{"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/24","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":24,"pages_in_order":249,"rows_per_page":100,"rows":[2301,2400],"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/23","next":"/method/multi-head-attention/papers/25","papers":[{"paper":null,"slug":"harnessing-generative-pre-trained-transformer","title":"Harnessing Generative Pre-Trained Transformer for Datacenter Packet Trace Generation","date":"2025-01-21","arxiv_id":"2501.12033","n_code_links":0,"syntology":null},{"paper":"/paper/med-r-2-crafting-trustworthy-llm-physicians","slug":"med-r-2-crafting-trustworthy-llm-physicians","title":"Med-R$^2$: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine","date":"2025-01-21","arxiv_id":"2501.11885","n_code_links":1,"syntology":null},{"paper":"/paper/network-informed-prompt-engineering-against","slug":"network-informed-prompt-engineering-against","title":"Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class Imbalance","date":"2025-01-21","arxiv_id":"2501.11849","n_code_links":1,"syntology":null},{"paper":"/paper/panoramic-interests-stylistic-content-aware-1","slug":"panoramic-interests-stylistic-content-aware-1","title":"Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation","date":"2025-01-21","arxiv_id":"2501.11900","n_code_links":1,"syntology":null},{"paper":"/paper/towards-accurate-unified-anomaly-segmentation","slug":"towards-accurate-unified-anomaly-segmentation","title":"Towards Accurate Unified Anomaly Segmentation","date":"2025-01-21","arxiv_id":"2501.12295","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-language-models-for-automated-chest-x","title":"Vision-Language Models for Automated Chest X-ray Interpretation: Leveraging ViT and GPT-2","date":"2025-01-21","arxiv_id":"2501.12356","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-parameters-identification-for","title":"Adaptive parameters identification for nonlinear dynamics using deep permutation invariant networks","date":"2025-01-20","arxiv_id":"2501.11350","n_code_links":0,"syntology":null},{"paper":null,"slug":"dlinear-based-prediction-of-remaining-useful","title":"DLinear-based Prediction of Remaining Useful Life of Lithium-Ion Batteries: Feature Engineering through Explainable Artificial Intelligence","date":"2025-01-20","arxiv_id":"2501.11542","n_code_links":0,"syntology":null},{"paper":"/paper/early-evidence-of-how-llms-outperform","slug":"early-evidence-of-how-llms-outperform","title":"Early evidence of how LLMs outperform traditional systems on OCR/HTR tasks for historical records","date":"2025-01-20","arxiv_id":"2501.11623","n_code_links":1,"syntology":null},{"paper":null,"slug":"explainable-lane-change-prediction-for-near","title":"Explainable Lane Change Prediction for Near-Crash Scenarios Using Knowledge Graph Embeddings and Retrieval Augmented Generation","date":"2025-01-20","arxiv_id":"2501.11560","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-enabled-blockage-prediction-for","title":"Generative AI-enabled Blockage Prediction for Robust Dual-Band mmWave Communication","date":"2025-01-20","arxiv_id":"2501.11763","n_code_links":0,"syntology":null},{"paper":"/paper/glinthawk-a-two-tiered-architecture-for-high","slug":"glinthawk-a-two-tiered-architecture-for-high","title":"Glinthawk: A Two-Tiered Architecture for Offline LLM Inference","date":"2025-01-20","arxiv_id":"2501.11779","n_code_links":1,"syntology":null},{"paper":null,"slug":"keir-ecir-2025-the-second-workshop-on","title":"KEIR @ ECIR 2025: The Second Workshop on Knowledge-Enhanced Information Retrieval","date":"2025-01-20","arxiv_id":"2501.11499","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-contextual-reinforcement-framework-for","title":"Neural Contextual Reinforcement Framework for Logical Structure Language Generation","date":"2025-01-20","arxiv_id":"2501.11417","n_code_links":0,"syntology":null},{"paper":"/paper/pike-rag-specialized-knowledge-and-rationale","slug":"pike-rag-specialized-knowledge-and-rationale","title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","date":"2025-01-20","arxiv_id":"2501.11551","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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/pike-rag"],"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/poison-rag-adversarial-data-poisoning-attacks","slug":"poison-rag-adversarial-data-poisoning-attacks","title":"Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems","date":"2025-01-20","arxiv_id":"2501.11759","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthetic-data-can-mislead-evaluations","title":"Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection","date":"2025-01-20","arxiv_id":"2501.11786","n_code_links":0,"syntology":null},{"paper":null,"slug":"trustformer-a-trusted-federated-transformer","title":"Trustformer: A Trusted Federated Transformer","date":"2025-01-20","arxiv_id":"2501.11706","n_code_links":0,"syntology":null},{"paper":null,"slug":"tutorllm-customizing-learning-recommendations","title":"TutorLLM: Customizing Learning Recommendations with Knowledge Tracing and Retrieval-Augmented Generation","date":"2025-01-20","arxiv_id":"2502.15709","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-reasoning-towards-unified","title":"Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective","date":"2025-01-19","arxiv_id":"2501.11110","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-arabic-text-to-puzzles-llm-driven","title":"From Arabic Text to Puzzles: LLM-Driven Development of Arabic Educational Crosswords","date":"2025-01-19","arxiv_id":"2501.11035","n_code_links":0,"syntology":null},{"paper":"/paper/a-cnn-transformer-for-classification-of","slug":"a-cnn-transformer-for-classification-of","title":"A CNN-Transformer for Classification of Longitudinal 3D MRI Images -- A Case Study on Hepatocellular Carcinoma Prediction","date":"2025-01-18","arxiv_id":"2501.10733","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-trend-fusion-module-for-traffic-flow","slug":"dynamic-trend-fusion-module-for-traffic-flow","title":"Dynamic Trend Fusion Module for Traffic Flow Prediction","date":"2025-01-18","arxiv_id":"2501.10796","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-auto-labeling-of-large-scale","title":"Efficient Auto-Labeling of Large-Scale Poultry Datasets (ALPD) Using Semi-Supervised Models, Active Learning, and Prompt-then-Detect Approach","date":"2025-01-18","arxiv_id":"2501.10809","n_code_links":0,"syntology":null},{"paper":null,"slug":"fsmoe-a-flexible-and-scalable-training-system","title":"FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models","date":"2025-01-18","arxiv_id":"2501.10714","n_code_links":0,"syntology":null},{"paper":null,"slug":"gec-rag-improving-generative-error-correction","title":"GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems","date":"2025-01-18","arxiv_id":"2501.10734","n_code_links":0,"syntology":null},{"paper":"/paper/ld-detr-loop-decoder-detection-transformer","slug":"ld-detr-loop-decoder-detection-transformer","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","date":"2025-01-18","arxiv_id":"2501.10787","n_code_links":1,"syntology":null},{"paper":null,"slug":"simulation-of-hypergraph-algorithms-with","title":"Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers","date":"2025-01-18","arxiv_id":"2501.10688","n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-rag-expanding-mllm-visual-knowledge","title":"Visual RAG: Expanding MLLM visual knowledge without fine-tuning","date":"2025-01-18","arxiv_id":"2501.10834","n_code_links":0,"syntology":null},{"paper":"/paper/4bit-quantization-in-vector-embedding-for-rag","slug":"4bit-quantization-in-vector-embedding-for-rag","title":"4bit-Quantization in Vector-Embedding for RAG","date":"2025-01-17","arxiv_id":"2501.10534","n_code_links":1,"syntology":null},{"paper":null,"slug":"airrag-activating-intrinsic-reasoning-for","title":"AirRAG: Activating Intrinsic Reasoning for Retrieval Augmented Generation via Tree-based Search","date":"2025-01-17","arxiv_id":"2501.10053","n_code_links":0,"syntology":null},{"paper":null,"slug":"bbpos-bert-based-part-of-speech-tagging-for","title":"BBPOS: BERT-based Part-of-Speech Tagging for Uzbek","date":"2025-01-17","arxiv_id":"2501.10107","n_code_links":0,"syntology":null},{"paper":"/paper/bias-in-decision-making-for-ai-s-ethical","slug":"bias-in-decision-making-for-ai-s-ethical","title":"Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude","date":"2025-01-17","arxiv_id":"2501.10484","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-the-reliability-in-machine-learning","title":"Enhancing the Reliability in Machine Learning for Gravitational Wave Parameter Estimation with Attention-Based Models","date":"2025-01-17","arxiv_id":"2501.10486","n_code_links":0,"syntology":null},{"paper":"/paper/filo-zero-few-shot-anomaly-detection-by-fused","slug":"filo-zero-few-shot-anomaly-detection-by-fused","title":"FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization","date":"2025-01-17","arxiv_id":"2501.10067","n_code_links":1,"syntology":null},{"paper":"/paper/pasa-an-llm-agent-for-comprehensive-academic","slug":"pasa-an-llm-agent-for-comprehensive-academic","title":"PaSa: An LLM Agent for Comprehensive Academic Paper Search","date":"2025-01-17","arxiv_id":"2501.10120","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bytedance/pasa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"passage-segmentation-of-documents-for","title":"Passage Segmentation of Documents for Extractive Question Answering","date":"2025-01-17","arxiv_id":"2501.09940","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-clustering-graph-transformer-approach-to","title":"Self-Clustering Graph Transformer Approach to Model Resting-State Functional Brain Activity","date":"2025-01-17","arxiv_id":"2501.16345","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-aerial-detection-baseline-of","slug":"a-simple-aerial-detection-baseline-of","title":"A Simple Aerial Detection Baseline of Multimodal Language Models","date":"2025-01-16","arxiv_id":"2501.09720","n_code_links":1,"syntology":null},{"paper":"/paper/confidence-estimation-for-error-detection-in","slug":"confidence-estimation-for-error-detection-in","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","date":"2025-01-16","arxiv_id":"2501.09527","n_code_links":1,"syntology":null},{"paper":"/paper/fine-grained-image-text-correspondence-with","slug":"fine-grained-image-text-correspondence-with","title":"Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation","date":"2025-01-16","arxiv_id":"2501.09688","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["kaist-cvml/part-catseg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generalized-single-image-based-morphing","title":"Generalized Single-Image-Based Morphing Attack Detection Using Deep Representations from Vision Transformer","date":"2025-01-16","arxiv_id":"2501.09817","n_code_links":0,"syntology":null},{"paper":"/paper/hspformer-hierarchical-spatial-perception","slug":"hspformer-hierarchical-spatial-perception","title":"HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation","date":"2025-01-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"learnings-from-scaling-visual-tokenizers-for","title":"Learnings from Scaling Visual Tokenizers for Reconstruction and Generation","date":"2025-01-16","arxiv_id":"2501.09755","n_code_links":0,"syntology":null},{"paper":"/paper/on-learning-informative-trajectory-embeddings","slug":"on-learning-informative-trajectory-embeddings","title":"On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression","date":"2025-01-16","arxiv_id":"2501.09327","n_code_links":1,"syntology":null},{"paper":null,"slug":"perspective-transition-of-large-language","title":"Perspective Transition of Large Language Models for Solving Subjective Tasks","date":"2025-01-16","arxiv_id":"2501.09265","n_code_links":0,"syntology":null},{"paper":"/paper/practical-continual-forgetting-for-pre","slug":"practical-continual-forgetting-for-pre","title":"Practical Continual Forgetting for Pre-trained Vision Models","date":"2025-01-16","arxiv_id":"2501.09705","n_code_links":1,"syntology":null},{"paper":"/paper/prompt-cam-a-simpler-interpretable","slug":"prompt-cam-a-simpler-interpretable","title":"Prompt-CAM: A Simpler Interpretable Transformer for Fine-Grained Analysis","date":"2025-01-16","arxiv_id":"2501.09333","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"sentiment-analysis-in-twitter-social-network","title":"Sentiment Analysis in Twitter Social Network Centered on Cryptocurrencies Using Machine Learning","date":"2025-01-16","arxiv_id":"2501.09777","n_code_links":0,"syntology":null},{"paper":"/paper/towards-robust-and-realistic-human-pose","slug":"towards-robust-and-realistic-human-pose","title":"Towards Robust and Realistic Human Pose Estimation via WiFi Signals","date":"2025-01-16","arxiv_id":"2501.09411","n_code_links":1,"syntology":null},{"paper":null,"slug":"unified-face-matching-and-physical-digital","title":"Unified Face Matching and Physical-Digital Spoofing Attack Detection","date":"2025-01-16","arxiv_id":"2501.09635","n_code_links":0,"syntology":null},{"paper":"/paper/agentic-retrieval-augmented-generation-a","slug":"agentic-retrieval-augmented-generation-a","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","date":"2025-01-15","arxiv_id":"2501.09136","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-is-all-you-need-until-you-need","title":"Attention is All You Need Until You Need Retention","date":"2025-01-15","arxiv_id":"2501.09166","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-human-annotated-training-data-with","title":"Augmenting Human-Annotated Training Data with Large Language Model Generation and Distillation in Open-Response Assessment","date":"2025-01-15","arxiv_id":"2501.09126","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-speaker-identity-text-guided-target","slug":"beyond-speaker-identity-text-guided-target","title":"Beyond Speaker Identity: Text Guided Target Speech Extraction","date":"2025-01-15","arxiv_id":"2501.09169","n_code_links":1,"syntology":null},{"paper":"/paper/bright-vo-brightness-guided-hybrid","slug":"bright-vo-brightness-guided-hybrid","title":"BRIGHT-VO: Brightness-Guided Hybrid Transformer for Visual Odometry with Multi-modality Refinement Module","date":"2025-01-15","arxiv_id":"2501.08659","n_code_links":1,"syntology":null},{"paper":null,"slug":"cancer-net-pca-seg-benchmarking-deep-learning","title":"Cancer-Net PCa-Seg: Benchmarking Deep Learning Models for Prostate Cancer Segmentation Using Synthetic Correlated Diffusion Imaging","date":"2025-01-15","arxiv_id":"2501.09185","n_code_links":0,"syntology":null},{"paper":null,"slug":"ct-patchtst-channel-time-patch-time-series","title":"CT-PatchTST: Channel-Time Patch Time-Series Transformer for Long-Term Renewable Energy Forecasting","date":"2025-01-15","arxiv_id":"2501.08620","n_code_links":0,"syntology":null},{"paper":"/paper/deep-self-supervised-disturbance-mapping-with","slug":"deep-self-supervised-disturbance-mapping-with","title":"Deep Self-Supervised Disturbance Mapping with the OPERA Sentinel-1 Radiometric Terrain Corrected SAR Backscatter Product","date":"2025-01-15","arxiv_id":"2501.09129","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-large-language-models-for-effective","title":"Enhanced Large Language Models for Effective Screening of Depression and Anxiety","date":"2025-01-15","arxiv_id":"2501.08769","n_code_links":0,"syntology":null},{"paper":null,"slug":"expanding-vietnamese-sentiwordnet-to-improve","title":"Expanding Vietnamese SentiWordNet to Improve Performance of Vietnamese Sentiment Analysis Models","date":"2025-01-15","arxiv_id":"2501.08758","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-takes-a-statistics-exam-a","title":"Generative AI Takes a Statistics Exam: A Comparison of Performance between ChatGPT3.5, ChatGPT4, and ChatGPT4o-mini","date":"2025-01-15","arxiv_id":"2501.09171","n_code_links":0,"syntology":null},{"paper":null,"slug":"miafex-an-attention-based-feature-extraction","title":"MIAFEx: An Attention-based Feature Extraction Method for Medical Image Classification","date":"2025-01-15","arxiv_id":"2501.08562","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-transformers-for-airway-to-lung","title":"Multi-View Transformers for Airway-To-Lung Ratio Inference on Cardiac CT Scans: The C4R Study","date":"2025-01-15","arxiv_id":"2501.08902","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-fake-news-video-explanation","title":"Multimodal Fake News Video Explanation: Dataset, Analysis and Evaluation","date":"2025-01-15","arxiv_id":"2501.08514","n_code_links":0,"syntology":null},{"paper":"/paper/supersam-crafting-a-sam-supernetwork-via","slug":"supersam-crafting-a-sam-supernetwork-via","title":"SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization","date":"2025-01-15","arxiv_id":"2501.08504","n_code_links":1,"syntology":null},{"paper":"/paper/swintexco-exemplar-based-video-colorization","slug":"swintexco-exemplar-based-video-colorization","title":"SwinTExCo: Exemplar-based video colorization using Swin Transformer","date":"2025-01-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"the-impact-of-big-five-personality-traits-on","title":"The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study","date":"2025-01-15","arxiv_id":"2503.15497","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-driver-advisory-system-based-on-large","title":"A Driver Advisory System Based on Large Language Model for High-speed Train","date":"2025-01-14","arxiv_id":"2501.07837","n_code_links":0,"syntology":null},{"paper":null,"slug":"active-sampling-for-node-attribute-completion","title":"Active Sampling for Node Attribute Completion on Graphs","date":"2025-01-14","arxiv_id":"2501.08450","n_code_links":0,"syntology":null},{"paper":null,"slug":"astrid-an-automated-and-scalable-triad-for","title":"ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems","date":"2025-01-14","arxiv_id":"2501.08208","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-efficient-adapter","title":"Comparative Analysis of Efficient Adapter-Based Fine-Tuning of State-of-the-Art Transformer Models","date":"2025-01-14","arxiv_id":"2501.08271","n_code_links":0,"syntology":null},{"paper":null,"slug":"decision-transformers-for-ris-assisted","title":"Decision Transformers for RIS-Assisted Systems with Diffusion Model-Based Channel Acquisition","date":"2025-01-14","arxiv_id":"2501.08007","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-interpretable-logic-rules-from","title":"Decoding Interpretable Logic Rules from Neural Networks","date":"2025-01-14","arxiv_id":"2501.08281","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-deep-learning-based-forward-solvers","slug":"efficient-deep-learning-based-forward-solvers","title":"Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models","date":"2025-01-14","arxiv_id":"2501.08226","n_code_links":1,"syntology":null},{"paper":null,"slug":"eliciting-in-context-retrieval-and-reasoning","title":"Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models","date":"2025-01-14","arxiv_id":"2501.08248","n_code_links":0,"syntology":null},{"paper":"/paper/emonext-an-adapted-convnext-for-facial-1","slug":"emonext-an-adapted-convnext-for-facial-1","title":"EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition","date":"2025-01-14","arxiv_id":"2501.08199","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-narrative-clustering-in-large","title":"Exploring Narrative Clustering in Large Language Models: A Layerwise Analysis of BERT","date":"2025-01-14","arxiv_id":"2501.08053","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-robustness-of-multilingual-llms-on","slug":"exploring-robustness-of-multilingual-llms-on","title":"Exploring Robustness of Multilingual LLMs on Real-World Noisy Data","date":"2025-01-14","arxiv_id":"2501.08322","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-energy-efficiency-and","title":"Investigating Energy Efficiency and Performance Trade-offs in LLM Inference Across Tasks and DVFS Settings","date":"2025-01-14","arxiv_id":"2501.08219","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-text-classification","title":"Large Language Models For Text Classification: Case Study And Comprehensive Review","date":"2025-01-14","arxiv_id":"2501.08457","n_code_links":0,"syntology":null},{"paper":null,"slug":"md-syn-synergistic-drug-combination","title":"MD-Syn: Synergistic drug combination prediction based on the multidimensional feature fusion method and attention mechanisms","date":"2025-01-14","arxiv_id":"2501.07884","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-language-models-for-grammatical","title":"Optimizing Language Models for Grammatical Acceptability: A Comparative Study of Fine-Tuning Techniques","date":"2025-01-14","arxiv_id":"2501.07853","n_code_links":0,"syntology":null},{"paper":"/paper/pokerbench-training-large-language-models-to","slug":"pokerbench-training-large-language-models-to","title":"PokerBench: Training Large Language Models to become Professional Poker Players","date":"2025-01-14","arxiv_id":"2501.08328","n_code_links":1,"syntology":null},{"paper":null,"slug":"psreg-prior-guided-sparse-mixture-of-experts","title":"PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration","date":"2025-01-14","arxiv_id":"2501.07762","n_code_links":0,"syntology":null},{"paper":null,"slug":"read-reinforcement-based-adversarial-learning","title":"READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data","date":"2025-01-14","arxiv_id":"2501.08035","n_code_links":0,"syntology":null},{"paper":"/paper/rearter-retrieval-augmented-reasoning-with","slug":"rearter-retrieval-augmented-reasoning-with","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","date":"2025-01-14","arxiv_id":"2501.07861","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-lightweight-time-series-forecasting-a","title":"Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching","date":"2025-01-14","arxiv_id":"2501.10448","n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-indoor-localization-advanced","title":"Transforming Indoor Localization: Advanced Transformer Architecture for NLOS Dominated Wireless Environments with Distributed Sensors","date":"2025-01-14","arxiv_id":"2501.07774","n_code_links":0,"syntology":null},{"paper":"/paper/ufgraphfr-an-attempt-at-a-federated","slug":"ufgraphfr-an-attempt-at-a-federated","title":"UFGraphFR: An attempt at a federated recommendation system based on user text characteristics","date":"2025-01-14","arxiv_id":"2501.08044","n_code_links":1,"syntology":null},{"paper":"/paper/comparative-analysis-of-optical-character","slug":"comparative-analysis-of-optical-character","title":"Comparative analysis of optical character recognition methods for Sámi texts from the National Library of Norway","date":"2025-01-13","arxiv_id":"2501.07300","n_code_links":2,"syntology":null},{"paper":"/paper/d3mes-diffusion-transformer-with-multihead","slug":"d3mes-diffusion-transformer-with-multihead","title":"D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation","date":"2025-01-13","arxiv_id":"2501.07077","n_code_links":1,"syntology":null},{"paper":"/paper/edgetam-on-device-track-anything-model","slug":"edgetam-on-device-track-anything-model","title":"EdgeTAM: On-Device Track Anything Model","date":"2025-01-13","arxiv_id":"2501.07256","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/edgetam"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/enhancing-retrieval-augmented-generation-a","slug":"enhancing-retrieval-augmented-generation-a","title":"Enhancing Retrieval-Augmented Generation: A Study of Best Practices","date":"2025-01-13","arxiv_id":"2501.07391","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":["ali-bahrainian/rag_best_practices"],"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":"enhancing-talent-employment-insights-through","title":"Enhancing Talent Employment Insights Through Feature Extraction with LLM Finetuning","date":"2025-01-13","arxiv_id":"2501.07663","n_code_links":0,"syntology":null},{"paper":"/paper/estimating-musical-surprisal-in-audio","slug":"estimating-musical-surprisal-in-audio","title":"Estimating Musical Surprisal in Audio","date":"2025-01-13","arxiv_id":"2501.07474","n_code_links":1,"syntology":null},{"paper":"/paper/finerweb-10bt-refining-web-data-with-llm","slug":"finerweb-10bt-refining-web-data-with-llm","title":"FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering","date":"2025-01-13","arxiv_id":"2501.07314","n_code_links":1,"syntology":null},{"paper":null,"slug":"future-conditioned-recommendations-with-multi","title":"Future-Conditioned Recommendations with Multi-Objective Controllable Decision Transformer","date":"2025-01-13","arxiv_id":"2501.07212","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-as-a-monte-carlo-language-tree-a","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective","date":"2025-01-13","arxiv_id":"2501.07641","n_code_links":0,"syntology":null},{"paper":"/paper/how-gpt-learns-layer-by-layer","slug":"how-gpt-learns-layer-by-layer","title":"How GPT learns layer by layer","date":"2025-01-13","arxiv_id":"2501.07108","n_code_links":1,"syntology":null}],"record_sha256":"1f4a81470b31683ee020041a2b76deba93c9b3bb353fbe06d2252bb56e22b5d3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}