{"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/44","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":44,"pages_in_order":249,"rows_per_page":100,"rows":[4301,4400],"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/43","next":"/method/multi-head-attention/papers/45","papers":[{"paper":"/paper/mare-multi-aspect-rationale-extractor-on","slug":"mare-multi-aspect-rationale-extractor-on","title":"MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction","date":"2024-10-04","arxiv_id":"2410.03531","n_code_links":0,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"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":null}},{"paper":"/paper/melodi-exploring-memory-compression-for-long","slug":"melodi-exploring-memory-compression-for-long","title":"MELODI: Exploring Memory Compression for Long Contexts","date":"2024-10-04","arxiv_id":"2410.03156","n_code_links":1,"syntology":null},{"paper":null,"slug":"metadata-matters-for-time-series-informative","title":"Metadata Matters for Time Series: Informative Forecasting with Transformers","date":"2024-10-04","arxiv_id":"2410.03806","n_code_links":0,"syntology":null},{"paper":"/paper/predictive-coding-for-decision-transformer","slug":"predictive-coding-for-decision-transformer","title":"Predictive Coding for Decision Transformer","date":"2024-10-04","arxiv_id":"2410.03408","n_code_links":1,"syntology":null},{"paper":null,"slug":"prf-parallel-resonate-and-fire-neuron-for","title":"PRF: Parallel Resonate and Fire Neuron for Long Sequence Learning in Spiking Neural Networks","date":"2024-10-04","arxiv_id":"2410.03530","n_code_links":0,"syntology":null},{"paper":null,"slug":"sag-style-aligned-article-generation-via","title":"SAG: Style-Aligned Article Generation via Model Collaboration","date":"2024-10-04","arxiv_id":"2410.03137","n_code_links":0,"syntology":null},{"paper":"/paper/sda-grin-for-adaptive-spatial-temporal","slug":"sda-grin-for-adaptive-spatial-temporal","title":"SDA-GRIN for Adaptive Spatial-Temporal Multivariate Time Series Imputation","date":"2024-10-04","arxiv_id":"2410.03954","n_code_links":1,"syntology":null},{"paper":null,"slug":"selective-transformer-for-hyperspectral-image","title":"Selective Transformer for Hyperspectral Image Classification","date":"2024-10-04","arxiv_id":"2410.03171","n_code_links":0,"syntology":null},{"paper":"/paper/steering-large-language-models-between-code","slug":"steering-large-language-models-between-code","title":"Steering Large Language Models between Code Execution and Textual Reasoning","date":"2024-10-04","arxiv_id":"2410.03524","n_code_links":1,"syntology":null},{"paper":null,"slug":"still-not-quite-there-evaluating-large","title":"Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis","date":"2024-10-04","arxiv_id":"2410.03908","n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-list-grounded-question-answering","title":"Structured List-Grounded Question Answering","date":"2024-10-04","arxiv_id":"2410.03950","n_code_links":0,"syntology":null},{"paper":"/paper/swiftkv-fast-prefill-optimized-inference-with","slug":"swiftkv-fast-prefill-optimized-inference-with","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","date":"2024-10-04","arxiv_id":"2410.03960","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-linguistically-aware-and-language","title":"Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)","date":"2024-10-04","arxiv_id":"2410.03568","n_code_links":0,"syntology":null},{"paper":"/paper/trustemg-net-using-representation-masking","slug":"trustemg-net-using-representation-masking","title":"TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement","date":"2024-10-04","arxiv_id":"2410.03843","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-prompts-to-guide-large-language-models","title":"Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style","date":"2024-10-04","arxiv_id":"2410.03848","n_code_links":0,"syntology":null},{"paper":"/paper/variational-language-concepts-for","slug":"variational-language-concepts-for","title":"Variational Language Concepts for Interpreting Foundation Language Models","date":"2024-10-04","arxiv_id":"2410.03964","n_code_links":1,"syntology":null},{"paper":"/paper/vulnerability-detection-via-topological","slug":"vulnerability-detection-via-topological","title":"Vulnerability Detection via Topological Analysis of Attention Maps","date":"2024-10-04","arxiv_id":"2410.03470","n_code_links":1,"syntology":null},{"paper":"/paper/ward-provable-rag-dataset-inference-via-llm","slug":"ward-provable-rag-dataset-inference-via-llm","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","date":"2024-10-04","arxiv_id":"2410.03537","n_code_links":0,"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":null}},{"paper":null,"slug":"a-comprehensive-survey-of-retrieval-augmented","title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","date":"2024-10-03","arxiv_id":"2410.12837","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-inference-time-compute-llms-can","title":"Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation","date":"2024-10-03","arxiv_id":"2410.02725","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphaintegrator-transformer-action-search-for","title":"AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs","date":"2024-10-03","arxiv_id":"2410.02666","n_code_links":0,"syntology":null},{"paper":null,"slug":"braintransformers-snn-llm","title":"BrainTransformers: SNN-LLM","date":"2024-10-03","arxiv_id":"2410.14687","n_code_links":0,"syntology":null},{"paper":"/paper/can-llms-reliably-simulate-human-learner","slug":"can-llms-reliably-simulate-human-learner","title":"Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments","date":"2024-10-03","arxiv_id":"2410.02110","n_code_links":1,"syntology":null},{"paper":"/paper/cax-cellular-automata-accelerated-in-jax","slug":"cax-cellular-automata-accelerated-in-jax","title":"CAX: Cellular Automata Accelerated in JAX","date":"2024-10-03","arxiv_id":"2410.02651","n_code_links":1,"syntology":null},{"paper":null,"slug":"coal-mining-question-answering-with-llms","title":"Coal Mining Question Answering with LLMs","date":"2024-10-03","arxiv_id":"2410.02959","n_code_links":0,"syntology":null},{"paper":"/paper/codejudge-evaluating-code-generation-with","slug":"codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","arxiv_id":"2410.02184","n_code_links":1,"syntology":{"ran":15,"of":23,"n_ran_checked":14,"n_instrument":1,"unverified":8,"pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["VichyTong/CodeJudge"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/controlled-generation-of-natural-adversarial","slug":"controlled-generation-of-natural-adversarial","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","date":"2024-10-03","arxiv_id":"2410.02163","n_code_links":1,"syntology":null},{"paper":null,"slug":"defining-knowledge-bridging-epistemology-and","title":"Defining Knowledge: Bridging Epistemology and Large Language Models","date":"2024-10-03","arxiv_id":"2410.02499","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-specific-retrieval-augmented","title":"Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization","date":"2024-10-03","arxiv_id":"2410.02721","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-semantic-segmentation-via","title":"Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network","date":"2024-10-03","arxiv_id":"2410.02224","n_code_links":0,"syntology":null},{"paper":"/paper/fan-fourier-analysis-networks","slug":"fan-fourier-analysis-networks","title":"FAN: Fourier Analysis Networks","date":"2024-10-03","arxiv_id":"2410.02675","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yihongdong/fan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official"]}}},{"paper":null,"slug":"from-pixels-to-tokens-byte-pair-encoding-on","title":"From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities","date":"2024-10-03","arxiv_id":"2410.02155","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-large-language-models-in-embodied","title":"Grounding Large Language Models In Embodied Environment With Imperfect World Models","date":"2024-10-03","arxiv_id":"2410.02742","n_code_links":0,"syntology":null},{"paper":"/paper/helmet-how-to-evaluate-long-context-language","slug":"helmet-how-to-evaluate-long-context-language","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","date":"2024-10-03","arxiv_id":"2410.02694","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"6 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["princeton-nlp/helmet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hifiseg-high-frequency-information-enhanced","title":"HiFiSeg: High-Frequency Information Enhanced Polyp Segmentation with Global-Local Vision Transformer","date":"2024-10-03","arxiv_id":"2410.02528","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-much-can-rag-help-the-reasoning-of-llm","title":"How Much Can RAG Help the Reasoning of LLM?","date":"2024-10-03","arxiv_id":"2410.02338","n_code_links":0,"syntology":null},{"paper":null,"slug":"indicsenteval-how-effectively-do-multilingual","title":"IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?","date":"2024-10-03","arxiv_id":"2410.02611","n_code_links":0,"syntology":null},{"paper":null,"slug":"intrinsic-evaluation-of-rag-systems-for-deep","title":"Intrinsic Evaluation of RAG Systems for Deep-Logic Questions","date":"2024-10-03","arxiv_id":"2410.02932","n_code_links":0,"syntology":null},{"paper":null,"slug":"iot-llm-enhancing-real-world-iot-task","title":"IoT-LLM: Enhancing Real-World IoT Task Reasoning with Large Language Models","date":"2024-10-03","arxiv_id":"2410.02429","n_code_links":0,"syntology":null},{"paper":"/paper/l-citeeval-do-long-context-models-truly","slug":"l-citeeval-do-long-context-models-truly","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","date":"2024-10-03","arxiv_id":"2410.02115","n_code_links":2,"syntology":null},{"paper":null,"slug":"llava-critic-learning-to-evaluate-multimodal","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02712","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-based-gnn-enabled-energy-efficient","title":"Model-Based GNN Enabled Energy-Efficient Beamforming for Ultra-Dense Wireless Networks","date":"2024-10-03","arxiv_id":"2410.02289","n_code_links":0,"syntology":null},{"paper":null,"slug":"morphological-evaluation-of-subwords","title":"Morphological evaluation of subwords vocabulary used by BETO language model","date":"2024-10-03","arxiv_id":"2410.02283","n_code_links":0,"syntology":null},{"paper":null,"slug":"plots-unlock-time-series-understanding-in","title":"Plots Unlock Time-Series Understanding in Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02637","n_code_links":0,"syntology":null},{"paper":null,"slug":"reward-rag-enhancing-rag-with-reward-driven","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","date":"2024-10-03","arxiv_id":"2410.03780","n_code_links":0,"syntology":null},{"paper":null,"slug":"sc-cdm-enhancing-quality-of-image-semantic","title":"SC-CDM: Enhancing Quality of Image Semantic Communication with a Compact Diffusion Model","date":"2024-10-03","arxiv_id":"2410.02121","n_code_links":0,"syntology":null},{"paper":"/paper/sieve-general-purpose-data-filtering-system","slug":"sieve-general-purpose-data-filtering-system","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data","date":"2024-10-03","arxiv_id":"2410.02755","n_code_links":0,"syntology":null},{"paper":"/paper/theoretical-insights-into-fine-tuning","slug":"theoretical-insights-into-fine-tuning","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","date":"2024-10-03","arxiv_id":"2410.02247","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["chen123ctrls/efficientft","chen123CtrlS/LightweightAtt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-understanding-the-universality-of","title":"Towards Understanding the Universality of Transformers for Next-Token Prediction","date":"2024-10-03","arxiv_id":"2410.03011","n_code_links":0,"syntology":null},{"paper":"/paper/training-language-models-on-synthetic-edit","slug":"training-language-models-on-synthetic-edit","title":"Training Language Models on Synthetic Edit Sequences Improves Code Synthesis","date":"2024-10-03","arxiv_id":"2410.02749","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["upiterbarg/lintseq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"training-nonlinear-transformers-for-chain-of","title":"Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis","date":"2024-10-03","arxiv_id":"2410.02167","n_code_links":0,"syntology":null},{"paper":null,"slug":"trajgpt-irregular-time-series-representation","title":"TrajGPT: Irregular Time-Series Representation Learning for Health Trajectory Analysis","date":"2024-10-03","arxiv_id":"2410.02133","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertaintyrag-span-level-uncertainty","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","date":"2024-10-03","arxiv_id":"2410.02719","n_code_links":0,"syntology":null},{"paper":"/paper/visual-editing-with-llm-based-tool-chaining","slug":"visual-editing-with-llm-based-tool-chaining","title":"Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications","date":"2024-10-03","arxiv_id":"2410.02952","n_code_links":1,"syntology":null},{"paper":"/paper/a-spark-of-vision-language-intelligence-2","slug":"a-spark-of-vision-language-intelligence-2","title":"A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation","date":"2024-10-02","arxiv_id":"2410.01912","n_code_links":1,"syntology":null},{"paper":"/paper/a-versatile-machine-learning-workflow-for","slug":"a-versatile-machine-learning-workflow-for","title":"A versatile machine learning workflow for high-throughput analysis of supported metal catalyst particles","date":"2024-10-02","arxiv_id":"2410.01213","n_code_links":1,"syntology":null},{"paper":null,"slug":"ahp-powered-llm-reasoning-for-multi-criteria","title":"AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses","date":"2024-10-02","arxiv_id":"2410.01246","n_code_links":0,"syntology":null},{"paper":"/paper/attention-layers-provably-solve-single","slug":"attention-layers-provably-solve-single","title":"Attention layers provably solve single-location regression","date":"2024-10-02","arxiv_id":"2410.01537","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pierremarion23/single-location-regression"],"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":null,"slug":"automated-red-teaming-with-goat-the","title":"Automated Red Teaming with GOAT: the Generative Offensive Agent Tester","date":"2024-10-02","arxiv_id":"2410.01606","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-deductive-coding-in-discourse","slug":"automatic-deductive-coding-in-discourse","title":"Automatic deductive coding in discourse analysis: an application of large language models in learning analytics","date":"2024-10-02","arxiv_id":"2410.01240","n_code_links":1,"syntology":null},{"paper":"/paper/bordirlines-a-dataset-for-evaluating-cross","slug":"bordirlines-a-dataset-for-evaluating-cross","title":"BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation","date":"2024-10-02","arxiv_id":"2410.01171","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["manestay/bordirlines"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/deepprotein-deep-learning-library-and","slug":"deepprotein-deep-learning-library-and","title":"DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning","date":"2024-10-02","arxiv_id":"2410.02023","n_code_links":1,"syntology":null},{"paper":"/paper/depth-pro-sharp-monocular-metric-depth-in","slug":"depth-pro-sharp-monocular-metric-depth-in","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","date":"2024-10-02","arxiv_id":"2410.02073","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["apple/ml-depth-pro"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"emotion-aware-response-generation-using","title":"Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation","date":"2024-10-02","arxiv_id":"2410.01306","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-fine-tuning-for-text-to-sqls-by","title":"Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement","date":"2024-10-02","arxiv_id":"2410.01869","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-retrieval-in-qa-systems-with","slug":"enhancing-retrieval-in-qa-systems-with","title":"Enhancing Retrieval in QA Systems with Derived Feature Association","date":"2024-10-02","arxiv_id":"2410.03754","n_code_links":1,"syntology":null},{"paper":null,"slug":"entp-encoder-only-next-token-prediction","title":"ENTP: Encoder-only Next Token Prediction","date":"2024-10-02","arxiv_id":"2410.01600","n_code_links":0,"syntology":null},{"paper":null,"slug":"et-plan-bench-embodied-task-level-planning","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","date":"2024-10-02","arxiv_id":"2410.14682","n_code_links":0,"syntology":null},{"paper":null,"slug":"financial-sentiment-analysis-on-news-and","title":"Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT","date":"2024-10-02","arxiv_id":"2410.01987","n_code_links":0,"syntology":null},{"paper":"/paper/flashmask-efficient-and-rich-mask-extension","slug":"flashmask-efficient-and-rich-mask-extension","title":"FlashMask: Efficient and Rich Mask Extension of FlashAttention","date":"2024-10-02","arxiv_id":"2410.01359","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 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":["PaddlePaddle/Paddle"],"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":null,"slug":"getting-free-bits-back-from-rotational","title":"Getting Free Bits Back from Rotational Symmetries in LLMs","date":"2024-10-02","arxiv_id":"2410.01309","n_code_links":0,"syntology":null},{"paper":"/paper/imaging-foundation-model-for-universal","slug":"imaging-foundation-model-for-universal","title":"Imaging foundation model for universal enhancement of non-ideal measurement CT","date":"2024-10-02","arxiv_id":"2410.01591","n_code_links":1,"syntology":null},{"paper":"/paper/marple-a-benchmark-for-long-horizon-inference","slug":"marple-a-benchmark-for-long-horizon-inference","title":"MARPLE: A Benchmark for Long-Horizon Inference","date":"2024-10-02","arxiv_id":"2410.01926","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":["marple-benchmark/marple"],"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/mind-scramble-unveiling-large-language-model","slug":"mind-scramble-unveiling-large-language-model","title":"Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia","date":"2024-10-02","arxiv_id":"2410.01677","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-adaptation-of-unlimiformer-for-decoder","title":"On The Adaptation of Unlimiformer for Decoder-Only Transformers","date":"2024-10-02","arxiv_id":"2410.01637","n_code_links":0,"syntology":null},{"paper":"/paper/open-rag-enhanced-retrieval-augmented","slug":"open-rag-enhanced-retrieval-augmented","title":"Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models","date":"2024-10-02","arxiv_id":"2410.01782","n_code_links":1,"syntology":null},{"paper":"/paper/quantifying-generalization-complexity-for","slug":"quantifying-generalization-complexity-for","title":"Quantifying Generalization Complexity for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01769","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhentingqi/scylla"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"radar-robust-two-stage-modality-incomplete","title":"RADAR: Robust Two-stage Modality-incomplete Industrial Anomaly Detection","date":"2024-10-02","arxiv_id":"2410.01737","n_code_links":0,"syntology":null},{"paper":null,"slug":"rs-fme-swint-a-novel-feature-map-enhancement","title":"RS-FME-SwinT: A Novel Feature Map Enhancement Framework Integrating Customized SwinT with Residual and Spatial CNN for Monkeypox Diagnosis","date":"2024-10-02","arxiv_id":"2410.01216","n_code_links":0,"syntology":null},{"paper":"/paper/saliency-guided-detr-for-moment-retrieval-and","slug":"saliency-guided-detr-for-moment-retrieval-and","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","date":"2024-10-02","arxiv_id":"2410.01615","n_code_links":1,"syntology":null},{"paper":"/paper/seeing-eye-to-ai-human-alignment-via-gaze","slug":"seeing-eye-to-ai-human-alignment-via-gaze","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01532","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["telefonica-scientific-research/gaze_reward"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ulcergpt-a-multimodal-approach-leveraging","title":"UlcerGPT: A Multimodal Approach Leveraging Large Language and Vision Models for Diabetic Foot Ulcer Image Transcription","date":"2024-10-02","arxiv_id":"2410.01989","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-arabic-alphabet-sign-language","title":"Advanced Arabic Alphabet Sign Language Recognition Using Transfer Learning and Transformer Models","date":"2024-10-01","arxiv_id":"2410.00681","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-suffixes-may-be-features-too","slug":"adversarial-suffixes-may-be-features-too","title":"Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models","date":"2024-10-01","arxiv_id":"2410.00451","n_code_links":1,"syntology":null},{"paper":"/paper/alignsum-data-pyramid-hierarchical-fine","slug":"alignsum-data-pyramid-hierarchical-fine","title":"AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference","date":"2024-10-01","arxiv_id":"2410.00409","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 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":["csyanghan/alignsum"],"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/creative-and-context-aware-translation-of","slug":"creative-and-context-aware-translation-of","title":"Creative and Context-Aware Translation of East Asian Idioms with GPT-4","date":"2024-10-01","arxiv_id":"2410.00988","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoding-hate-exploring-language-models","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","date":"2024-10-01","arxiv_id":"2410.00775","n_code_links":0,"syntology":null},{"paper":"/paper/deep-multimodal-fusion-for-semantic","slug":"deep-multimodal-fusion-for-semantic","title":"Deep Multimodal Fusion for Semantic Segmentation of Remote Sensing Earth Observation Data","date":"2024-10-01","arxiv_id":"2410.00469","n_code_links":0,"syntology":null},{"paper":"/paper/domain-aware-multi-task-pretraining-of-3d","slug":"domain-aware-multi-task-pretraining-of-3d","title":"Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRI","date":"2024-10-01","arxiv_id":"2410.00410","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-speech-recognition-with-pre","slug":"end-to-end-speech-recognition-with-pre","title":"End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2024-10-01","arxiv_id":"2410.00528","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-learning-capabilities-of","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","date":"2024-10-01","arxiv_id":"2410.00519","n_code_links":0,"syntology":null},{"paper":"/paper/fce-yolov8-yolov8-with-feature-context","slug":"fce-yolov8-yolov8-with-feature-context","title":"Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images","date":"2024-10-01","arxiv_id":"2410.01031","n_code_links":1,"syntology":null},{"paper":null,"slug":"glmha-a-guided-low-rank-multi-head-self","title":"GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction","date":"2024-10-01","arxiv_id":"2410.00380","n_code_links":0,"syntology":null},{"paper":null,"slug":"insight-a-multi-modal-diagnostic-pipeline","title":"Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis","date":"2024-10-01","arxiv_id":"2410.00292","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-enhanced-model-for-eye-leme-an-open","title":"Language Enhanced Model for Eye (LEME): An Open-Source Ophthalmology-Specific Large Language Model","date":"2024-10-01","arxiv_id":"2410.03740","n_code_links":0,"syntology":null},{"paper":null,"slug":"map-unleashing-hybrid-mamba-transformer","title":"MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining","date":"2024-10-01","arxiv_id":"2410.00871","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-temporal-transformer-for-speech","title":"Multi-Scale Temporal Transformer For Speech Emotion Recognition","date":"2024-10-01","arxiv_id":"2410.00390","n_code_links":0,"syntology":null},{"paper":null,"slug":"ngpt-normalized-transformer-with","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","date":"2024-10-01","arxiv_id":"2410.01131","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-and-evaluating-enterprise","slug":"optimizing-and-evaluating-enterprise","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","date":"2024-10-01","arxiv_id":"2410.12812","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantifying-reliance-on-external-information","title":"Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis","date":"2024-10-01","arxiv_id":"2410.00857","n_code_links":0,"syntology":null}],"record_sha256":"12b33719c985719bd22eb9c4bbfb17d9bf7a476562373707f3e0dc5a81fd79e5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}