{"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/39","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":39,"pages_in_order":249,"rows_per_page":100,"rows":[3801,3900],"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/38","next":"/method/multi-head-attention/papers/40","papers":[{"paper":null,"slug":"the-nature-of-mathematical-modeling-and","title":"The Nature of Mathematical Modeling and Probabilistic Optimization Engineering in Generative AI","date":"2024-10-24","arxiv_id":"2410.18441","n_code_links":0,"syntology":null},{"paper":null,"slug":"toolflow-boosting-llm-tool-calling-through","title":"ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis","date":"2024-10-24","arxiv_id":"2410.18447","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-players-as-if-they-are-talking","title":"Understanding Players as if They Are Talking to the Game in a Customized Language: A Pilot Study","date":"2024-10-24","arxiv_id":"2410.18605","n_code_links":0,"syntology":null},{"paper":null,"slug":"where-am-i-and-what-will-i-see-an-auto","title":"Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction","date":"2024-10-24","arxiv_id":"2410.18962","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-methodology-for-transformer-ratio","title":"A Methodology for Transformer Ratio Adjustment in Small-Size Rotary Transformers","date":"2024-10-23","arxiv_id":"2410.18217","n_code_links":0,"syntology":null},{"paper":"/paper/alta-compiler-based-analysis-of-transformers","slug":"alta-compiler-based-analysis-of-transformers","title":"ALTA: Compiler-Based Analysis of Transformers","date":"2024-10-23","arxiv_id":"2410.18077","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-deepmind/alta"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-adaptive-framework-for-generating","slug":"an-adaptive-framework-for-generating","title":"An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms","date":"2024-10-23","arxiv_id":"2410.17694","n_code_links":1,"syntology":null},{"paper":null,"slug":"anomaly-resilient-temporal-qos-prediction","title":"Anomaly Resilient Temporal QoS Prediction using Hypergraph Convoluted Transformer Network","date":"2024-10-23","arxiv_id":"2410.17762","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-position-how-rotary-embeddings-shape","title":"Beyond Position: the emergence of wavelet-like properties in Transformers","date":"2024-10-23","arxiv_id":"2410.18067","n_code_links":0,"syntology":null},{"paper":null,"slug":"clr-bench-evaluating-large-language-models-in","title":"CLR-Bench: Evaluating Large Language Models in College-level Reasoning","date":"2024-10-23","arxiv_id":"2410.17558","n_code_links":0,"syntology":null},{"paper":"/paper/differentially-private-learning-needs-better","slug":"differentially-private-learning-needs-better","title":"Differentially Private Learning Needs Better Model Initialization and Self-Distillation","date":"2024-10-23","arxiv_id":"2410.17566","n_code_links":1,"syntology":null},{"paper":"/paper/federated-transformer-multi-party-vertical","slug":"federated-transformer-multi-party-vertical","title":"Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data","date":"2024-10-23","arxiv_id":"2410.17986","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["xtra-computing/fet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fiper-generalizable-factorized-fields-for","title":"FIPER: Generalizable Factorized Features for Robust Low-Level Vision Models","date":"2024-10-23","arxiv_id":"2410.18083","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-pdfs-to-structured-data-utilizing-llm","title":"From PDFs to Structured Data: Utilizing LLM Analysis in Sports Database Management","date":"2024-10-23","arxiv_id":"2410.17619","n_code_links":0,"syntology":null},{"paper":null,"slug":"future-token-prediction-causal-language","title":"Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction","date":"2024-10-23","arxiv_id":"2410.18160","n_code_links":0,"syntology":null},{"paper":null,"slug":"gazelle-an-instruction-dataset-for-arabic","title":"Gazelle: An Instruction Dataset for Arabic Writing Assistance","date":"2024-10-23","arxiv_id":"2410.18163","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-the-domain-adaptation-of-retrieval","title":"Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination","date":"2024-10-23","arxiv_id":"2410.17783","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-neural-app-control","title":"Lightweight Neural App Control","date":"2024-10-23","arxiv_id":"2410.17883","n_code_links":0,"syntology":null},{"paper":null,"slug":"locating-information-in-large-language-models","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","date":"2024-10-23","arxiv_id":"2410.17770","n_code_links":0,"syntology":null},{"paper":"/paper/longrag-a-dual-perspective-retrieval","slug":"longrag-a-dual-perspective-retrieval","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","date":"2024-10-23","arxiv_id":"2410.18050","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":8,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qingfei1/longrag"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mcubert-memory-efficient-bert-inference-on","title":"MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers","date":"2024-10-23","arxiv_id":"2410.17957","n_code_links":0,"syntology":null},{"paper":null,"slug":"milora-efficient-mixture-of-low-rank","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","date":"2024-10-23","arxiv_id":"2410.18035","n_code_links":0,"syntology":null},{"paper":"/paper/multi-scale-feature-reconstruction-network","slug":"multi-scale-feature-reconstruction-network","title":"Multi-scale feature reconstruction network for industrial anomaly detection","date":"2024-10-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/omniflatten-an-end-to-end-gpt-model-for","slug":"omniflatten-an-end-to-end-gpt-model-for","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","date":"2024-10-23","arxiv_id":"2410.17799","n_code_links":1,"syntology":null},{"paper":null,"slug":"simrag-self-improving-retrieval-augmented","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","date":"2024-10-23","arxiv_id":"2410.17952","n_code_links":0,"syntology":null},{"paper":"/paper/tabdpt-scaling-tabular-foundation-models","slug":"tabdpt-scaling-tabular-foundation-models","title":"TabDPT: Scaling Tabular Foundation Models","date":"2024-10-23","arxiv_id":"2410.18164","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["layer6ai-labs/TabDPT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tage-trustworthy-attribute-group-editing-for","title":"TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation","date":"2024-10-23","arxiv_id":"2410.17855","n_code_links":0,"syntology":null},{"paper":"/paper/value-residual-learning-for-alleviating","slug":"value-residual-learning-for-alleviating","title":"Value Residual Learning For Alleviating Attention Concentration In Transformers","date":"2024-10-23","arxiv_id":"2410.17897","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":6,"n_instrument":3,"unverified":3,"pointer_only":1,"phrase":"9 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; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Zcchill/Value-Residual-Learning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"which-client-is-reliable-a-reliable-and","title":"Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering","date":"2024-10-23","arxiv_id":"2410.17484","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bayesian-perspective-on-the-maximum-score","title":"A Bayesian Perspective on the Maximum Score Problem","date":"2024-10-22","arxiv_id":"2410.17153","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-statistical-analysis-of-llms-self","title":"A Statistical Analysis of LLMs' Self-Evaluation Using Proverbs","date":"2024-10-22","arxiv_id":"2410.16640","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-eye-for-an-ai-evaluating-gpt-4o-s-visual","title":"An Eye for an AI: Evaluating GPT-4o's Visual Perception Skills and Geometric Reasoning Skills Using Computer Graphics Questions","date":"2024-10-22","arxiv_id":"2410.16991","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessment-of-transformer-based-encoder","title":"Assessment of Transformer-Based Encoder-Decoder Model for Human-Like Summarization","date":"2024-10-22","arxiv_id":"2410.16842","n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-to-score-conversion-model-based-on","title":"Audio-to-Score Conversion Model Based on Whisper methodology","date":"2024-10-22","arxiv_id":"2410.17209","n_code_links":0,"syntology":null},{"paper":"/paper/automated-spinal-mri-labelling-from-reports","slug":"automated-spinal-mri-labelling-from-reports","title":"Automated Spinal MRI Labelling from Reports Using a Large Language Model","date":"2024-10-22","arxiv_id":"2410.17235","n_code_links":1,"syntology":null},{"paper":"/paper/dhoroni-exploring-bengali-climate-change-and","slug":"dhoroni-exploring-bengali-climate-change-and","title":"Dhoroni: Exploring Bengali Climate Change and Environmental Views with a Multi-Perspective News Dataset and Natural Language Processing","date":"2024-10-22","arxiv_id":"2410.17225","n_code_links":1,"syntology":null},{"paper":"/paper/di-maskdino-a-joint-object-detection-and","slug":"di-maskdino-a-joint-object-detection-and","title":"DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model","date":"2024-10-22","arxiv_id":"2410.16707","n_code_links":1,"syntology":null},{"paper":null,"slug":"distill-synthkg-distilling-knowledge-graph","title":"Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency","date":"2024-10-22","arxiv_id":"2410.16597","n_code_links":0,"syntology":null},{"paper":"/paper/dnahlm-dna-sequence-and-human-language-mixed","slug":"dnahlm-dna-sequence-and-human-language-mixed","title":"DNAHLM -- DNA sequence and Human Language mixed large language Model","date":"2024-10-22","arxiv_id":"2410.16917","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-possibilities-of-ai-powered-legal","slug":"exploring-possibilities-of-ai-powered-legal","title":"Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling","date":"2024-10-22","arxiv_id":"2410.17210","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-transformers-dream-of-electric-flow","title":"Graph Transformers Dream of Electric Flow","date":"2024-10-22","arxiv_id":"2410.16699","n_code_links":0,"syntology":null},{"paper":"/paper/in-context-learning-and-reasoning-for","slug":"in-context-learning-and-reasoning-for","title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","date":"2024-10-22","arxiv_id":"2410.17448","n_code_links":1,"syntology":null},{"paper":null,"slug":"interchangeable-token-embeddings-for","title":"Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence","date":"2024-10-22","arxiv_id":"2410.17161","n_code_links":0,"syntology":null},{"paper":"/paper/lino-advancing-recursive-residual","slug":"lino-advancing-recursive-residual","title":"LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecasting","date":"2024-10-22","arxiv_id":"2410.17159","n_code_links":1,"syntology":null},{"paper":null,"slug":"methods-of-improving-llm-training-stability","title":"Methods of improving LLM training stability","date":"2024-10-22","arxiv_id":"2410.16682","n_code_links":0,"syntology":null},{"paper":"/paper/representation-shattering-in-transformers-a","slug":"representation-shattering-in-transformers-a","title":"Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing","date":"2024-10-22","arxiv_id":"2410.17194","n_code_links":0,"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":null}},{"paper":null,"slug":"scattered-forest-search-smarter-code-space","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","date":"2024-10-22","arxiv_id":"2411.05010","n_code_links":0,"syntology":null},{"paper":null,"slug":"smartrag-jointly-learn-rag-related-tasks-from","title":"SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback","date":"2024-10-22","arxiv_id":"2410.18141","n_code_links":0,"syntology":null},{"paper":"/paper/tracing-the-development-of-the-virtual","slug":"tracing-the-development-of-the-virtual","title":"Tracing the Development of the Virtual Particle Concept Using Semantic Change Detection","date":"2024-10-22","arxiv_id":"2410.16855","n_code_links":1,"syntology":null},{"paper":"/paper/an-efficient-system-for-automatic-map","slug":"an-efficient-system-for-automatic-map","title":"An Efficient System for Automatic Map Storytelling -- A Case Study on Historical Maps","date":"2024-10-21","arxiv_id":"2410.15780","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-explainable-contrastive-based-dilated","title":"An Explainable Contrastive-based Dilated Convolutional Network with Transformer for Pediatric Pneumonia Detection","date":"2024-10-21","arxiv_id":"2410.16143","n_code_links":0,"syntology":null},{"paper":"/paper/arithmetic-transformers-can-length-generalize","slug":"arithmetic-transformers-can-length-generalize","title":"Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count","date":"2024-10-21","arxiv_id":"2410.15787","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-2-4-exploring-v-n-m-sparsity-for","title":"Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs","date":"2024-10-21","arxiv_id":"2410.16135","n_code_links":0,"syntology":null},{"paper":"/paper/building-a-coding-assistant-via-the-retrieval","slug":"building-a-coding-assistant-via-the-retrieval","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","date":"2024-10-21","arxiv_id":"2410.16229","n_code_links":1,"syntology":null},{"paper":"/paper/causalgraph2llm-evaluating-llms-for-causal","slug":"causalgraph2llm-evaluating-llms-for-causal","title":"CausalGraph2LLM: Evaluating LLMs for Causal Queries","date":"2024-10-21","arxiv_id":"2410.15939","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-and-data-augmentation-for","slug":"deep-learning-and-data-augmentation-for","title":"Deep Learning and Data Augmentation for Detecting Self-Admitted Technical Debt","date":"2024-10-21","arxiv_id":"2410.15804","n_code_links":1,"syntology":null},{"paper":"/paper/developing-retrieval-augmented-generation-rag","slug":"developing-retrieval-augmented-generation-rag","title":"Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report","date":"2024-10-21","arxiv_id":"2410.15944","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-transformer-policy","slug":"diffusion-transformer-policy","title":"Diffusion Transformer Policy","date":"2024-10-21","arxiv_id":"2410.15959","n_code_links":1,"syntology":null},{"paper":null,"slug":"disambiguating-monocular-reconstruction-of-3d","title":"Disambiguating Monocular Reconstruction of 3D Clothed Human with Spatial-Temporal Transformer","date":"2024-10-21","arxiv_id":"2410.16337","n_code_links":0,"syntology":null},{"paper":"/paper/domain-adaptive-pre-training-of-self","slug":"domain-adaptive-pre-training-of-self","title":"Domain-Adaptive Pre-training of Self-Supervised Foundation Models for Medical Image Classification in Gastrointestinal Endoscopy","date":"2024-10-21","arxiv_id":"2410.21302","n_code_links":1,"syntology":null},{"paper":null,"slug":"enabling-energy-efficient-deployment-of-large","title":"Enabling Energy-Efficient Deployment of Large Language Models on Memristor Crossbar: A Synergy of Large and Small","date":"2024-10-21","arxiv_id":"2410.15977","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-pretraining-via-active-forgetting","title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models","date":"2024-10-21","arxiv_id":"2410.16168","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalized-probabilistic-attention-mechanism","title":"Generalized Probabilistic Attention Mechanism in Transformers","date":"2024-10-21","arxiv_id":"2410.15578","n_code_links":0,"syntology":null},{"paper":"/paper/generalizing-motion-planners-with-mixture-of","slug":"generalizing-motion-planners-with-mixture-of","title":"Generalizing Motion Planners with Mixture of Experts for Autonomous Driving","date":"2024-10-21","arxiv_id":"2410.15774","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["tsinghua-mars-lab/statetransformer"],"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":"/paper/grefel-geometry-aware-reliable-facial","slug":"grefel-geometry-aware-reliable-facial","title":"GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution","date":"2024-10-21","arxiv_id":"2410.15927","n_code_links":0,"syntology":null},{"paper":null,"slug":"guardians-of-discourse-evaluating-llms-on","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","date":"2024-10-21","arxiv_id":"2410.15623","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-neuron-level-interpretability-with","title":"Improving Neuron-level Interpretability with White-box Language Models","date":"2024-10-21","arxiv_id":"2410.16443","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-body-language-models","title":"Large Body Language Models","date":"2024-10-21","arxiv_id":"2410.16533","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-in-computer-science","slug":"large-language-models-in-computer-science","title":"Large Language Models in Computer Science Education: A Systematic Literature Review","date":"2024-10-21","arxiv_id":"2410.16349","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-retrieval-augmented-generation-for","title":"Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions","date":"2024-10-21","arxiv_id":"2410.15572","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightfusionrec-lightweight-transformers-based","title":"LightFusionRec: Lightweight Transformers-Based Cross-Domain Recommendation Model","date":"2024-10-21","arxiv_id":"2410.15656","n_code_links":0,"syntology":null},{"paper":null,"slug":"modelling-concurrent-rtp-flows-for-end-to-end","title":"Modelling Concurrent RTP Flows for End-to-end Predictions of QoS in Real Time Communications","date":"2024-10-21","arxiv_id":"2410.15846","n_code_links":0,"syntology":null},{"paper":"/paper/natural-galore-accelerating-galore-for-memory","slug":"natural-galore-accelerating-galore-for-memory","title":"Natural GaLore: Accelerating GaLore for memory-efficient LLM Training and Fine-tuning","date":"2024-10-21","arxiv_id":"2410.16029","n_code_links":1,"syntology":null},{"paper":"/paper/on-creating-an-english-thai-code-switched","slug":"on-creating-an-english-thai-code-switched","title":"On Creating an English-Thai Code-switched Machine Translation in Medical Domain","date":"2024-10-21","arxiv_id":"2410.16221","n_code_links":1,"syntology":null},{"paper":null,"slug":"rag4itops-a-supervised-fine-tunable-and","title":"RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance","date":"2024-10-21","arxiv_id":"2410.15805","n_code_links":0,"syntology":null},{"paper":"/paper/reflection-bench-probing-ai-intelligence-with","slug":"reflection-bench-probing-ai-intelligence-with","title":"Reflection-Bench: probing AI intelligence with reflection","date":"2024-10-21","arxiv_id":"2410.16270","n_code_links":1,"syntology":null},{"paper":"/paper/seislm-a-foundation-model-for-seismic","slug":"seislm-a-foundation-model-for-seismic","title":"SeisLM: a Foundation Model for Seismic Waveforms","date":"2024-10-21","arxiv_id":"2410.15765","n_code_links":1,"syntology":null},{"paper":null,"slug":"students-rather-than-experts-a-new-ai-for","title":"Students Rather Than Experts: A New AI For Education Pipeline To Model More Human-Like And Personalised Early Adolescences","date":"2024-10-21","arxiv_id":"2410.15701","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-reliable-offline-personal-ai","title":"Towards a Reliable Offline Personal AI Assistant for Long Duration Spaceflight","date":"2024-10-21","arxiv_id":"2410.16397","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-gpt-models-for-qualitative-and","title":"Using GPT Models for Qualitative and Quantitative News Analytics in the 2024 US Presidental Election Process","date":"2024-10-21","arxiv_id":"2410.15884","n_code_links":0,"syntology":null},{"paper":null,"slug":"vimoe-an-empirical-study-of-designing-vision","title":"ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts","date":"2024-10-21","arxiv_id":"2410.15732","n_code_links":0,"syntology":null},{"paper":null,"slug":"weighted-diversified-sampling-for-efficient","title":"Weighted Diversified Sampling for Efficient Data-Driven Single-Cell Gene-Gene Interaction Discovery","date":"2024-10-21","arxiv_id":"2410.15616","n_code_links":0,"syntology":null},{"paper":"/paper/who-s-who-large-language-models-meet","slug":"who-s-who-large-language-models-meet","title":"Who's Who: Large Language Models Meet Knowledge Conflicts in Practice","date":"2024-10-21","arxiv_id":"2410.15737","n_code_links":1,"syntology":null},{"paper":null,"slug":"yolo11-and-vision-transformers-based-3d-pose","title":"YOLO11 and Vision Transformers based 3D Pose Estimation of Immature Green Fruits in Commercial Apple Orchards for Robotic Thinning","date":"2024-10-21","arxiv_id":"2410.19846","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-gasoline-consumption-forecasting-a","title":"Advancing Gasoline Consumption Forecasting: A Novel Hybrid Model Integrating Transformers, LSTM, and CNN","date":"2024-10-20","arxiv_id":"2410.16336","n_code_links":0,"syntology":null},{"paper":"/paper/back-to-school-translation-using-grammar","slug":"back-to-school-translation-using-grammar","title":"Back to School: Translation Using Grammar Books","date":"2024-10-20","arxiv_id":"2410.15263","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 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) · 4 unverified","official":{"repos":["jonathanhus/back-to-school"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/brief-bridging-retrieval-and-inference-for","slug":"brief-bridging-retrieval-and-inference-for","title":"BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression","date":"2024-10-20","arxiv_id":"2410.15277","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-lstm-gru-and","title":"Comparative Analysis of LSTM, GRU, and Transformer Models for Stock Price Prediction","date":"2024-10-20","arxiv_id":"2411.05790","n_code_links":0,"syntology":null},{"paper":"/paper/contextual-augmented-multi-model-programming","slug":"contextual-augmented-multi-model-programming","title":"Contextual Augmented Multi-Model Programming (CAMP): A Hybrid Local-Cloud Copilot Framework","date":"2024-10-20","arxiv_id":"2410.15285","n_code_links":1,"syntology":null},{"paper":null,"slug":"contregen-context-driven-tree-structured","title":"ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation","date":"2024-10-20","arxiv_id":"2410.15511","n_code_links":0,"syntology":null},{"paper":"/paper/do-rag-systems-cover-what-matters-evaluating","slug":"do-rag-systems-cover-what-matters-evaluating","title":"Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage","date":"2024-10-20","arxiv_id":"2410.15531","n_code_links":1,"syntology":null},{"paper":"/paper/does-chatgpt-have-a-poetic-style","slug":"does-chatgpt-have-a-poetic-style","title":"Does ChatGPT Have a Poetic Style?","date":"2024-10-20","arxiv_id":"2410.15299","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-consistencies-in-llm-responses","title":"Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering","date":"2024-10-20","arxiv_id":"2410.15440","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-social-desirability-response-bias","title":"Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations","date":"2024-10-20","arxiv_id":"2410.15442","n_code_links":0,"syntology":null},{"paper":null,"slug":"ltpnet-integration-of-deep-learning-and","title":"LTPNet Integration of Deep Learning and Environmental Decision Support Systems for Renewable Energy Demand Forecasting","date":"2024-10-20","arxiv_id":"2410.15286","n_code_links":0,"syntology":null},{"paper":null,"slug":"mmcs-a-multimodal-medical-diagnosis-system","title":"MMDS: A Multimodal Medical Diagnosis System Integrating Image Analysis and Knowledge-based Departmental Consultation","date":"2024-10-20","arxiv_id":"2410.15403","n_code_links":0,"syntology":null},{"paper":null,"slug":"sdp4bit-toward-4-bit-communication","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","date":"2024-10-20","arxiv_id":"2410.15526","n_code_links":0,"syntology":null},{"paper":"/paper/sea-state-exchange-attention-for-high","slug":"sea-state-exchange-attention-for-high","title":"SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers","date":"2024-10-20","arxiv_id":"2410.15495","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["parsaesmati/sea"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":7,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"training-language-models-to-critique-with","title":"Training Language Models to Critique With Multi-agent Feedback","date":"2024-10-20","arxiv_id":"2410.15287","n_code_links":0,"syntology":null},{"paper":null,"slug":"unveiling-and-consulting-core-experts-in","title":"Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs","date":"2024-10-20","arxiv_id":"2410.15438","n_code_links":0,"syntology":null}],"record_sha256":"003283d8538bc609e30374edfd351fac725b77dc809136f86c317eaec413be51","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}