{"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/52","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":52,"pages_in_order":249,"rows_per_page":100,"rows":[5101,5200],"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/51","next":"/method/multi-head-attention/papers/53","papers":[{"paper":"/paper/prformer-pyramidal-recurrent-transformer-for","slug":"prformer-pyramidal-recurrent-transformer-for","title":"PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting","date":"2024-08-20","arxiv_id":"2408.10483","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":["usualheart/prformer"],"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/quantum-inverse-contextual-vision","slug":"quantum-inverse-contextual-vision","title":"Quantum Inverse Contextual Vision Transformers (Q-ICVT): A New Frontier in 3D Object Detection for AVs","date":"2024-08-20","arxiv_id":"2408.11207","n_code_links":1,"syntology":null},{"paper":null,"slug":"reading-with-intent","title":"Reading with Intent","date":"2024-08-20","arxiv_id":"2408.11189","n_code_links":0,"syntology":null},{"paper":null,"slug":"reconciling-methodological-paradigms","title":"Reconciling Methodological Paradigms: Employing Large Language Models as Novice Qualitative Research Assistants in Talent Management Research","date":"2024-08-20","arxiv_id":"2408.11043","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-verilogeval-newer-llms-in-context","slug":"revisiting-verilogeval-newer-llms-in-context","title":"Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation","date":"2024-08-20","arxiv_id":"2408.11053","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":["nvlabs/verilog-eval"],"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/soda-eval-open-domain-dialogue-evaluation-in","slug":"soda-eval-open-domain-dialogue-evaluation-in","title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","date":"2024-08-20","arxiv_id":"2408.10902","n_code_links":1,"syntology":null},{"paper":null,"slug":"target-prompt-online-graph-collaborative","title":"GACL: Graph Attention Collaborative Learning for Temporal QoS Prediction","date":"2024-08-20","arxiv_id":"2408.10555","n_code_links":0,"syntology":null},{"paper":null,"slug":"towardseffective-teaching-assistants-from","title":"Towardseffective teaching assistants: From intent-based chatbots to LLM-poweredteachingassistants","date":"2024-08-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tracing-privacy-leakage-of-language-models-to","title":"Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions","date":"2024-08-20","arxiv_id":"2408.10468","n_code_links":0,"syntology":null},{"paper":"/paper/uie-unfold-deep-unfolding-network-with-color","slug":"uie-unfold-deep-unfolding-network-with-color","title":"UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement","date":"2024-08-20","arxiv_id":"2408.10653","n_code_links":1,"syntology":null},{"paper":"/paper/while-github-copilot-excels-at-coding-does-it","slug":"while-github-copilot-excels-at-coding-does-it","title":"Security Attacks on LLM-based Code Completion Tools","date":"2024-08-20","arxiv_id":"2408.11006","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-strategy-to-combine-1stgen-transformers-and","title":"A Strategy to Combine 1stGen Transformers and Open LLMs for Automatic Text Classification","date":"2024-08-19","arxiv_id":"2408.09629","n_code_links":0,"syntology":null},{"paper":"/paper/acquiring-bidirectionality-via-large-and","slug":"acquiring-bidirectionality-via-large-and","title":"Acquiring Bidirectionality via Large and Small Language Models","date":"2024-08-19","arxiv_id":"2408.09640","n_code_links":1,"syntology":null},{"paper":null,"slug":"active-learning-for-identifying-disaster","title":"Active Learning for Identifying Disaster-Related Tweets: A Comparison with Keyword Filtering and Generic Fine-Tuning","date":"2024-08-19","arxiv_id":"2408.09914","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-llms-for-translating-classical","title":"Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving","date":"2024-08-19","arxiv_id":"2408.09945","n_code_links":0,"syntology":null},{"paper":null,"slug":"carbon-footprint-accounting-driven-by-large","title":"Carbon Footprint Accounting Driven by Large Language Models and Retrieval-augmented Generation","date":"2024-08-19","arxiv_id":"2408.09713","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-cloud-collaborative-motion-planning-for","title":"Edge-Cloud Collaborative Motion Planning for Autonomous Driving with Large Language Models","date":"2024-08-19","arxiv_id":"2408.09972","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-lifelong-model-editing-with","slug":"enhance-lifelong-model-editing-with","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","date":"2024-08-19","arxiv_id":"2408.11869","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-document-retrieval-with-topic","title":"Enhanced document retrieval with topic embeddings","date":"2024-08-19","arxiv_id":"2408.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-dreamer-training-a-high-quality","title":"Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data","date":"2024-08-19","arxiv_id":"2408.10119","n_code_links":0,"syntology":null},{"paper":"/paper/goldfish-monolingual-language-models-for-350","slug":"goldfish-monolingual-language-models-for-350","title":"Goldfish: Monolingual Language Models for 350 Languages","date":"2024-08-19","arxiv_id":"2408.10441","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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":{"repos":["tylerachang/goldfish"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-augmented-reinforcement-learning-with","title":"GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching","date":"2024-08-19","arxiv_id":"2408.10286","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-precise-affordances-from-egocentric","title":"Learning Precise Affordances from Egocentric Videos for Robotic Manipulation","date":"2024-08-19","arxiv_id":"2408.10123","n_code_links":0,"syntology":null},{"paper":"/paper/legalbench-rag-a-benchmark-for-retrieval","slug":"legalbench-rag-a-benchmark-for-retrieval","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","date":"2024-08-19","arxiv_id":"2408.10343","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["zeroentropy-cc/legalbenchrag"],"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":["official"]}}},{"paper":null,"slug":"lightweather-harnessing-absolute-positional","title":"LightWeather: Harnessing Absolute Positional Encoding to Efficient and Scalable Global Weather Forecasting","date":"2024-08-19","arxiv_id":"2408.09695","n_code_links":0,"syntology":null},{"paper":null,"slug":"modegpt-modular-decomposition-for-large","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","date":"2024-08-19","arxiv_id":"2408.09632","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-representation-learning-for-image","title":"Multi-Scale Representation Learning for Image Restoration with State-Space Model","date":"2024-08-19","arxiv_id":"2408.10145","n_code_links":0,"syntology":null},{"paper":"/paper/pedestrian-attribute-recognition-a-new","slug":"pedestrian-attribute-recognition-a-new","title":"Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework","date":"2024-08-19","arxiv_id":"2408.09720","n_code_links":2,"syntology":null},{"paper":null,"slug":"propagating-the-prior-from-shallow-to-deep","title":"Propagating the prior from shallow to deep with a pre-trained velocity-model Generative Transformer network","date":"2024-08-19","arxiv_id":"2408.09767","n_code_links":0,"syntology":null},{"paper":"/paper/r2gencsr-retrieving-context-samples-for-large","slug":"r2gencsr-retrieving-context-samples-for-large","title":"R2GenCSR: Retrieving Context Samples for Large Language Model based X-ray Medical Report Generation","date":"2024-08-19","arxiv_id":"2408.09743","n_code_links":1,"syntology":null},{"paper":null,"slug":"rhyme-aware-chinese-lyric-generator-based-on","title":"Rhyme-aware Chinese lyric generator based on GPT","date":"2024-08-19","arxiv_id":"2408.10130","n_code_links":0,"syntology":null},{"paper":"/paper/sam-unet-enhancing-zero-shot-segmentation-of","slug":"sam-unet-enhancing-zero-shot-segmentation-of","title":"SAM-UNet:Enhancing Zero-Shot Segmentation of SAM for Universal Medical Images","date":"2024-08-19","arxiv_id":"2408.09886","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-directed-turing-test-for-large-language","title":"Self-Directed Turing Test for Large Language Models","date":"2024-08-19","arxiv_id":"2408.09853","n_code_links":0,"syntology":null},{"paper":null,"slug":"tba-faster-large-language-model-training","title":"SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training","date":"2024-08-19","arxiv_id":"2408.10013","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-large-scale-spiking-neural-networks-a","title":"Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions","date":"2024-08-19","arxiv_id":"2409.02111","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-to-ssms-distilling-quadratic","slug":"transformers-to-ssms-distilling-quadratic","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","date":"2024-08-19","arxiv_id":"2408.10189","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-framework-for-interpretable","title":"A Unified Framework for Interpretable Transformers Using PDEs and Information Theory","date":"2024-08-18","arxiv_id":"2408.09523","n_code_links":0,"syntology":null},{"paper":null,"slug":"agentic-retrieval-augmented-generation-for","title":"Agentic Retrieval-Augmented Generation for Time Series Analysis","date":"2024-08-18","arxiv_id":"2408.14484","n_code_links":0,"syntology":null},{"paper":null,"slug":"fd2talk-towards-generalized-talking-head","title":"FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model","date":"2024-08-18","arxiv_id":"2408.09384","n_code_links":0,"syntology":null},{"paper":null,"slug":"ou-covit-copula-enhanced-bi-channel-multi","title":"OU-CoViT: Copula-Enhanced Bi-Channel Multi-Task Vision Transformers with Dual Adaptation for OU-UWF Images","date":"2024-08-18","arxiv_id":"2408.09395","n_code_links":0,"syntology":null},{"paper":"/paper/out-of-distribution-generalization-via-1","slug":"out-of-distribution-generalization-via-1","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","date":"2024-08-18","arxiv_id":"2408.09503","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["jiajunsong629/ood-generalization-via-composition"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"conversum-a-contrastive-learning-based","title":"ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents","date":"2024-08-17","arxiv_id":"2408.09273","n_code_links":0,"syntology":null},{"paper":"/paper/cross-species-data-integration-for-enhanced","slug":"cross-species-data-integration-for-enhanced","title":"Cross-Species Data Integration for Enhanced Layer Segmentation in Kidney Pathology","date":"2024-08-17","arxiv_id":"2408.09278","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybridocc-nerf-enhanced-transformer-based","title":"HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction","date":"2024-08-17","arxiv_id":"2408.09104","n_code_links":0,"syntology":null},{"paper":"/paper/linear-attention-is-enough-in-spatial","slug":"linear-attention-is-enough-in-spatial","title":"Linear Attention is Enough in Spatial-Temporal Forecasting","date":"2024-08-17","arxiv_id":"2408.09158","n_code_links":1,"syntology":null},{"paper":null,"slug":"maskbev-towards-a-unified-framework-for-bev","title":"MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation","date":"2024-08-17","arxiv_id":"2408.09122","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-preservice-teachers","title":"Sentiment analysis of preservice teachers' reflections using a large language model","date":"2024-08-17","arxiv_id":"2408.11862","n_code_links":0,"syntology":null},{"paper":null,"slug":"tablebench-a-comprehensive-and-complex","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","date":"2024-08-17","arxiv_id":"2408.09174","n_code_links":0,"syntology":null},{"paper":"/paper/tc-rag-turing-complete-rag-s-case-study-on","slug":"tc-rag-turing-complete-rag-s-case-study-on","title":"TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems","date":"2024-08-17","arxiv_id":"2408.09199","n_code_links":2,"syntology":null},{"paper":null,"slug":"unraveling-text-generation-in-llms-a","title":"Unraveling Text Generation in LLMs: A Stochastic Differential Equation Approach","date":"2024-08-17","arxiv_id":"2408.11863","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mean-field-ansatz-for-zero-shot-weight","title":"A Mean Field Ansatz for Zero-Shot Weight Transfer","date":"2024-08-16","arxiv_id":"2408.08681","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-approach-to-classify-power-quality","title":"A Novel Approach to Classify Power Quality Signals Using Vision Transformers","date":"2024-08-16","arxiv_id":"2409.00025","n_code_links":0,"syntology":null},{"paper":"/paper/biolay-ak-ss-at-biolaysumm-domain-adaptation","slug":"biolay-ak-ss-at-biolaysumm-domain-adaptation","title":"BioLay_AK_SS at BioLaySumm: Domain Adaptation by Two-Stage Fine-Tuning of Large Language Models used for Biomedical Lay Summary Generation","date":"2024-08-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"blockchain-enabled-accountability-in-data","title":"Blockchain-Enabled Accountability in Data Supply Chain: A Data Bill of Materials Approach","date":"2024-08-16","arxiv_id":"2408.08536","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-improve-the","slug":"can-large-language-models-improve-the","title":"Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?","date":"2024-08-16","arxiv_id":"2408.08685","n_code_links":1,"syntology":null},{"paper":null,"slug":"cikmar-a-dual-encoder-approach-to-prompt","title":"CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems","date":"2024-08-16","arxiv_id":"2408.08805","n_code_links":0,"syntology":null},{"paper":"/paper/communitykg-rag-leveraging-community","slug":"communitykg-rag-leveraging-community","title":"CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checking","date":"2024-08-16","arxiv_id":"2408.08535","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-generative-models","title":"Comparative Analysis of Generative Models: Enhancing Image Synthesis with VAEs, GANs, and Stable Diffusion","date":"2024-08-16","arxiv_id":"2408.08751","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-llms-for-autonomous-spacecraft","slug":"fine-tuning-llms-for-autonomous-spacecraft","title":"Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program","date":"2024-08-16","arxiv_id":"2408.08676","n_code_links":1,"syntology":null},{"paper":null,"slug":"geotransformer-enhancing-urban-forecasting","title":"GeoTransformer: Enhancing Urban Forecasting with Dependency Retrieval and Geospatial Attention","date":"2024-08-16","arxiv_id":"2408.08852","n_code_links":0,"syntology":null},{"paper":null,"slug":"hycot-hyperspectral-compression-transformer","title":"HyCoT: A Transformer-Based Autoencoder for Hyperspectral Image Compression","date":"2024-08-16","arxiv_id":"2408.08700","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-vte-identification-through-language","title":"Improving VTE Identification through Language Models from Radiology Reports: A Comparative Study of Mamba, Phi-3 Mini, and BERT","date":"2024-08-16","arxiv_id":"2408.09043","n_code_links":0,"syntology":null},{"paper":"/paper/mat-sed-amasked-audio-transformer-with-masked","slug":"mat-sed-amasked-audio-transformer-with-masked","title":"MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection","date":"2024-08-16","arxiv_id":"2408.08673","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-knowledge-for-retrieval-augmented-large","title":"Meta Knowledge for Retrieval Augmented Large Language Models","date":"2024-08-16","arxiv_id":"2408.09017","n_code_links":0,"syntology":null},{"paper":"/paper/opencity-open-spatio-temporal-foundation","slug":"opencity-open-spatio-temporal-foundation","title":"OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction","date":"2024-08-16","arxiv_id":"2408.10269","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["hkuds/opencity"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"persona-is-a-double-edged-sword-enhancing-the","title":"Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks","date":"2024-08-16","arxiv_id":"2408.08631","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-the-effectiveness-of-student","title":"Quantifying the Effectiveness of Student Organization Activities using Natural Language Processing","date":"2024-08-16","arxiv_id":"2408.08694","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-personalized-compression","title":"Research on Personalized Compression Algorithm for Pre-trained Models Based on Homomorphic Entropy Increase","date":"2024-08-16","arxiv_id":"2408.08684","n_code_links":0,"syntology":null},{"paper":"/paper/se-sgformer-a-self-explainable-signed-graph","slug":"se-sgformer-a-self-explainable-signed-graph","title":"Self-Explainable Graph Transformer for Link Sign Prediction","date":"2024-08-16","arxiv_id":"2408.08754","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":3,"n_instrument":0,"unverified":6,"pointer_only":9,"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) · 6 unverified","official":{"repos":["liule66/SE-SGformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/see-what-llms-cannot-answer-a-self-challenge","slug":"see-what-llms-cannot-answer-a-self-challenge","title":"See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses","date":"2024-08-16","arxiv_id":"2408.08978","n_code_links":1,"syntology":null},{"paper":"/paper/tamer-tree-aware-transformer-for-handwritten","slug":"tamer-tree-aware-transformer-for-handwritten","title":"TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition","date":"2024-08-16","arxiv_id":"2408.08578","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"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":["qingzhenduyu/tamer"],"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":"/paper/task-aware-dynamic-transformer-for-efficient","slug":"task-aware-dynamic-transformer-for-efficient","title":"Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution","date":"2024-08-16","arxiv_id":"2408.08736","n_code_links":1,"syntology":null},{"paper":"/paper/the-fellowship-of-the-llms-multi-agent","slug":"the-fellowship-of-the-llms-multi-agent","title":"The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation","date":"2024-08-16","arxiv_id":"2408.08688","n_code_links":1,"syntology":null},{"paper":null,"slug":"vera-validation-and-evaluation-of-retrieval","title":"VERA: Validation and Evaluation of Retrieval-Augmented Systems","date":"2024-08-16","arxiv_id":"2409.03759","n_code_links":0,"syntology":null},{"paper":"/paper/arablegaleval-a-multitask-benchmark-for","slug":"arablegaleval-a-multitask-benchmark-for","title":"ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models","date":"2024-08-15","arxiv_id":"2408.07983","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-the-capabilities-of-large","title":"Benchmarking the Capabilities of Large Language Models in Transportation System Engineering: Accuracy, Consistency, and Reasoning Behaviors","date":"2024-08-15","arxiv_id":"2408.08302","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-uniform-query-distribution-key-driven","slug":"beyond-uniform-query-distribution-key-driven","title":"Beyond Uniform Query Distribution: Key-Driven Grouped Query Attention","date":"2024-08-15","arxiv_id":"2408.08454","n_code_links":1,"syntology":null},{"paper":"/paper/computer-vision-model-compression-techniques","slug":"computer-vision-model-compression-techniques","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","date":"2024-08-15","arxiv_id":"2408.08250","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-data-sketches-and-fine-tuning-for","title":"Distributional Drift Detection in Medical Imaging with Sketching and Fine-Tuned Transformer","date":"2024-08-15","arxiv_id":"2408.08456","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-validity-of-word-level","slug":"evaluating-the-validity-of-word-level","title":"Evaluating the Validity of Word-level Adversarial Attacks with Large Language Models","date":"2024-08-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fusechat-knowledge-fusion-of-chat-models-1","slug":"fusechat-knowledge-fusion-of-chat-models-1","title":"FuseChat: Knowledge Fusion of Chat Models","date":"2024-08-15","arxiv_id":"2408.07990","n_code_links":3,"syntology":null},{"paper":"/paper/graph-retrieval-augmented-generation-a-survey","slug":"graph-retrieval-augmented-generation-a-survey","title":"Graph Retrieval-Augmented Generation: A Survey","date":"2024-08-15","arxiv_id":"2408.08921","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-web-crawled-data-for-high-quality","slug":"leveraging-web-crawled-data-for-high-quality","title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning","date":"2024-08-15","arxiv_id":"2408.08003","n_code_links":1,"syntology":null},{"paper":"/paper/mag-sql-multi-agent-generative-approach-with","slug":"mag-sql-multi-agent-generative-approach-with","title":"MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL","date":"2024-08-15","arxiv_id":"2408.07930","n_code_links":1,"syntology":{"ran":21,"of":25,"n_ran_checked":19,"n_instrument":2,"unverified":4,"pointer_only":4,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 3 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["LancelotXWX/MAG-SQL"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mambavt-spatio-temporal-contextual-modeling","slug":"mambavt-spatio-temporal-contextual-modeling","title":"MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking","date":"2024-08-15","arxiv_id":"2408.07889","n_code_links":1,"syntology":null},{"paper":"/paper/mol2lang-vlm-vision-and-text-guided","slug":"mol2lang-vlm-vision-and-text-guided","title":"Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion","date":"2024-08-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"plan-with-code-comparing-approaches-for","title":"Plan with Code: Comparing approaches for robust NL to DSL generation","date":"2024-08-15","arxiv_id":"2408.08335","n_code_links":0,"syntology":null},{"paper":null,"slug":"polaris-open-ended-interactive-robotic","title":"Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models","date":"2024-08-15","arxiv_id":"2408.07975","n_code_links":0,"syntology":null},{"paper":"/paper/pqv-mobile-a-combined-pruning-and","slug":"pqv-mobile-a-combined-pruning-and","title":"PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile Applications","date":"2024-08-15","arxiv_id":"2408.08437","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-lung-cancer-patient-prognosis-with","title":"Predicting Lung Cancer Patient Prognosis with Large Language Models","date":"2024-08-15","arxiv_id":"2408.07971","n_code_links":0,"syntology":null},{"paper":"/paper/ragchecker-a-fine-grained-framework-for","slug":"ragchecker-a-fine-grained-framework-for","title":"RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation","date":"2024-08-15","arxiv_id":"2408.08067","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["amazon-science/ragchecker"],"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":"/paper/unsupervised-part-discovery-via-dual","slug":"unsupervised-part-discovery-via-dual","title":"Unsupervised Part Discovery via Dual Representation Alignment","date":"2024-08-15","arxiv_id":"2408.08108","n_code_links":1,"syntology":null},{"paper":null,"slug":"your-turn-real-world-turning-angle-estimation","title":"Your Turn: At Home Turning Angle Estimation for Parkinson's Disease Severity Assessment","date":"2024-08-15","arxiv_id":"2408.08182","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-nested-graph-reinforcement-learning-based","title":"A Nested Graph Reinforcement Learning-based Decision-making Strategy for Eco-platooning","date":"2024-08-14","arxiv_id":"2408.07578","n_code_links":0,"syntology":null},{"paper":"/paper/a-spitting-image-modular-superpixel","slug":"a-spitting-image-modular-superpixel","title":"A Spitting Image: Modular Superpixel Tokenization in Vision Transformers","date":"2024-08-14","arxiv_id":"2408.07680","n_code_links":1,"syntology":{"ran":16,"of":18,"n_ran_checked":16,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dsb-ifi/spit"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"codemirage-hallucinations-in-code-generated","title":"CodeMirage: Hallucinations in Code Generated by Large Language Models","date":"2024-08-14","arxiv_id":"2408.08333","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-aware-early-fusion-with-stage-divided","title":"Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation","date":"2024-08-14","arxiv_id":"2408.07539","n_code_links":0,"syntology":null},{"paper":"/paper/datavist5-a-pre-trained-language-model-for","slug":"datavist5-a-pre-trained-language-model-for","title":"DataVisT5: A Pre-trained Language Model for Jointly Understanding Text and Data Visualization","date":"2024-08-14","arxiv_id":"2408.07401","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-semantic-centric-video-based","title":"End-to-end Semantic-centric Video-based Multimodal Affective Computing","date":"2024-08-14","arxiv_id":"2408.07694","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-visual-question-answering-through-1","title":"Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion","date":"2024-08-14","arxiv_id":"2408.07303","n_code_links":0,"syntology":null}],"record_sha256":"d660ff8674f2a855aeb937595b7843aef519981143d55a539faeceb47c63996d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}