{"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/60","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":60,"pages_in_order":249,"rows_per_page":100,"rows":[5901,6000],"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/59","next":"/method/multi-head-attention/papers/61","papers":[{"paper":null,"slug":"tailor3d-customized-3d-assets-editing-and","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","date":"2024-07-08","arxiv_id":"2407.06191","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-optimizing-and-evaluating-a-retrieval","title":"Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loop","date":"2024-07-08","arxiv_id":"2407.05925","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-with-self-supervised-vision","slug":"transfer-learning-with-self-supervised-vision","title":"Transfer Learning with Self-Supervised Vision Transformers for Snake Identification","date":"2024-07-08","arxiv_id":"2407.06178","n_code_links":1,"syntology":null},{"paper":"/paper/transma-an-explainable-multi-modal-deep","slug":"transma-an-explainable-multi-modal-deep","title":"TransMA: an explainable multi-modal deep learning model for predicting properties of ionizable lipid nanoparticles in mRNA delivery","date":"2024-07-08","arxiv_id":"2407.05736","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-braille-an-end-to-end-tool-for-chinese","title":"Vision-Braille: An End-to-End Tool for Chinese Braille Image-to-Text Translation","date":"2024-07-08","arxiv_id":"2407.06048","n_code_links":0,"syntology":null},{"paper":"/paper/wsi-vqa-interpreting-whole-slide-images-by","slug":"wsi-vqa-interpreting-whole-slide-images-by","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","date":"2024-07-08","arxiv_id":"2407.05603","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["cpystan/wsi-vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-computer-programming-education-with","title":"Enhancing Computer Programming Education with LLMs: A Study on Effective Prompt Engineering for Python Code Generation","date":"2024-07-07","arxiv_id":"2407.05437","n_code_links":0,"syntology":null},{"paper":"/paper/just-read-twice-closing-the-recall-gap-for","slug":"just-read-twice-closing-the-recall-gap-for","title":"Just read twice: closing the recall gap for recurrent language models","date":"2024-07-07","arxiv_id":"2407.05483","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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":["HazyResearch/prefix-linear-attention"],"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":"large-language-model-as-an-assignment","title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course","date":"2024-07-07","arxiv_id":"2407.05216","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-motion-blur-robust-vision","title":"Learning Motion Blur Robust Vision Transformers with Dynamic Early Exit for Real-Time UAV Tracking","date":"2024-07-07","arxiv_id":"2407.05383","n_code_links":0,"syntology":null},{"paper":null,"slug":"mamba-hawkes-process","title":"Mamba Hawkes Process","date":"2024-07-07","arxiv_id":"2407.05302","n_code_links":0,"syntology":null},{"paper":null,"slug":"mindecho-role-playing-language-agents-for-key","title":"MINDECHO: Role-Playing Language Agents for Key Opinion Leaders","date":"2024-07-07","arxiv_id":"2407.05305","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-prompt-learning-with-missing","slug":"multimodal-prompt-learning-with-missing","title":"Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition","date":"2024-07-07","arxiv_id":"2407.05374","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["zrguo/MPLMM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/ptarl-prototype-based-tabular-representation-1","slug":"ptarl-prototype-based-tabular-representation-1","title":"PTaRL: Prototype-based Tabular Representation Learning via Space Calibration","date":"2024-07-07","arxiv_id":"2407.05364","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"4 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; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/clipvqa-video-quality-assessment-via-clip","slug":"clipvqa-video-quality-assessment-via-clip","title":"CLIPVQA:Video Quality Assessment via CLIP","date":"2024-07-06","arxiv_id":"2407.04928","n_code_links":1,"syntology":null},{"paper":null,"slug":"eva-score-evaluation-of-long-form","title":"EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation","date":"2024-07-06","arxiv_id":"2407.04969","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-you-know-that-teaching-generative","slug":"how-do-you-know-that-teaching-generative","title":"How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions","date":"2024-07-06","arxiv_id":"2407.05015","n_code_links":1,"syntology":null},{"paper":null,"slug":"integer-only-quantized-transformers-for","title":"Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT","date":"2024-07-06","arxiv_id":"2407.11041","n_code_links":0,"syntology":null},{"paper":"/paper/prance-joint-token-optimization-and","slug":"prance-joint-token-optimization-and","title":"PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference","date":"2024-07-06","arxiv_id":"2407.05010","n_code_links":1,"syntology":null},{"paper":"/paper/rule-reliable-multimodal-rag-for-factuality","slug":"rule-reliable-multimodal-rag-for-factuality","title":"RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models","date":"2024-07-06","arxiv_id":"2407.05131","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["richard-peng-xia/rule"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/shine-saliency-aware-hierarchical-negative","slug":"shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","date":"2024-07-06","arxiv_id":"2407.05118","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zxccade/shine"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/solving-for-x-and-beyond-can-large-language","slug":"solving-for-x-and-beyond-can-large-language","title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?","date":"2024-07-06","arxiv_id":"2407.05134","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-solution-for-the-aigc-inference","title":"The Solution for the AIGC Inference Performance Optimization Competition","date":"2024-07-06","arxiv_id":"2407.04991","n_code_links":0,"syntology":null},{"paper":null,"slug":"vortex-under-ripplet-an-empirical-study-of","title":"Are LLMs Correctly Integrated into Software Systems?","date":"2024-07-06","arxiv_id":"2407.05138","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-model-evaluations-with-human","title":"Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments","date":"2024-07-05","arxiv_id":"2407.12847","n_code_links":0,"syntology":null},{"paper":"/paper/anah-v2-scaling-analytical-hallucination","slug":"anah-v2-scaling-analytical-hallucination","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","date":"2024-07-05","arxiv_id":"2407.04693","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":0,"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":["open-compass/anah"],"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":"are-large-language-models-strategic-decision","title":"Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games","date":"2024-07-05","arxiv_id":"2407.04467","n_code_links":0,"syntology":null},{"paper":"/paper/associative-recurrent-memory-transformer","slug":"associative-recurrent-memory-transformer","title":"Associative Recurrent Memory Transformer","date":"2024-07-05","arxiv_id":"2407.04841","n_code_links":1,"syntology":{"ran":4,"of":14,"n_ran_checked":4,"n_instrument":0,"unverified":10,"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) · 10 unverified","official":{"repos":["RodkinIvan/associative-recurrent-memory-transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-vs-retro-exploring-the-intersection-of","title":"GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning","date":"2024-07-05","arxiv_id":"2407.04528","n_code_links":0,"syntology":null},{"paper":null,"slug":"hcs-tnas-hybrid-constraint-driven-semi","title":"HCS-TNAS: Hybrid Constraint-driven Semi-supervised Transformer-NAS for Ultrasound Image Segmentation","date":"2024-07-05","arxiv_id":"2407.04203","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-ensemble-extreme-precipitation","title":"Improving ensemble extreme precipitation forecasts using generative artificial intelligence","date":"2024-07-05","arxiv_id":"2407.04882","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-learn-at-test-time-rnns-with","slug":"learning-to-learn-at-test-time-rnns-with","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","date":"2024-07-05","arxiv_id":"2407.04620","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["test-time-training/ttt-lm-pytorch"],"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","unlocated"]}}},{"paper":"/paper/multi-modal-masked-siamese-network-improves","slug":"multi-modal-masked-siamese-network-improves","title":"Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning","date":"2024-07-05","arxiv_id":"2407.04449","n_code_links":3,"syntology":null},{"paper":null,"slug":"robust-decision-transformer-tackling-data","title":"Robust Decision Transformer: Tackling Data Corruption in Offline RL via Sequence Modeling","date":"2024-07-05","arxiv_id":"2407.04285","n_code_links":0,"syntology":null},{"paper":"/paper/strengthening-structural-inductive-biases-by","slug":"strengthening-structural-inductive-biases-by","title":"Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations","date":"2024-07-05","arxiv_id":"2407.04543","n_code_links":1,"syntology":null},{"paper":"/paper/using-llms-to-label-medical-papers-according","slug":"using-llms-to-label-medical-papers-according","title":"Using LLMs to label medical papers according to the CIViC evidence model","date":"2024-07-05","arxiv_id":"2407.04466","n_code_links":1,"syntology":null},{"paper":"/paper/wavelet-based-temporal-attention-improves","slug":"wavelet-based-temporal-attention-improves","title":"Spatiotemporal Forecasting of Traffic Flow using Wavelet-based Temporal Attention","date":"2024-07-05","arxiv_id":"2407.04440","n_code_links":1,"syntology":null},{"paper":"/paper/yourmt3-multi-instrument-music-transcription","slug":"yourmt3-multi-instrument-music-transcription","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","date":"2024-07-05","arxiv_id":"2407.04822","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-computer-vision-approach-to-estimate-the","title":"A Computer Vision Approach to Estimate the Localized Sea State","date":"2024-07-04","arxiv_id":"2407.03755","n_code_links":0,"syntology":null},{"paper":"/paper/adapt-multimodal-learning-for-detecting","slug":"adapt-multimodal-learning-for-detecting","title":"ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalities","date":"2024-07-04","arxiv_id":"2407.03836","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-step-size-perception-unfolding","title":"Adaptive Step-size Perception Unfolding Network with Non-local Hybrid Attention for Hyperspectral Image Reconstruction","date":"2024-07-04","arxiv_id":"2407.04024","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-vs-large-language-models-for","title":"Convolutional vs Large Language Models for Software Log Classification in Edge-Deployable Cellular Network Testing","date":"2024-07-04","arxiv_id":"2407.03759","n_code_links":0,"syntology":null},{"paper":"/paper/dass-distilled-audio-state-space-models-are","slug":"dass-distilled-audio-state-space-models-are","title":"DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners","date":"2024-07-04","arxiv_id":"2407.04082","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Saurabhbhati/DASS"],"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/deep-content-understanding-toward-entity-and","slug":"deep-content-understanding-toward-entity-and","title":"Deep Content Understanding Toward Entity and Aspect Target Sentiment Analysis on Foundation Models","date":"2024-07-04","arxiv_id":"2407.04050","n_code_links":1,"syntology":null},{"paper":null,"slug":"diverse-and-fine-grained-instruction","title":"Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data","date":"2024-07-04","arxiv_id":"2407.03942","n_code_links":0,"syntology":null},{"paper":null,"slug":"dslr-document-refinement-with-sentence-level","title":"DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation","date":"2024-07-04","arxiv_id":"2407.03627","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-language-model-context-windows-a","slug":"evaluating-language-model-context-windows-a","title":"Evaluating Language Model Context Windows: A \"Working Memory\" Test and Inference-time Correction","date":"2024-07-04","arxiv_id":"2407.03651","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-data-to-commonsense-reasoning-the-use-of","title":"From Data to Commonsense Reasoning: The Use of Large Language Models for Explainable AI","date":"2024-07-04","arxiv_id":"2407.03778","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalizing-graph-transformers-across","title":"Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-Training on Industrial-Scale Data","date":"2024-07-04","arxiv_id":"2407.03953","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-vs-human-translators-a-comprehensive","title":"GPT-4 vs. Human Translators: A Comprehensive Evaluation of Translation Quality Across Languages, Domains, and Expertise Levels","date":"2024-07-04","arxiv_id":"2407.03658","n_code_links":0,"syntology":null},{"paper":null,"slug":"hera-high-efficiency-matrix-compression-via","title":"QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering","date":"2024-07-04","arxiv_id":"2407.03637","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrinfox-at-checkthat-2024-task-1-enhancing","title":"HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation","date":"2024-07-04","arxiv_id":"2407.03850","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrinfox-at-checkthat-2024-task-2-enriching","title":"HYBRINFOX at CheckThat! 2024 -- Task 2: Enriching BERT Models with the Expert System VAGO for Subjectivity Detection","date":"2024-07-04","arxiv_id":"2407.03770","n_code_links":0,"syntology":null},{"paper":null,"slug":"looking-for-tiny-defects-via-forward-backward","title":"Looking for Tiny Defects via Forward-Backward Feature Transfer","date":"2024-07-04","arxiv_id":"2407.04092","n_code_links":0,"syntology":null},{"paper":null,"slug":"nutribench-a-dataset-for-evaluating-large","title":"NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions","date":"2024-07-04","arxiv_id":"2407.12843","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-benchmarking-of-llms-for-open-domain","title":"On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation","date":"2024-07-04","arxiv_id":"2407.03841","n_code_links":0,"syntology":null},{"paper":"/paper/planning-with-large-language-models-for","slug":"planning-with-large-language-models-for","title":"Controllable Conversations: Planning-Based Dialogue Agent with Large Language Models","date":"2024-07-04","arxiv_id":"2407.03884","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-guided-self-supervised-summarization-of","title":"Query-Guided Self-Supervised Summarization of Nursing Notes","date":"2024-07-04","arxiv_id":"2407.04125","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-analysis-prompting-improves-llm","title":"Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks","date":"2024-07-04","arxiv_id":"2407.03624","n_code_links":0,"syntology":null},{"paper":null,"slug":"slice-100k-a-multimodal-dataset-for-extrusion","title":"Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing","date":"2024-07-04","arxiv_id":"2407.04180","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-zebra-puzzles-using-constraint-guided","title":"Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems","date":"2024-07-04","arxiv_id":"2407.03956","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-automating-text-annotation-a-case","title":"Towards Automating Text Annotation: A Case Study on Semantic Proximity Annotation using GPT-4","date":"2024-07-04","arxiv_id":"2407.04130","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-dsl-code-generation","title":"A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation","date":"2024-07-03","arxiv_id":"2407.02742","n_code_links":0,"syntology":null},{"paper":"/paper/a-unified-framework-for-3d-scene","slug":"a-unified-framework-for-3d-scene","title":"A Unified Framework for 3D Scene Understanding","date":"2024-07-03","arxiv_id":"2407.03263","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dk-liang/uniseg3d"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"agentinstruct-toward-generative-teaching-with","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","date":"2024-07-03","arxiv_id":"2407.03502","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-gradient-descent-with-generalized","slug":"automatic-gradient-descent-with-generalized","title":"Gradient descent with generalized Newton's method","date":"2024-07-03","arxiv_id":"2407.02772","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["shiyunxu/autogen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/catt-character-based-arabic-tashkeel","slug":"catt-character-based-arabic-tashkeel","title":"CATT: Character-based Arabic Tashkeel Transformer","date":"2024-07-03","arxiv_id":"2407.03236","n_code_links":1,"syntology":null},{"paper":null,"slug":"croppable-knowledge-graph-embedding","title":"Croppable Knowledge Graph Embedding","date":"2024-07-03","arxiv_id":"2407.02779","n_code_links":0,"syntology":null},{"paper":"/paper/fine-grained-scene-image-classification-with","slug":"fine-grained-scene-image-classification-with","title":"Fine-Grained Scene Image Classification with Modality-Agnostic Adapter","date":"2024-07-03","arxiv_id":"2407.02769","n_code_links":1,"syntology":null},{"paper":null,"slug":"fisher-aware-quantization-for-detr-detectors","title":"Fisher-aware Quantization for DETR Detectors with Critical-category Objectives","date":"2024-07-03","arxiv_id":"2407.03442","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-and-skipped-transformer-exploiting","title":"Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation","date":"2024-07-03","arxiv_id":"2407.02990","n_code_links":0,"syntology":null},{"paper":"/paper/human-like-linguistic-biases-in-neural-speech","slug":"human-like-linguistic-biases-in-neural-speech","title":"Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0","date":"2024-07-03","arxiv_id":"2407.03005","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-llm-abilities-in-idiomatic","title":"Improving LLM Abilities in Idiomatic Translation","date":"2024-07-03","arxiv_id":"2407.03518","n_code_links":0,"syntology":null},{"paper":null,"slug":"iswsst-index-space-wave-state-superposition","title":"ISWSST: Index-space-wave State Superposition Transformers for Multispectral Remotely Sensed Imagery Semantic Segmentation","date":"2024-07-03","arxiv_id":"2407.03033","n_code_links":0,"syntology":null},{"paper":null,"slug":"lane-logic-alignment-of-non-tuning-large","title":"LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation","date":"2024-07-03","arxiv_id":"2407.02833","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-evaluators-for-1","title":"Large Language Models as Evaluators for Scientific Synthesis","date":"2024-07-03","arxiv_id":"2407.02977","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-reduce-towards-improving","title":"Learning to Reduce: Towards Improving Performance of Large Language Models on Structured Data","date":"2024-07-03","arxiv_id":"2407.02750","n_code_links":0,"syntology":null},{"paper":null,"slug":"m5-a-whole-genome-bacterial-encoder-at-single","title":"M5: A Whole Genome Bacterial Encoder at Single Nucleotide Resolution","date":"2024-07-03","arxiv_id":"2407.03392","n_code_links":0,"syntology":null},{"paper":null,"slug":"mlkd-bert-multi-level-knowledge-distillation","title":"MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models","date":"2024-07-03","arxiv_id":"2407.02775","n_code_links":0,"syntology":null},{"paper":null,"slug":"mvgt-a-multi-view-graph-transformer-based-on","title":"MVGT: A Multi-view Graph Transformer Based on Spatial Relations for EEG Emotion Recognition","date":"2024-07-03","arxiv_id":"2407.03131","n_code_links":0,"syntology":null},{"paper":null,"slug":"obfuscatune-obfuscated-offsite-fine-tuning","title":"ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets","date":"2024-07-03","arxiv_id":"2407.02960","n_code_links":0,"syntology":null},{"paper":"/paper/on-large-language-models-in-national-security","slug":"on-large-language-models-in-national-security","title":"On Large Language Models in National Security Applications","date":"2024-07-03","arxiv_id":"2407.03453","n_code_links":1,"syntology":null},{"paper":null,"slug":"ospc-artificial-vlm-features-for-hateful-meme","title":"OSPC: Artificial VLM Features for Hateful Meme Detection","date":"2024-07-03","arxiv_id":"2407.12836","n_code_links":0,"syntology":null},{"paper":null,"slug":"rdbe-reasoning-distillation-based-evaluation","title":"RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring","date":"2024-07-03","arxiv_id":"2407.13781","n_code_links":0,"syntology":null},{"paper":null,"slug":"regurgitative-training-the-value-of-real-data","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","date":"2024-07-03","arxiv_id":"2407.12835","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-vision-transformer-are","slug":"self-supervised-vision-transformer-are","title":"Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization","date":"2024-07-03","arxiv_id":"2407.02900","n_code_links":1,"syntology":null},{"paper":null,"slug":"semiollm-assessing-large-language-models-for","title":"SemioLLM: Assessing Large Language Models for Semiological Analysis in Epilepsy Research","date":"2024-07-03","arxiv_id":"2407.03004","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatio-temporal-adaptive-diffusion-models-for","title":"Generative AI Enables EEG Super-Resolution via Spatio-Temporal Adaptive Diffusion Learning","date":"2024-07-03","arxiv_id":"2407.03089","n_code_links":0,"syntology":null},{"paper":"/paper/theoremllama-transforming-general-purpose","slug":"theoremllama-transforming-general-purpose","title":"TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts","date":"2024-07-03","arxiv_id":"2407.03203","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["RickySkywalker/TheoremLlama"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-depression-detection-method-based-on-multi","title":"A Depression Detection Method Based on Multi-Modal Feature Fusion Using Cross-Attention","date":"2024-07-02","arxiv_id":"2407.12825","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-modality-balanced-online-knowledge","slug":"adaptive-modality-balanced-online-knowledge","title":"Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer based Dim Object Detection","date":"2024-07-02","arxiv_id":"2407.01894","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-the-code-clone-detection-capability","title":"Assessing the Code Clone Detection Capability of Large Language Models","date":"2024-07-02","arxiv_id":"2407.02402","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-numeric-awards-in-context-dueling","title":"Beyond Numeric Awards: In-Context Dueling Bandits with LLM Agents","date":"2024-07-02","arxiv_id":"2407.01887","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-apparent-diffusion","title":"Deep Learning Based Apparent Diffusion Coefficient Map Generation from Multi-parametric MR Images for Patients with Diffuse Gliomas","date":"2024-07-02","arxiv_id":"2407.02616","n_code_links":0,"syntology":null},{"paper":"/paper/extracting-and-encoding-leveraging-large","slug":"extracting-and-encoding-leveraging-large","title":"Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation","date":"2024-07-02","arxiv_id":"2407.01948","n_code_links":1,"syntology":null},{"paper":null,"slug":"fake-news-detection-and-manipulation","title":"Fake News Detection and Manipulation Reasoning via Large Vision-Language Models","date":"2024-07-02","arxiv_id":"2407.02042","n_code_links":0,"syntology":null},{"paper":"/paper/gptcast-a-weather-language-model-for","slug":"gptcast-a-weather-language-model-for","title":"GPTCast: a weather language model for precipitation nowcasting","date":"2024-07-02","arxiv_id":"2407.02089","n_code_links":1,"syntology":null},{"paper":null,"slug":"grasp-a-grid-based-benchmark-for-evaluating","title":"GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning","date":"2024-07-02","arxiv_id":"2407.01892","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-visual-storytelling-with-multimodal","title":"Improving Visual Storytelling with Multimodal Large Language Models","date":"2024-07-02","arxiv_id":"2407.02586","n_code_links":0,"syntology":null},{"paper":"/paper/integrate-the-essence-and-eliminate-the-dross","slug":"integrate-the-essence-and-eliminate-the-dross","title":"Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation","date":"2024-07-02","arxiv_id":"2407.02056","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["WangXinglin/FSC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}],"record_sha256":"85fec9adb790865a3b3f8d2b582a70dd5284ff1465cfc7d315e5eb01406b417a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}