa-camera-pose-awareness-diffusion","title":"CPA: Camera-pose-awareness Diffusion Transformer for Video Generation","date":"2024-12-02","arxiv_id":"2412.01429","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-crop-segmentation-in-satellite-1","title":"Enhancing Crop Segmentation in Satellite Image Time Series with Transformer Networks","date":"2024-12-02","arxiv_id":"2412.01944","n_code_links":0,"syntology":null}],"record_sha256":"8a9787fc53c2c6ce4501b3302917f22c04691af16703e997afbba81382c04ff5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}