{"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/36","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":36,"pages_in_order":249,"rows_per_page":100,"rows":[3501,3600],"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/35","next":"/method/multi-head-attention/papers/37","papers":[{"paper":"/paper/learning-the-rules-of-peptide-self-assembly","slug":"learning-the-rules-of-peptide-self-assembly","title":"Learning the rules of peptide self-assembly through data mining with large language models","date":"2024-11-08","arxiv_id":"2411.05421","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-document-financial-question-answering","title":"Multi-Document Financial Question Answering using LLMs","date":"2024-11-08","arxiv_id":"2411.07264","n_code_links":0,"syntology":null},{"paper":null,"slug":"neko-toward-post-recognition-generative","title":"NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts","date":"2024-11-08","arxiv_id":"2411.05945","n_code_links":0,"syntology":null},{"paper":"/paper/online-lora-task-free-online-continual","slug":"online-lora-task-free-online-continual","title":"Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation","date":"2024-11-08","arxiv_id":"2411.05663","n_code_links":1,"syntology":null},{"paper":null,"slug":"qwen2-5-32b-leveraging-self-consistent-tool","title":"Qwen2.5-32B: Leveraging Self-Consistent Tool-Integrated Reasoning for Bengali Mathematical Olympiad Problem Solving","date":"2024-11-08","arxiv_id":"2411.05934","n_code_links":0,"syntology":null},{"paper":null,"slug":"saswise-ue-segmentation-and-synthesis-with","title":"SASWISE-UE: Segmentation and Synthesis with Interpretable Scalable Ensembles for Uncertainty Estimation","date":"2024-11-08","arxiv_id":"2411.05324","n_code_links":0,"syntology":null},{"paper":"/paper/sentiment-analysis-of-cyberbullying-data-in","slug":"sentiment-analysis-of-cyberbullying-data-in","title":"Sentiment Analysis of Cyberbullying Data in Social Media","date":"2024-11-08","arxiv_id":"2411.05958","n_code_links":1,"syntology":null},{"paper":null,"slug":"smile-upon-the-face-but-sadness-in-the-eyes","title":"Smile upon the Face but Sadness in the Eyes: Emotion Recognition based on Facial Expressions and Eye Behaviors","date":"2024-11-08","arxiv_id":"2411.05879","n_code_links":0,"syntology":null},{"paper":"/paper/tell-what-you-hear-from-what-you-see-video-to","slug":"tell-what-you-hear-from-what-you-see-video-to","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","date":"2024-11-08","arxiv_id":"2411.05679","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["DragonLiu1995/multimodal-llm-for-audio-gen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/using-language-models-to-disambiguate-lexical","slug":"using-language-models-to-disambiguate-lexical","title":"Using Language Models to Disambiguate Lexical Choices in Translation","date":"2024-11-08","arxiv_id":"2411.05781","n_code_links":1,"syntology":null},{"paper":null,"slug":"vit-enhanced-privacy-preserving-secure","title":"ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification","date":"2024-11-08","arxiv_id":"2411.05901","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-robustness-of-in-context-learning","title":"Adversarial Robustness of In-Context Learning in Transformers for Linear Regression","date":"2024-11-07","arxiv_id":"2411.05189","n_code_links":0,"syntology":null},{"paper":null,"slug":"best-practices-for-distilling-large-language","title":"Best Practices for Distilling Large Language Models into BERT for Web Search Ranking","date":"2024-11-07","arxiv_id":"2411.04539","n_code_links":0,"syntology":null},{"paper":null,"slug":"dancefusion-a-spatio-temporal-skeleton","title":"DanceFusion: A Spatio-Temporal Skeleton Diffusion Transformer for Audio-Driven Dance Motion Reconstruction","date":"2024-11-07","arxiv_id":"2411.04646","n_code_links":0,"syntology":null},{"paper":"/paper/deploying-large-language-models-with","slug":"deploying-large-language-models-with","title":"Deploying Large Language Models With Retrieval Augmented Generation","date":"2024-11-07","arxiv_id":"2411.11895","n_code_links":1,"syntology":null},{"paper":null,"slug":"dino-wm-world-models-on-pre-trained-visual","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","date":"2024-11-07","arxiv_id":"2411.04983","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-classroom-teaching-with-llms-and","title":"Enhancing classroom teaching with LLMs and RAG","date":"2024-11-07","arxiv_id":"2411.04341","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-low-light-images-with-kolmogorov","slug":"enhancing-low-light-images-with-kolmogorov","title":"Enhancing Low-Light Images with Kolmogorov–Arnold Networks in Transformer Attention","date":"2024-11-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"esc-misr-enhancing-spatial-correlations-for","title":"ESC-MISR: Enhancing Spatial Correlations for Multi-Image Super-Resolution in Remote Sensing","date":"2024-11-07","arxiv_id":"2411.04706","n_code_links":0,"syntology":null},{"paper":"/paper/finetunebench-how-well-do-commercial-fine","slug":"finetunebench-how-well-do-commercial-fine","title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","date":"2024-11-07","arxiv_id":"2411.05059","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-guided-monte-carlo-tree-search-for","title":"GPT-Guided Monte Carlo Tree Search for Symbolic Regression in Financial Fraud Detection","date":"2024-11-07","arxiv_id":"2411.04459","n_code_links":0,"syntology":null},{"paper":"/paper/hourvideo-1-hour-video-language-understanding","slug":"hourvideo-1-hour-video-language-understanding","title":"HourVideo: 1-Hour Video-Language Understanding","date":"2024-11-07","arxiv_id":"2411.04998","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":13,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["keshik6/HourVideo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/llm2clip-powerful-language-model-unlock","slug":"llm2clip-powerful-language-model-unlock","title":"LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation","date":"2024-11-07","arxiv_id":"2411.04997","n_code_links":1,"syntology":null},{"paper":null,"slug":"m3docrag-multi-modal-retrieval-is-what-you","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","date":"2024-11-07","arxiv_id":"2411.04952","n_code_links":0,"syntology":null},{"paper":null,"slug":"measure-to-measure-interpolation-using","title":"Measure-to-measure interpolation using Transformers","date":"2024-11-07","arxiv_id":"2411.04551","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-short-form-factuality-in-large","slug":"measuring-short-form-factuality-in-large","title":"Measuring short-form factuality in large language models","date":"2024-11-07","arxiv_id":"2411.04368","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-temporal-crack-segmentation-in-concrete","title":"Multi-temporal crack segmentation in concrete structure using deep learning approaches","date":"2024-11-07","arxiv_id":"2411.04620","n_code_links":0,"syntology":null},{"paper":null,"slug":"pose2trajectory-using-transformers-on-body","title":"Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory","date":"2024-11-07","arxiv_id":"2411.04501","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrievegpt-merging-prompts-and-mathematical","title":"RetrieveGPT: Merging Prompts and Mathematical Models for Enhanced Code-Mixed Information Retrieval","date":"2024-11-07","arxiv_id":"2411.04752","n_code_links":0,"syntology":null},{"paper":null,"slug":"selecting-between-bert-and-gpt-for-text","title":"Selecting Between BERT and GPT for Text Classification in Political Science Research","date":"2024-11-07","arxiv_id":"2411.05050","n_code_links":0,"syntology":null},{"paper":null,"slug":"stand-guard-a-small-task-adaptive-content","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","date":"2024-11-07","arxiv_id":"2411.05214","n_code_links":0,"syntology":null},{"paper":null,"slug":"words-that-move-markets-quantifying-the","title":"Words that Move Markets- Quantifying the Impact of RBI's Monetary Policy Communications on Indian Financial Market","date":"2024-11-07","arxiv_id":"2411.04808","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-recent-large-language","title":"A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients","date":"2024-11-06","arxiv_id":"2411.03805","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-contrastive-self-supervised-learning-scheme","title":"A Contrastive Self-Supervised Learning scheme for beat tracking amenable to few-shot learning","date":"2024-11-06","arxiv_id":"2411.04152","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multilingual-sentiment-lexicon-for-low","title":"A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI","date":"2024-11-06","arxiv_id":"2411.04316","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-rag-models-with-graph-structures","title":"Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation","date":"2024-11-06","arxiv_id":"2411.03572","n_code_links":0,"syntology":null},{"paper":"/paper/bio-xlstm-generative-modeling-representation","slug":"bio-xlstm-generative-modeling-representation","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","date":"2024-11-06","arxiv_id":"2411.04165","n_code_links":3,"syntology":{"ran":27,"of":29,"n_ran_checked":25,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"27 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 0 honoured, 1 violated, 24 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ml-jku/chem-xlstm","ml-jku/dna-xlstm","ml-jku/prot-xlstm"],"state":"official (archive's flag): 27 ran","n_ran":27,"n_constructed":0,"n_ran_no_instrument_failure":25,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-custom-models-learn-in-context-an","slug":"can-custom-models-learn-in-context-an","title":"Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks","date":"2024-11-06","arxiv_id":"2411.03945","n_code_links":1,"syntology":null},{"paper":"/paper/customized-multiple-clustering-via-multi","slug":"customized-multiple-clustering-via-multi","title":"Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning","date":"2024-11-06","arxiv_id":"2411.03978","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":5,"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) · 2 unverified","official":{"repos":["alexander-yao/multi-sub"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"diversity-helps-jailbreak-large-language","title":"Diversity Helps Jailbreak Large Language Models","date":"2024-11-06","arxiv_id":"2411.04223","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-grained-guidance-for-retrievers","title":"Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation","date":"2024-11-06","arxiv_id":"2411.03957","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-medprompt-to-o1-exploration-of-run-time","title":"From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond","date":"2024-11-06","arxiv_id":"2411.03590","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-word-vectors-to-multimodal-embeddings","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","date":"2024-11-06","arxiv_id":"2411.05036","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-device-emoji-classifier-trained-with-gpt","title":"On-Device Emoji Classifier Trained with GPT-based Data Augmentation for a Mobile Keyboard","date":"2024-11-06","arxiv_id":"2411.05031","n_code_links":0,"syntology":null},{"paper":null,"slug":"phdgpt-introducing-a-psychometric-and","title":"PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology","date":"2024-11-06","arxiv_id":"2411.10473","n_code_links":0,"syntology":null},{"paper":"/paper/prion-vit-prions-inspired-vision-transformers","slug":"prion-vit-prions-inspired-vision-transformers","title":"Prion-ViT: Prions-Inspired Vision Transformers for Temperature prediction with Specklegrams","date":"2024-11-06","arxiv_id":"2411.05836","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-engineering-using-gpt-for-word-level","title":"Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages","date":"2024-11-06","arxiv_id":"2411.04025","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragulator-lightweight-out-of-context","title":"RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation","date":"2024-11-06","arxiv_id":"2411.03920","n_code_links":0,"syntology":null},{"paper":null,"slug":"reducing-catastrophic-forgetting-of","title":"Reducing catastrophic forgetting of incremental learning in the absence of rehearsal memory with task-specific token","date":"2024-11-06","arxiv_id":"2411.05846","n_code_links":0,"syntology":null},{"paper":"/paper/towards-interpreting-language-models-a-case","slug":"towards-interpreting-language-models-a-case","title":"Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning","date":"2024-11-06","arxiv_id":"2411.05037","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 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) · 1 unverified","official":{"repos":["msakarvadia/attentionlens"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-the-effects-of-human-written","slug":"understanding-the-effects-of-human-written","title":"Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection","date":"2024-11-06","arxiv_id":"2411.03806","n_code_links":1,"syntology":null},{"paper":null,"slug":"youtube-comments-decoded-leveraging-llms-for","title":"YouTube Comments Decoded: Leveraging LLMs for Low Resource Language Classification","date":"2024-11-06","arxiv_id":"2411.05039","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-convex-relaxation-approach-to","title":"A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networks","date":"2024-11-05","arxiv_id":"2411.02767","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mamba-foundation-model-for-time-series","title":"A Mamba Foundation Model for Time Series Forecasting","date":"2024-11-05","arxiv_id":"2411.02941","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-question-hints-for","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","date":"2024-11-05","arxiv_id":"2411.03495","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-feature-aggregation-and-scale-aware","slug":"efficient-feature-aggregation-and-scale-aware","title":"Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection","date":"2024-11-05","arxiv_id":"2411.02747","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-real-time-threat-detection-in-5g","title":"Enhanced Real-Time Threat Detection in 5G Networks: A Self-Attention RNN Autoencoder Approach for Spectral Intrusion Analysis","date":"2024-11-05","arxiv_id":"2411.03365","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-transformer-training-efficiency","title":"Enhancing Transformer Training Efficiency with Dynamic Dropout","date":"2024-11-05","arxiv_id":"2411.03236","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-benefits-of-domain-pretraining","title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","date":"2024-11-05","arxiv_id":"2411.03542","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-ai-model-for-medical-image","title":"Foundation AI Model for Medical Image Segmentation","date":"2024-11-05","arxiv_id":"2411.02745","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-pixels-to-prose-advancing-multi-modal","title":"From Pixels to Prose: Advancing Multi-Modal Language Models for Remote Sensing","date":"2024-11-05","arxiv_id":"2411.05826","n_code_links":0,"syntology":null},{"paper":"/paper/htmlrag-html-is-better-than-plain-text-for","slug":"htmlrag-html-is-better-than-plain-text-for","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","date":"2024-11-05","arxiv_id":"2411.02959","n_code_links":1,"syntology":null},{"paper":"/paper/kernel-approximation-using-analog-in-memory","slug":"kernel-approximation-using-analog-in-memory","title":"Kernel Approximation using Analog In-Memory Computing","date":"2024-11-05","arxiv_id":"2411.03375","n_code_links":1,"syntology":null},{"paper":null,"slug":"laser-attention-with-exponential","title":"LASER: Attention with Exponential Transformation","date":"2024-11-05","arxiv_id":"2411.03493","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-context-rag-performance-of-large","title":"Long Context RAG Performance of Large Language Models","date":"2024-11-05","arxiv_id":"2411.03538","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixtures-of-in-context-learners","title":"Mixtures of In-Context Learners","date":"2024-11-05","arxiv_id":"2411.02830","n_code_links":0,"syntology":null},{"paper":null,"slug":"neurons-for-neutrons-a-transformer-model-for","title":"Neurons for Neutrons: A Transformer Model for Computation Load Estimation on Domain-Decomposed Neutron Transport Problems","date":"2024-11-05","arxiv_id":"2411.03389","n_code_links":0,"syntology":null},{"paper":null,"slug":"p-moss-learned-scheduling-for-indexes-over","title":"P-MOSS: Learned Scheduling For Indexes Over NUMA Servers Using Low-Level Hardware Statistics","date":"2024-11-05","arxiv_id":"2411.02933","n_code_links":0,"syntology":null},{"paper":null,"slug":"persianrag-a-retrieval-augmented-generation","title":"PersianRAG: A Retrieval-Augmented Generation System for Persian Language","date":"2024-11-05","arxiv_id":"2411.02832","n_code_links":0,"syntology":null},{"paper":null,"slug":"predictor-corrector-enhanced-transformers","title":"Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning","date":"2024-11-05","arxiv_id":"2411.03042","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-decoders-for-transformer-based","slug":"rethinking-decoders-for-transformer-based","title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","date":"2024-11-05","arxiv_id":"2411.03033","n_code_links":1,"syntology":null},{"paper":null,"slug":"transunext-towards-a-more-advanced-u-shaped","title":"TransUNext: towards a more advanced U-shaped framework for automatic vessel segmentation in the fundus image","date":"2024-11-05","arxiv_id":"2411.02724","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-quantification-for-clinical","title":"Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models","date":"2024-11-05","arxiv_id":"2411.03497","n_code_links":0,"syntology":null},{"paper":null,"slug":"user-centric-semantic-communications","title":"Receiver-Centric Generative Semantic Communications","date":"2024-11-05","arxiv_id":"2411.03127","n_code_links":0,"syntology":null},{"paper":null,"slug":"veritas-a-unified-approach-to-reliability","title":"VERITAS: A Unified Approach to Reliability Evaluation","date":"2024-11-05","arxiv_id":"2411.03300","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-analysis-of-counterfactual","title":"A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers","date":"2024-11-04","arxiv_id":"2411.02643","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancements-and-limitations-of-llms-in","title":"Advancements and limitations of LLMs in replicating human color-word associations","date":"2024-11-04","arxiv_id":"2411.02116","n_code_links":0,"syntology":null},{"paper":"/paper/amortized-bayesian-experimental-design-for","slug":"amortized-bayesian-experimental-design-for","title":"Amortized Bayesian Experimental Design for Decision-Making","date":"2024-11-04","arxiv_id":"2411.02064","n_code_links":1,"syntology":null},{"paper":"/paper/ask-and-it-shall-be-given-turing-completeness","slug":"ask-and-it-shall-be-given-turing-completeness","title":"Ask, and it shall be given: On the Turing completeness of prompting","date":"2024-11-04","arxiv_id":"2411.01992","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-language-models-enable-in-context","title":"Can Language Models Enable In-Context Database?","date":"2024-11-04","arxiv_id":"2411.01807","n_code_links":0,"syntology":null},{"paper":null,"slug":"disrupting-test-development-with-ai","title":"Disrupting Test Development with AI Assistants","date":"2024-11-04","arxiv_id":"2411.02328","n_code_links":0,"syntology":null},{"paper":"/paper/elastst-towards-robust-varied-horizon","slug":"elastst-towards-robust-varied-horizon","title":"ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer","date":"2024-11-04","arxiv_id":"2411.01842","n_code_links":1,"syntology":{"ran":14,"of":14,"n_ran_checked":12,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"14 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/probts"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"encoding-multi-level-dynamics-in-effect","title":"Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs","date":"2024-11-04","arxiv_id":"2411.02134","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-risk-assessment-in-transformers","title":"Enhancing Risk Assessment in Transformers with Loss-at-Risk Functions","date":"2024-11-04","arxiv_id":"2411.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-ability-of-large-language-1","title":"Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFast","date":"2024-11-04","arxiv_id":"2411.02318","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-emotional-descriptions-to","title":"Grounding Emotional Descriptions to Electrovibration Haptic Signals","date":"2024-11-04","arxiv_id":"2411.02118","n_code_links":0,"syntology":null},{"paper":null,"slug":"mdeval-massively-multilingual-code-debugging","title":"MdEval: Massively Multilingual Code Debugging","date":"2024-11-04","arxiv_id":"2411.02310","n_code_links":0,"syntology":null},{"paper":"/paper/ragviz-diagnose-and-visualize-retrieval","slug":"ragviz-diagnose-and-visualize-retrieval","title":"RAGViz: Diagnose and Visualize Retrieval-Augmented Generation","date":"2024-11-04","arxiv_id":"2411.01751","n_code_links":1,"syntology":null},{"paper":"/paper/regress-don-t-guess-a-regression-like-loss-on","slug":"regress-don-t-guess-a-regression-like-loss-on","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","date":"2024-11-04","arxiv_id":"2411.02083","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 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["tum-ai/number-token-loss"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scalable-efficient-training-of-large-language","slug":"scalable-efficient-training-of-large-language","title":"Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention","date":"2024-11-04","arxiv_id":"2411.02063","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tsinghuac3i/lpa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/seq-vcr-preventing-collapse-in-intermediate","slug":"seq-vcr-preventing-collapse-in-intermediate","title":"Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning","date":"2024-11-04","arxiv_id":"2411.02344","n_code_links":1,"syntology":null},{"paper":"/paper/sira-scalable-inter-frame-relation-and-1","slug":"sira-scalable-inter-frame-relation-and-1","title":"SIRA: Scalable Inter-frame Relation and Association for Radar Perception","date":"2024-11-04","arxiv_id":"2411.02220","n_code_links":0,"syntology":null},{"paper":"/paper/teleoracle-fine-tuned-retrieval-augmented","slug":"teleoracle-fine-tuned-retrieval-augmented","title":"TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network","date":"2024-11-04","arxiv_id":"2411.02617","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-leveraging-news-media-to-support","title":"Towards Leveraging News Media to Support Impact Assessment of AI Technologies","date":"2024-11-04","arxiv_id":"2411.02536","n_code_links":0,"syntology":null},{"paper":"/paper/training-compute-optimal-protein-language","slug":"training-compute-optimal-protein-language","title":"Training Compute-Optimal Protein Language Models","date":"2024-11-04","arxiv_id":"2411.02142","n_code_links":1,"syntology":null},{"paper":"/paper/training-free-regional-prompting-for","slug":"training-free-regional-prompting-for","title":"Training-free Regional Prompting for Diffusion Transformers","date":"2024-11-04","arxiv_id":"2411.02395","n_code_links":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["instantX-research/Regional-Prompting-FLUX"],"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","unlocated"]}}},{"paper":null,"slug":"v-cas-a-realtime-vehicle-anti-collision","title":"V-CAS: A Realtime Vehicle Anti Collision System Using Vision Transformer on Multi-Camera Streams","date":"2024-11-04","arxiv_id":"2411.01963","n_code_links":0,"syntology":null},{"paper":null,"slug":"wave-network-an-ultra-small-language-model","title":"Wave Network: An Ultra-Small Language Model","date":"2024-11-04","arxiv_id":"2411.02674","n_code_links":0,"syntology":null},{"paper":"/paper/xdit-an-inference-engine-for-diffusion","slug":"xdit-an-inference-engine-for-diffusion","title":"xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism","date":"2024-11-04","arxiv_id":"2411.01738","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-dive-into-large-language-model-code","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","date":"2024-11-03","arxiv_id":"2411.01414","n_code_links":0,"syntology":null}],"record_sha256":"c0754167544e292a2b20ab83e941f371500e11b8ff673811bc306b262d26d0f6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}