{"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/62","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":62,"pages_in_order":249,"rows_per_page":100,"rows":[6101,6200],"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/61","next":"/method/multi-head-attention/papers/63","papers":[{"paper":"/paper/geometric-features-enhanced-human-object","slug":"geometric-features-enhanced-human-object","title":"Geometric Features Enhanced Human-Object Interaction Detection","date":"2024-06-26","arxiv_id":"2406.18691","n_code_links":1,"syntology":null},{"paper":null,"slug":"glue-pizza-and-eat-rocks-exploiting","title":"\"Glue pizza and eat rocks\" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models","date":"2024-06-26","arxiv_id":"2406.19417","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-free-prompted-based-anomaly-detection","title":"Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme","date":"2024-06-26","arxiv_id":"2406.18197","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-entity-recognition-using-ensembles","title":"Improving Entity Recognition Using Ensembles of Deep Learning and Fine-tuned Large Language Models: A Case Study on Adverse Event Extraction from Multiple Sources","date":"2024-06-26","arxiv_id":"2406.18049","n_code_links":0,"syntology":null},{"paper":"/paper/jailbreaking-llms-with-arabic-transliteration","slug":"jailbreaking-llms-with-arabic-transliteration","title":"Jailbreaking LLMs with Arabic Transliteration and Arabizi","date":"2024-06-26","arxiv_id":"2406.18725","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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["securedl/arabic_jailbreak"],"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/knowledge-graph-enhanced-retrieval-augmented","slug":"knowledge-graph-enhanced-retrieval-augmented","title":"Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis","date":"2024-06-26","arxiv_id":"2406.18114","n_code_links":1,"syntology":null},{"paper":"/paper/mathodyssey-benchmarking-mathematical-problem","slug":"mathodyssey-benchmarking-mathematical-problem","title":"MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data","date":"2024-06-26","arxiv_id":"2406.18321","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/mfdnet-multi-frequency-deflare-network-for","slug":"mfdnet-multi-frequency-deflare-network-for","title":"MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal","date":"2024-06-26","arxiv_id":"2406.18079","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":7,"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) · 1 unverified","official":{"repos":["Jiang-maomao/flare-removal"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-step-knowledge-retrieval-and-inference","title":"Multi-step Inference over Unstructured Data","date":"2024-06-26","arxiv_id":"2406.17987","n_code_links":0,"syntology":null},{"paper":null,"slug":"octo-planner-on-device-language-model-for","title":"Octo-planner: On-device Language Model for Planner-Action Agents","date":"2024-06-26","arxiv_id":"2406.18082","n_code_links":0,"syntology":null},{"paper":"/paper/pianobart-symbolic-piano-music-generation-and","slug":"pianobart-symbolic-piano-music-generation-and","title":"PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training","date":"2024-06-26","arxiv_id":"2407.03361","n_code_links":1,"syntology":null},{"paper":null,"slug":"poisoned-langchain-jailbreak-llms-by","title":"Poisoned LangChain: Jailbreak LLMs by LangChain","date":"2024-06-26","arxiv_id":"2406.18122","n_code_links":0,"syntology":null},{"paper":null,"slug":"re-ranking-step-by-step-investigating-pre","title":"Re-Ranking Step by Step: Investigating Pre-Filtering for Re-Ranking with Large Language Models","date":"2024-06-26","arxiv_id":"2406.18740","n_code_links":0,"syntology":null},{"paper":"/paper/repeat-and-concatenate-2d-to-3d-image","slug":"repeat-and-concatenate-2d-to-3d-image","title":"Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling","date":"2024-06-26","arxiv_id":"2406.18422","n_code_links":1,"syntology":null},{"paper":"/paper/resumeatlas-revisiting-resume-classification","slug":"resumeatlas-revisiting-resume-classification","title":"ResumeAtlas: Revisiting Resume Classification with Large-Scale Datasets and Large Language Models","date":"2024-06-26","arxiv_id":"2406.18125","n_code_links":1,"syntology":null},{"paper":"/paper/step-dpo-step-wise-preference-optimization","slug":"step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","arxiv_id":"2406.18629","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":10,"n_instrument":1,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dvlab-research/step-dpo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/themis-towards-flexible-and-interpretable-nlg","slug":"themis-towards-flexible-and-interpretable-nlg","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","date":"2024-06-26","arxiv_id":"2406.18365","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PKU-ONELab/Themis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/understand-what-llm-needs-dual-preference","slug":"understand-what-llm-needs-dual-preference","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","date":"2024-06-26","arxiv_id":"2406.18676","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["dongguanting/dpa-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unveiling-and-controlling-anomalous-attention","title":"Unveiling and Controlling Anomalous Attention Distribution in Transformers","date":"2024-06-26","arxiv_id":"2407.01601","n_code_links":0,"syntology":null},{"paper":"/paper/wildguard-open-one-stop-moderation-tools-for","slug":"wildguard-open-one-stop-moderation-tools-for","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","date":"2024-06-26","arxiv_id":"2406.18495","n_code_links":4,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["allenai/wildguard"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"zero-shot-prompt-based-classification-topic","title":"Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets","date":"2024-06-26","arxiv_id":"2406.18239","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-clinical-evidence-synthesis-with","title":"Accelerating Clinical Evidence Synthesis with Large Language Models","date":"2024-06-25","arxiv_id":"2406.17755","n_code_links":0,"syntology":null},{"paper":"/paper/ares-alternating-reinforcement-learning-and","slug":"ares-alternating-reinforcement-learning-and","title":"ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback","date":"2024-06-25","arxiv_id":"2407.00087","n_code_links":1,"syntology":null},{"paper":null,"slug":"autonomous-prompt-engineering-in-large","title":"Autonomous Prompt Engineering in Large Language Models","date":"2024-06-25","arxiv_id":"2407.11000","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-neural-information-retrieval-boolean","title":"SetBERT: Enhancing Retrieval Performance for Boolean Logic and Set Operation Queries","date":"2024-06-25","arxiv_id":"2406.17282","n_code_links":0,"syntology":null},{"paper":null,"slug":"brain-tumor-classification-using-vision","title":"Brain Tumor Classification using Vision Transformer with Selective Cross-Attention Mechanism and Feature Calibration","date":"2024-06-25","arxiv_id":"2406.17670","n_code_links":0,"syntology":null},{"paper":"/paper/cross-modal-spherical-aggregation-for-weakly","slug":"cross-modal-spherical-aggregation-for-weakly","title":"Cross-Modal Spherical Aggregation for Weakly Supervised Remote Sensing Shadow Removal","date":"2024-06-25","arxiv_id":"2406.17469","n_code_links":1,"syntology":null},{"paper":"/paper/ctbench-a-comprehensive-benchmark-for","slug":"ctbench-a-comprehensive-benchmark-for","title":"CTBench: A Comprehensive Benchmark for Evaluating Language Model Capabilities in Clinical Trial Design","date":"2024-06-25","arxiv_id":"2406.17888","n_code_links":1,"syntology":null},{"paper":null,"slug":"dark-transformer-a-video-transformer-for","title":"Dark Transformer: A Video Transformer for Action Recognition in the Dark","date":"2024-06-25","arxiv_id":"2407.12805","n_code_links":0,"syntology":null},{"paper":"/paper/director3d-real-world-camera-trajectory-and","slug":"director3d-real-world-camera-trajectory-and","title":"Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text","date":"2024-06-25","arxiv_id":"2406.17601","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":7,"n_instrument":5,"unverified":3,"pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["imlixinyang/director3d"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"discrete-diffusion-language-model-for-long","title":"Discrete Diffusion Language Model for Long Text Summarization","date":"2024-06-25","arxiv_id":"2407.10998","n_code_links":0,"syntology":null},{"paper":null,"slug":"et-tu-clip-addressing-common-object-errors","title":"ET tu, CLIP? Addressing Common Object Errors for Unseen Environments","date":"2024-06-25","arxiv_id":"2406.17876","n_code_links":0,"syntology":null},{"paper":"/paper/interpreting-attention-layer-outputs-with","slug":"interpreting-attention-layer-outputs-with","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","date":"2024-06-25","arxiv_id":"2406.17759","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["ckkissane/attention-output-saes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"knowledge-distillation-in-automated","title":"Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels","date":"2024-06-25","arxiv_id":"2406.17633","n_code_links":0,"syntology":null},{"paper":null,"slug":"longins-a-challenging-long-context","title":"LongIns: A Challenging Long-context Instruction-based Exam for LLMs","date":"2024-06-25","arxiv_id":"2406.17588","n_code_links":0,"syntology":null},{"paper":"/paper/lumberchunker-long-form-narrative-document","slug":"lumberchunker-long-form-narrative-document","title":"LumberChunker: Long-Form Narrative Document Segmentation","date":"2024-06-25","arxiv_id":"2406.17526","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["joaodsmarques/lumberchunker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multimodal-cross-task-interaction-for","slug":"multimodal-cross-task-interaction-for","title":"Multimodal Cross-Task Interaction for Survival Analysis in Whole Slide Pathological Images","date":"2024-06-25","arxiv_id":"2406.17225","n_code_links":1,"syntology":null},{"paper":null,"slug":"point-tree-transformer-for-point-cloud","title":"Point Tree Transformer for Point Cloud Registration","date":"2024-06-25","arxiv_id":"2406.17530","n_code_links":0,"syntology":null},{"paper":"/paper/q-dit-accurate-post-training-quantization-for","slug":"q-dit-accurate-post-training-quantization-for","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","date":"2024-06-25","arxiv_id":"2406.17343","n_code_links":1,"syntology":{"ran":17,"of":19,"n_ran_checked":11,"n_instrument":6,"unverified":2,"pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["juanerx/q-dit"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"ragbench-explainable-benchmark-for-retrieval","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","date":"2024-06-25","arxiv_id":"2407.11005","n_code_links":0,"syntology":null},{"paper":"/paper/revitalizing-convolutional-network-for-image","slug":"revitalizing-convolutional-network-for-image","title":"Revitalizing Convolutional Network for Image Restoration","date":"2024-06-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"semi-supervised-classification-of-dental","title":"Semi-supervised classification of dental conditions in panoramic radiographs using large language model and instance segmentation: A real-world dataset evaluation","date":"2024-06-25","arxiv_id":"2406.17915","n_code_links":0,"syntology":null},{"paper":null,"slug":"sound-tagging-in-infant-centric-home","title":"Sound Tagging in Infant-centric Home Soundscapes","date":"2024-06-25","arxiv_id":"2406.17190","n_code_links":0,"syntology":null},{"paper":"/paper/structured-unrestricted-rank-matrices-for","slug":"structured-unrestricted-rank-matrices-for","title":"Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning","date":"2024-06-25","arxiv_id":"2406.17740","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["arijitthegame/structured-matrices-peft"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sum-saliency-unification-through-mamba-for","slug":"sum-saliency-unification-through-mamba-for","title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","date":"2024-06-25","arxiv_id":"2406.17815","n_code_links":1,"syntology":{"ran":14,"of":14,"n_ran_checked":14,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Arhosseini77/SUM"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"task-agnostic-federated-learning","title":"Task-Agnostic Federated Learning","date":"2024-06-25","arxiv_id":"2406.17235","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-channel-modeling-in-multi-head-self","slug":"temporal-channel-modeling-in-multi-head-self","title":"Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection","date":"2024-06-25","arxiv_id":"2406.17376","n_code_links":1,"syntology":null},{"paper":"/paper/this-paper-had-the-smartest-reviewers","slug":"this-paper-had-the-smartest-reviewers","title":"This Paper Had the Smartest Reviewers -- Flattery Detection Utilising an Audio-Textual Transformer-Based Approach","date":"2024-06-25","arxiv_id":"2406.17667","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-optimal-trade-offs-in-knowledge","title":"Towards Optimal Trade-offs in Knowledge Distillation for CNNs and Vision Transformers at the Edge","date":"2024-06-25","arxiv_id":"2407.12808","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-segmentation-of-adnexal","title":"Improving ovarian cancer segmentation accuracy with transformers through AI-guided labeling","date":"2024-06-25","arxiv_id":"2406.17666","n_code_links":0,"syntology":null},{"paper":"/paper/univariate-skeleton-prediction-in","slug":"univariate-skeleton-prediction-in","title":"Univariate Skeleton Prediction in Multivariate Systems Using Transformers","date":"2024-06-25","arxiv_id":"2406.17834","n_code_links":1,"syntology":null},{"paper":"/paper/unlocking-continual-learning-abilities-in","slug":"unlocking-continual-learning-abilities-in","title":"Unlocking Continual Learning Abilities in Language Models","date":"2024-06-25","arxiv_id":"2406.17245","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wenyudu/migu"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-do-the-circuits-mean-a-knowledge-edit","title":"Understanding Language Model Circuits through Knowledge Editing","date":"2024-06-25","arxiv_id":"2406.17241","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-phase-field-simulations-through","title":"Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbone","date":"2024-06-24","arxiv_id":"2406.17119","n_code_links":0,"syntology":null},{"paper":null,"slug":"anomaly-detection-of-tabular-data-using-llms","title":"Anomaly Detection of Tabular Data Using LLMs","date":"2024-06-24","arxiv_id":"2406.16308","n_code_links":0,"syntology":null},{"paper":"/paper/attention-instruction-amplifying-attention-in","slug":"attention-instruction-amplifying-attention-in","title":"Attention Instruction: Amplifying Attention in the Middle via Prompting","date":"2024-06-24","arxiv_id":"2406.17095","n_code_links":1,"syntology":null},{"paper":"/paper/building-on-efficient-foundations-effectively","slug":"building-on-efficient-foundations-effectively","title":"Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers","date":"2024-06-24","arxiv_id":"2406.16450","n_code_links":1,"syntology":null},{"paper":null,"slug":"classification-of-geological-borehole","title":"Classification of Geological Borehole Descriptions Using a Domain Adapted Large Language Model","date":"2024-06-24","arxiv_id":"2407.10991","n_code_links":0,"syntology":null},{"paper":null,"slug":"diff3dformer-leveraging-slice-sequence","title":"Diff3Dformer: Leveraging Slice Sequence Diffusion for Enhanced 3D CT Classification with Transformer Networks","date":"2024-06-24","arxiv_id":"2406.17173","n_code_links":0,"syntology":null},{"paper":"/paper/dreambench-a-human-aligned-benchmark-for","slug":"dreambench-a-human-aligned-benchmark-for","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","date":"2024-06-24","arxiv_id":"2406.16855","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":["yuangpeng/dreambench_plus"],"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":"evaluation-of-instruction-following-ability","title":"Evaluation of Instruction-Following Ability for Large Language Models on Story-Ending Generation","date":"2024-06-24","arxiv_id":"2406.16356","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-of-language-models-in-the-medical","slug":"evaluation-of-language-models-in-the-medical","title":"Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings","date":"2024-06-24","arxiv_id":"2406.16611","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-factual-entailment-with-nli-a-news","title":"Exploring Factual Entailment with NLI: A News Media Study","date":"2024-06-24","arxiv_id":"2406.16842","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-fusion-for-human-activity-recognition","title":"Feature Fusion for Human Activity Recognition using Parameter-Optimized Multi-Stage Graph Convolutional Network and Transformer Models","date":"2024-06-24","arxiv_id":"2406.16638","n_code_links":0,"syntology":null},{"paper":"/paper/finding-transformer-circuits-with-edge","slug":"finding-transformer-circuits-with-edge","title":"Finding Transformer Circuits with Edge Pruning","date":"2024-06-24","arxiv_id":"2406.16778","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":3,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/edge-pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/geomformer-a-general-architecture-for","slug":"geomformer-a-general-architecture-for","title":"GeoMFormer: A General Architecture for Geometric Molecular Representation Learning","date":"2024-06-24","arxiv_id":"2406.16853","n_code_links":1,"syntology":null},{"paper":"/paper/gmt-guided-mask-transformer-for-leaf-instance","slug":"gmt-guided-mask-transformer-for-leaf-instance","title":"GMT: Guided Mask Transformer for Leaf Instance Segmentation","date":"2024-06-24","arxiv_id":"2406.17109","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-in-student-assessment","title":"Large Language Models in Student Assessment: Comparing ChatGPT and Human Graders","date":"2024-06-24","arxiv_id":"2406.16510","n_code_links":0,"syntology":null},{"paper":"/paper/make-graph-neural-networks-great-again-a","slug":"make-graph-neural-networks-great-again-a","title":"Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction","date":"2024-06-24","arxiv_id":"2406.16992","n_code_links":1,"syntology":null},{"paper":null,"slug":"metrik-measurement-efficient-randomized","title":"METRIK: Measurement-Efficient Randomized Controlled Trials using Transformers with Input Masking","date":"2024-06-24","arxiv_id":"2406.16351","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-a-novel-dataset-for-testing","title":"modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models","date":"2024-06-24","arxiv_id":"2406.17038","n_code_links":0,"syntology":null},{"paper":"/paper/multi-logieval-towards-evaluating-multi-step","slug":"multi-logieval-towards-evaluating-multi-step","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","date":"2024-06-24","arxiv_id":"2406.17169","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-modal-vision-transformers-for-crop","title":"Multi-Modal Vision Transformers for Crop Mapping from Satellite Image Time Series","date":"2024-06-24","arxiv_id":"2406.16513","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-role-of-long-tail-knowledge-in","title":"On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models","date":"2024-06-24","arxiv_id":"2406.16367","n_code_links":0,"syntology":null},{"paper":"/paper/otce-hybrid-ssm-and-attention-with-cross","slug":"otce-hybrid-ssm-and-attention-with-cross","title":"OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser","date":"2024-06-24","arxiv_id":"2406.16495","n_code_links":1,"syntology":null},{"paper":"/paper/panza-a-personalized-text-writing-assistant","slug":"panza-a-personalized-text-writing-assistant","title":"Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant","date":"2024-06-24","arxiv_id":"2407.10994","n_code_links":1,"syntology":null},{"paper":null,"slug":"plagbench-exploring-the-duality-of-large","title":"PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection","date":"2024-06-24","arxiv_id":"2406.16288","n_code_links":0,"syntology":null},{"paper":null,"slug":"priorformer-a-ugc-vqa-method-with-content-and","title":"Priorformer: A UGC-VQA Method with content and distortion priors","date":"2024-06-24","arxiv_id":"2406.16297","n_code_links":0,"syntology":null},{"paper":"/paper/ragnarok-a-reusable-rag-framework-and","slug":"ragnarok-a-reusable-rag-framework-and","title":"Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","date":"2024-06-24","arxiv_id":"2406.16828","n_code_links":2,"syntology":{"ran":19,"of":23,"n_ran_checked":19,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["castorini/ragnarok"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/the-gpt-writingprompts-dataset-a-comparative","slug":"the-gpt-writingprompts-dataset-a-comparative","title":"The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories","date":"2024-06-24","arxiv_id":"2406.16767","n_code_links":1,"syntology":null},{"paper":"/paper/towards-better-graph-based-cross-document","slug":"towards-better-graph-based-cross-document","title":"Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing","date":"2024-06-24","arxiv_id":"2406.16529","n_code_links":1,"syntology":null},{"paper":"/paper/unambiguous-recognition-should-not-rely","slug":"unambiguous-recognition-should-not-rely","title":"MixTex: Unambiguous Recognition Should Not Rely Solely on Real Data","date":"2024-06-24","arxiv_id":"2406.17148","n_code_links":1,"syntology":null},{"paper":null,"slug":"uno-arena-for-evaluating-sequential-decision","title":"UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models","date":"2024-06-24","arxiv_id":"2406.16382","n_code_links":0,"syntology":null},{"paper":null,"slug":"usdc-a-dataset-of-underline-u-ser-underline-s","title":"USDC: A Dataset of $\\underline{U}$ser $\\underline{S}$tance and $\\underline{D}$ogmatism in Long $\\underline{C}$onversations","date":"2024-06-24","arxiv_id":"2406.16833","n_code_links":0,"syntology":null},{"paper":null,"slug":"venturing-into-uncharted-waters-the","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","date":"2024-06-24","arxiv_id":"2406.16722","n_code_links":0,"syntology":null},{"paper":"/paper/breaking-the-frame-image-retrieval-by-visual","slug":"breaking-the-frame-image-retrieval-by-visual","title":"Breaking the Frame: Visual Place Recognition by Overlap Prediction","date":"2024-06-23","arxiv_id":"2406.16204","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["weitong8591/vop"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"editfollower-tunable-car-following-models-for","title":"EditFollower: Tunable Car Following Models for Customizable Adaptive Cruise Control Systems","date":"2024-06-23","arxiv_id":"2407.02516","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-commentary-strategies-for-imperfect","slug":"enhancing-commentary-strategies-for-imperfect","title":"Enhancing Commentary Strategies for Imperfect Information Card Games: A Study of Large Language Models in Guandan Commentary","date":"2024-06-23","arxiv_id":"2406.17807","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-ensemble-methods-for-news","title":"Evaluating Ensemble Methods for News Recommender Systems","date":"2024-06-23","arxiv_id":"2406.16106","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-the","title":"Evaluating the Effectiveness of the Foundational Models for Q&A Classification in Mental Health care","date":"2024-06-23","arxiv_id":"2406.15966","n_code_links":0,"syntology":null},{"paper":null,"slug":"grapheval2000-benchmarking-and-improving","title":"GraphEval2000: Benchmarking and Improving Large Language Models on Graph Datasets","date":"2024-06-23","arxiv_id":"2406.16176","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-temporal-difference-transformer","title":"Multi-Scale Temporal Difference Transformer for Video-Text Retrieval","date":"2024-06-23","arxiv_id":"2406.16111","n_code_links":0,"syntology":null},{"paper":"/paper/wound-tissue-segmentation-in-diabetic-foot","slug":"wound-tissue-segmentation-in-diabetic-foot","title":"Wound Tissue Segmentation in Diabetic Foot Ulcer Images Using Deep Learning: A Pilot Study","date":"2024-06-23","arxiv_id":"2406.16012","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-speaker-multi-lingual-voice-cloning","title":"A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge","date":"2024-06-22","arxiv_id":"2406.17801","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-individual-facts-investigating","title":"Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models","date":"2024-06-22","arxiv_id":"2406.15940","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-generate-visualizations-with","title":"Can LLMs Generate Visualizations with Dataless Prompts?","date":"2024-06-22","arxiv_id":"2406.17805","n_code_links":0,"syntology":null},{"paper":"/paper/decentralized-transformers-with-centralized","slug":"decentralized-transformers-with-centralized","title":"Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models","date":"2024-06-22","arxiv_id":"2406.15836","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-solar-driver-forecasting-with","slug":"enhancing-solar-driver-forecasting-with","title":"Enhancing Solar Driver Forecasting with Multivariate Transformers","date":"2024-06-22","arxiv_id":"2406.15847","n_code_links":1,"syntology":null},{"paper":"/paper/fast-tree-field-integrators-from-low","slug":"fast-tree-field-integrators-from-low","title":"Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers","date":"2024-06-22","arxiv_id":"2406.15881","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["brcsomnath/fasttreeintegrator"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ladder-a-model-agnostic-framework-boosting","slug":"ladder-a-model-agnostic-framework-boosting","title":"Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level","date":"2024-06-22","arxiv_id":"2406.15741","n_code_links":3,"syntology":{"ran":2,"of":8,"n_ran_checked":0,"n_instrument":2,"unverified":6,"pointer_only":8,"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) · 6 unverified","official":{"repos":["fzp0424/ladder","fzp0424/mt-ladder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}}],"record_sha256":"7c22e10181537ec95ba89c52d8c335756be715e00d908a31633d5a71da376749","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}