{"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/61","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":61,"pages_in_order":249,"rows_per_page":100,"rows":[6001,6100],"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/60","next":"/method/multi-head-attention/papers/62","papers":[{"paper":null,"slug":"llm-select-feature-selection-with-large","title":"LLM-Select: Feature Selection with Large Language Models","date":"2024-07-02","arxiv_id":"2407.02694","n_code_links":0,"syntology":null},{"paper":"/paper/mememo-on-device-retrieval-augmentation-for","slug":"mememo-on-device-retrieval-augmentation-for","title":"MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation","date":"2024-07-02","arxiv_id":"2407.01972","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-trolley-problems-for-language","slug":"multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","date":"2024-07-02","arxiv_id":"2407.02273","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["causalNLP/moralmachine","causalnlp/multitp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"open-foundation-models-for-azerbaijani","title":"Open foundation models for Azerbaijani language","date":"2024-07-02","arxiv_id":"2407.02337","n_code_links":0,"syntology":null},{"paper":null,"slug":"openvid-1m-a-large-scale-high-quality-dataset","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","date":"2024-07-02","arxiv_id":"2407.02371","n_code_links":0,"syntology":null},{"paper":"/paper/rankrag-unifying-context-ranking-with","slug":"rankrag-unifying-context-ranking-with","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","date":"2024-07-02","arxiv_id":"2407.02485","n_code_links":0,"syntology":null},{"paper":"/paper/sop-unlock-the-power-of-social-facilitation","slug":"sop-unlock-the-power-of-social-facilitation","title":"SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters","date":"2024-07-02","arxiv_id":"2407.01902","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yang-yan-yang-yan/sop"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-art-of-saying-no-contextual-noncompliance","slug":"the-art-of-saying-no-contextual-noncompliance","title":"The Art of Saying No: Contextual Noncompliance in Language Models","date":"2024-07-02","arxiv_id":"2407.12043","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"the-solution-for-the-pst-kdd-2024-oag","title":"The Solution for The PST-KDD-2024 OAG-Challenge","date":"2024-07-02","arxiv_id":"2407.12827","n_code_links":0,"syntology":null},{"paper":"/paper/2407-01003","slug":"2407-01003","title":"Embedded Prompt Tuning: Towards Enhanced Calibration of Pretrained Models for Medical Images","date":"2024-07-01","arxiv_id":"2407.01003","n_code_links":1,"syntology":null},{"paper":"/paper/bergen-a-benchmarking-library-for-retrieval","slug":"bergen-a-benchmarking-library-for-retrieval","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","date":"2024-07-01","arxiv_id":"2407.01102","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver/bergen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/deciphering-the-factors-influencing-the","slug":"deciphering-the-factors-influencing-the","title":"Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning","date":"2024-07-01","arxiv_id":"2407.01687","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["aksh555/deciphering_cot"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/domain-influence-in-mri-medical-image","slug":"domain-influence-in-mri-medical-image","title":"Domain Influence in MRI Medical Image Segmentation: spatial versus k-space inputs","date":"2024-07-01","arxiv_id":"2407.01367","n_code_links":1,"syntology":null},{"paper":null,"slug":"face4rag-factual-consistency-evaluation-for","title":"Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese","date":"2024-07-01","arxiv_id":"2407.01080","n_code_links":0,"syntology":null},{"paper":null,"slug":"ground-every-sentence-improving-retrieval","title":"Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation","date":"2024-07-01","arxiv_id":"2407.01796","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-overparameterization-affect-features","title":"How Does Overparameterization Affect Features?","date":"2024-07-01","arxiv_id":"2407.00968","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-rag-empowered-multi-modal-llm-for","title":"Hybrid RAG-empowered Multi-modal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-based Contract Approach","date":"2024-07-01","arxiv_id":"2407.00978","n_code_links":0,"syntology":null},{"paper":"/paper/hypformer-exploring-efficient-hyperbolic","slug":"hypformer-exploring-efficient-hyperbolic","title":"Hypformer: Exploring Efficient Hyperbolic Transformer Fully in Hyperbolic Space","date":"2024-07-01","arxiv_id":"2407.01290","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Graph-and-Geometric-Learning/hyperbolic-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"image-to-text-logic-jailbreak-your","title":"Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything","date":"2024-07-01","arxiv_id":"2407.02534","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-trip-mode-choice-modeling-using","title":"Improving Trip Mode Choice Modeling Using Ensemble Synthesizer (ENSY)","date":"2024-07-01","arxiv_id":"2407.01769","n_code_links":0,"syntology":null},{"paper":"/paper/increasing-model-capacity-for-free-a-simple","slug":"increasing-model-capacity-for-free-a-simple","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","date":"2024-07-01","arxiv_id":"2407.01320","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":7,"phrase":"7 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lins-lab/capaboost"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"investigating-the-potential-of-sparse","title":"Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation","date":"2024-07-01","arxiv_id":"2407.01126","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-enhanced-knowledge","title":"Large Language Model Enhanced Knowledge Representation Learning: A Survey","date":"2024-07-01","arxiv_id":"2407.00936","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-branch-cnn-and-grouping-cascade","title":"Multi-branch CNN and grouping cascade attention for medical image classification","date":"2024-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-fusion-based-multi-task-semantic","title":"Multi-Modal Fusion-Based Multi-Task Semantic Communication System","date":"2024-07-01","arxiv_id":"2407.00964","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-state-action-tokenisation-in-decision","title":"Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spaces","date":"2024-07-01","arxiv_id":"2407.01310","n_code_links":0,"syntology":null},{"paper":"/paper/papez-resource-efficient-speech-separation","slug":"papez-resource-efficient-speech-separation","title":"Papez: Resource-Efficient Speech Separation with Auditory Working Memory","date":"2024-07-01","arxiv_id":"2407.00888","n_code_links":1,"syntology":null},{"paper":null,"slug":"pictures-of-midi-controlled-music-generation","title":"Pictures Of MIDI: Controlled Music Generation via Graphical Prompts for Image-Based Diffusion Inpainting","date":"2024-07-01","arxiv_id":"2407.01499","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-dc-link-capacitor-current-ripple","title":"Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier Circuits Using Fine-Tuned Large Language Models","date":"2024-07-01","arxiv_id":"2407.01724","n_code_links":0,"syntology":null},{"paper":null,"slug":"pron-vs-prompt-can-large-language-models","title":"Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?","date":"2024-07-01","arxiv_id":"2407.01119","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-in","slug":"retrieval-augmented-generation-in","title":"Retrieval-augmented generation in multilingual settings","date":"2024-07-01","arxiv_id":"2407.01463","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver/bergen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"roleplay-doh-enabling-domain-experts-to","title":"Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles","date":"2024-07-01","arxiv_id":"2407.00870","n_code_links":0,"syntology":null},{"paper":"/paper/searching-for-best-practices-in-retrieval","slug":"searching-for-best-practices-in-retrieval","title":"Searching for Best Practices in Retrieval-Augmented Generation","date":"2024-07-01","arxiv_id":"2407.01219","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":["FudanDNN-NLP/RAG"],"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":"/paper/summary-of-a-haystack-a-challenge-to-long","slug":"summary-of-a-haystack-a-challenge-to-long","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","date":"2024-07-01","arxiv_id":"2407.01370","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salesforce/summary-of-a-haystack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-memory-3-language-modeling-with-explicit","title":"$\\text{Memory}^3$: Language Modeling with Explicit Memory","date":"2024-07-01","arxiv_id":"2407.01178","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-solution-for-temporal-sound-localisation","title":"The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023","date":"2024-07-01","arxiv_id":"2407.02318","n_code_links":0,"syntology":null},{"paper":"/paper/uni-dvps-unified-model-for-depth-aware-video","slug":"uni-dvps-unified-model-for-depth-aware-video","title":"Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation","date":"2024-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"universal-approximation-theory-the-basic","title":"Dynamic Universal Approximation Theory: The Basic Theory for Transformer-based Large Language Models","date":"2024-07-01","arxiv_id":"2407.00958","n_code_links":0,"syntology":null},{"paper":null,"slug":"characterizing-stereotypical-bias-from","title":"Characterizing Stereotypical Bias from Privacy-preserving Pre-Training","date":"2024-06-30","arxiv_id":"2407.00764","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-bias-towards-medical","title":"Evaluation of Bias Towards Medical Professionals in Large Language Models","date":"2024-06-30","arxiv_id":"2407.12031","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-a-physics-informed-decision","title":"Exploring a Physics-Informed Decision Transformer for Distribution System Restoration: Methodology and Performance Analysis","date":"2024-06-30","arxiv_id":"2407.00808","n_code_links":0,"syntology":null},{"paper":"/paper/instruct-ipt-all-in-one-image-processing-1","slug":"instruct-ipt-all-in-one-image-processing-1","title":"Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation","date":"2024-06-30","arxiv_id":"2407.00676","n_code_links":1,"syntology":null},{"paper":null,"slug":"legalturk-optimized-bert-for-multi-label-text","title":"LegalTurk Optimized BERT for Multi-Label Text Classification and NER","date":"2024-06-30","arxiv_id":"2407.00648","n_code_links":0,"syntology":null},{"paper":null,"slug":"naist-simultaneous-speech-translation-system","title":"NAIST Simultaneous Speech Translation System for IWSLT 2024","date":"2024-06-30","arxiv_id":"2407.00826","n_code_links":0,"syntology":null},{"paper":"/paper/parm-efficient-training-of-large-sparsely","slug":"parm-efficient-training-of-large-sparsely","title":"Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules","date":"2024-06-30","arxiv_id":"2407.00599","n_code_links":1,"syntology":null},{"paper":null,"slug":"answering-real-world-clinical-questions-using","title":"Answering real-world clinical questions using large language model based systems","date":"2024-06-29","arxiv_id":"2407.00541","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-rag-to-riches-retrieval-interlaced-with","title":"From RAG to RICHES: Retrieval Interlaced with Sequence Generation","date":"2024-06-29","arxiv_id":"2407.00361","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-pretrained-speech-models-for","title":"Interpreting Pretrained Speech Models for Automatic Speech Assessment of Voice Disorders","date":"2024-06-29","arxiv_id":"2407.00531","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-generated-natural-language-meets-scaling","title":"LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods","date":"2024-06-29","arxiv_id":"2407.00322","n_code_links":0,"syntology":null},{"paper":null,"slug":"too-late-to-train-too-early-to-use-a-study-on","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","date":"2024-06-29","arxiv_id":"2407.00416","n_code_links":0,"syntology":null},{"paper":"/paper/towards-universal-mesh-movement-networks","slug":"towards-universal-mesh-movement-networks","title":"Towards Universal Mesh Movement Networks","date":"2024-06-29","arxiv_id":"2407.00382","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["mesh-adaptation/um2n"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"urban-visual-appeal-according-to-chatgpt","title":"Urban Visual Appeal According to ChatGPT: Contrasting AI and Human Insights","date":"2024-06-29","arxiv_id":"2407.14268","n_code_links":0,"syntology":null},{"paper":"/paper/anomallmy-detecting-anomalous-tokens-in-black","slug":"anomallmy-detecting-anomalous-tokens-in-black","title":"AnomaLLMy -- Detecting anomalous tokens in black-box LLMs through low-confidence single-token predictions","date":"2024-06-28","arxiv_id":"2406.19840","n_code_links":1,"syntology":null},{"paper":null,"slug":"applying-rlaif-for-code-generation-with-api","title":"Applying RLAIF for Code Generation with API-usage in Lightweight LLMs","date":"2024-06-28","arxiv_id":"2406.20060","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-meets-uavs-a-comprehensive","title":"Attention Meets UAVs: A Comprehensive Evaluation of DDoS Detection in Low-Cost UAVs","date":"2024-06-28","arxiv_id":"2406.19881","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomner-a-dataset-for-biomedical-method","title":"BioMNER: A Dataset for Biomedical Method Entity Recognition","date":"2024-06-28","arxiv_id":"2406.20038","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-4-help-detect-quit-vaping-intentions","title":"Can GPT-4 Help Detect Quit Vaping Intentions? An Exploration of Automatic Data Annotation Approach","date":"2024-06-28","arxiv_id":"2407.00167","n_code_links":0,"syntology":null},{"paper":null,"slug":"covert-malicious-finetuning-challenges-in","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","date":"2024-06-28","arxiv_id":"2406.20053","n_code_links":0,"syntology":null},{"paper":null,"slug":"fred-flexible-reduction-distribution","title":"FRED: Flexible REduction-Distribution Interconnect and Communication Implementation for Wafer-Scale Distributed Training of DNN Models","date":"2024-06-28","arxiv_id":"2406.19580","n_code_links":0,"syntology":null},{"paper":"/paper/generative-iris-prior-embedded-transformer","slug":"generative-iris-prior-embedded-transformer","title":"Generative Iris Prior Embedded Transformer for Iris Restoration","date":"2024-06-28","arxiv_id":"2407.00261","n_code_links":1,"syntology":null},{"paper":"/paper/infinigen-efficient-generative-inference-of","slug":"infinigen-efficient-generative-inference-of","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","date":"2024-06-28","arxiv_id":"2406.19707","n_code_links":1,"syntology":{"ran":14,"of":15,"n_ran_checked":10,"n_instrument":4,"unverified":1,"pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/machine-learning-predictors-for-min-entropy","slug":"machine-learning-predictors-for-min-entropy","title":"Machine Learning Predictors for Min-Entropy Estimation","date":"2024-06-28","arxiv_id":"2406.19983","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-prototyping-for-cancer-survival","slug":"multimodal-prototyping-for-cancer-survival","title":"Multimodal Prototyping for cancer survival prediction","date":"2024-06-28","arxiv_id":"2407.00224","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":4,"n_instrument":3,"unverified":5,"pointer_only":12,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mahmoodlab/MMP"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"poliformer-scaling-on-policy-rl-with","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","date":"2024-06-28","arxiv_id":"2406.20083","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalebio-scalable-bilevel-optimization-for","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","date":"2024-06-28","arxiv_id":"2406.19976","n_code_links":0,"syntology":null},{"paper":"/paper/shortcutsbench-a-large-scale-real-world","slug":"shortcutsbench-a-large-scale-real-world","title":"ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents","date":"2024-06-28","arxiv_id":"2407.00132","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eachsheep/shortcutsbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-computational-curse-of-big-data-for","slug":"the-computational-curse-of-big-data-for","title":"The Computational Curse of Big Data for Bayesian Additive Regression Trees: A Hitting Time Analysis","date":"2024-06-28","arxiv_id":"2406.19958","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-quantification-in-large-language","title":"Uncertainty Quantification in Large Language Models Through Convex Hull Analysis","date":"2024-06-28","arxiv_id":"2406.19712","n_code_links":0,"syntology":null},{"paper":"/paper/autopuredata-automated-filtering-of-web-data","slug":"autopuredata-automated-filtering-of-web-data","title":"AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge","date":"2024-06-27","arxiv_id":"2406.19271","n_code_links":1,"syntology":null},{"paper":null,"slug":"autorag-hp-automatic-online-hyper-parameter","title":"AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation","date":"2024-06-27","arxiv_id":"2406.19251","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-generate-high","slug":"can-large-language-models-generate-high","title":"Can Large Language Models Generate High-quality Patent Claims?","date":"2024-06-27","arxiv_id":"2406.19465","n_code_links":1,"syntology":null},{"paper":null,"slug":"diminishing-stereotype-bias-in-image","title":"Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback","date":"2024-06-27","arxiv_id":"2407.09551","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-video-language-representations-with","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","date":"2024-06-27","arxiv_id":"2406.19255","n_code_links":0,"syntology":null},{"paper":"/paper/fibottention-inceptive-visual-representation","slug":"fibottention-inceptive-visual-representation","title":"Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads","date":"2024-06-27","arxiv_id":"2406.19391","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuned-network-relies-on-generic","title":"Fine-tuned network relies on generic representation to solve unseen cognitive task","date":"2024-06-27","arxiv_id":"2406.18926","n_code_links":0,"syntology":null},{"paper":"/paper/from-artificial-needles-to-real-haystacks","slug":"from-artificial-needles-to-real-haystacks","title":"From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data","date":"2024-06-27","arxiv_id":"2406.19292","n_code_links":1,"syntology":null},{"paper":null,"slug":"granite-function-calling-model-introducing","title":"Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks","date":"2024-06-27","arxiv_id":"2407.00121","n_code_links":0,"syntology":null},{"paper":null,"slug":"historia-magistra-vitae-dynamic-topic","title":"Historia Magistra Vitae: Dynamic Topic Modeling of Roman Literature using Neural Embeddings","date":"2024-06-27","arxiv_id":"2406.18907","n_code_links":0,"syntology":null},{"paper":"/paper/human-aware-vision-and-language-navigation","slug":"human-aware-vision-and-language-navigation","title":"Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions","date":"2024-06-27","arxiv_id":"2406.19236","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lpercc/ha3d_simulator"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"indotoxic2024-a-demographically-enriched","title":"IndoToxic2024: A Demographically-Enriched Dataset of Hate Speech and Toxicity Types for Indonesian Language","date":"2024-06-27","arxiv_id":"2406.19349","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-contrastive-learning-for-enhanced","title":"Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers","date":"2024-06-27","arxiv_id":"2406.19258","n_code_links":0,"syntology":null},{"paper":null,"slug":"ntformer-a-composite-node-tokenized-graph","title":"NTFormer: A Composite Node Tokenized Graph Transformer for Node Classification","date":"2024-06-27","arxiv_id":"2406.19249","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-depression-and-anxiety-risk-in","title":"Predicting Depression and Anxiety Risk in Dutch Neighborhoods from Street-View Images","date":"2024-06-27","arxiv_id":"2407.09547","n_code_links":0,"syntology":null},{"paper":null,"slug":"raven-multitask-retrieval-augmented-vision","title":"RAVEN: Multitask Retrieval Augmented Vision-Language Learning","date":"2024-06-27","arxiv_id":"2406.19150","n_code_links":0,"syntology":null},{"paper":"/paper/retain-blend-and-exchange-a-quality-aware","slug":"retain-blend-and-exchange-a-quality-aware","title":"Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition","date":"2024-06-27","arxiv_id":"2406.18845","n_code_links":1,"syntology":null},{"paper":"/paper/seakr-self-aware-knowledge-retrieval-for","slug":"seakr-self-aware-knowledge-retrieval-for","title":"SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation","date":"2024-06-27","arxiv_id":"2406.19215","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thu-keg/seakr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"seeing-is-believing-black-box-membership","title":"Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation","date":"2024-06-27","arxiv_id":"2406.19234","n_code_links":0,"syntology":null},{"paper":null,"slug":"segment-anything-model-for-automated-image","title":"Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO","date":"2024-06-27","arxiv_id":"2406.19057","n_code_links":0,"syntology":null},{"paper":"/paper/sonnet-or-not-bot-poetry-evaluation-for-large","slug":"sonnet-or-not-bot-poetry-evaluation-for-large","title":"Sonnet or Not, Bot? Poetry Evaluation for Large Models and Datasets","date":"2024-06-27","arxiv_id":"2406.18906","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["maria-antoniak/poetry-eval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/structural-attention-rethinking-transformer","slug":"structural-attention-rethinking-transformer","title":"Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis","date":"2024-06-27","arxiv_id":"2406.18967","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-model-arena-for-cross-lingual-sentiment","title":"The Model Arena for Cross-lingual Sentiment Analysis: A Comparative Study in the Era of Large Language Models","date":"2024-06-27","arxiv_id":"2406.19358","n_code_links":0,"syntology":null},{"paper":"/paper/unigen-a-unified-framework-for-textual","slug":"unigen-a-unified-framework-for-textual","title":"UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models","date":"2024-06-27","arxiv_id":"2406.18966","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":8,"n_instrument":0,"unverified":5,"pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["howiehwong/unigen"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/yzs-model-a-predictive-model-for-organic-drug","slug":"yzs-model-a-predictive-model-for-organic-drug","title":"YZS-model: A Predictive Model for Organic Drug Solubility Based on Graph Convolutional Networks and Transformer-Attention","date":"2024-06-27","arxiv_id":"2406.19136","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-mvp-3d-multiview-pretraining-for-robotic","title":"3D-MVP: 3D Multiview Pretraining for Robotic Manipulation","date":"2024-06-26","arxiv_id":"2406.18158","n_code_links":0,"syntology":null},{"paper":"/paper/a-stem-agnostic-single-decoder-system-for","slug":"a-stem-agnostic-single-decoder-system-for","title":"A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems","date":"2024-06-26","arxiv_id":"2406.18747","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kwatcharasupat/query-bandit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adversarial-search-engine-optimization-for","title":"Adversarial Search Engine Optimization for Large Language Models","date":"2024-06-26","arxiv_id":"2406.18382","n_code_links":0,"syntology":null},{"paper":null,"slug":"apigen-automated-pipeline-for-generating","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","date":"2024-06-26","arxiv_id":"2406.18518","n_code_links":0,"syntology":null},{"paper":"/paper/badge-badminton-report-generation-and","slug":"badge-badminton-report-generation-and","title":"BADGE: BADminton report Generation and Evaluation with LLM","date":"2024-06-26","arxiv_id":"2406.18116","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-quality-of-answers-for-retrieval","title":"Evaluating Quality of Answers for Retrieval-Augmented Generation: A Strong LLM Is All You Need","date":"2024-06-26","arxiv_id":"2406.18064","n_code_links":0,"syntology":null},{"paper":"/paper/factfinders-at-checkthat-2024-refining-check","slug":"factfinders-at-checkthat-2024-refining-check","title":"FactFinders at CheckThat! 2024: Refining Check-worthy Statement Detection with LLMs through Data Pruning","date":"2024-06-26","arxiv_id":"2406.18297","n_code_links":1,"syntology":null}],"record_sha256":"618c44a5f5126195b8156c312872c431ef6606c0744bc439cb235d55db494fad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}