{"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/attention/papers/87","list_of":"/method/attention","method":"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":87,"pages_in_order":316,"rows_per_page":100,"rows":[8601,8700],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/86","next":"/method/attention/papers/88","papers":[{"paper":"/paper/tending-towards-stability-convergence","slug":"tending-towards-stability-convergence","title":"Tending Towards Stability: Convergence Challenges in Small Language Models","date":"2024-10-15","arxiv_id":"2410.11451","n_code_links":1,"syntology":null},{"paper":"/paper/teocc-radar-camera-multi-modal-occupancy","slug":"teocc-radar-camera-multi-modal-occupancy","title":"TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement","date":"2024-10-15","arxiv_id":"2410.11228","n_code_links":1,"syntology":null},{"paper":null,"slug":"tokenization-and-morphology-in-multilingual","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","date":"2024-10-15","arxiv_id":"2410.11627","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-fair-graph-representation-learning-in","title":"Towards Fair Graph Representation Learning in Social Networks","date":"2024-10-15","arxiv_id":"2410.11493","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-realistic-evaluation-of-commit","title":"Towards Realistic Evaluation of Commit Message Generation by Matching Online and Offline Settings","date":"2024-10-15","arxiv_id":"2410.12046","n_code_links":0,"syntology":null},{"paper":"/paper/tram-enhancing-user-sleep-prediction-with","slug":"tram-enhancing-user-sleep-prediction-with","title":"TraM : Enhancing User Sleep Prediction with Transformer-based Multivariate Time Series Modeling and Machine Learning Ensembles","date":"2024-10-15","arxiv_id":"2410.11293","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-layer-injection-a-novel-approach","title":"Transformer Layer Injection: A Novel Approach for Efficient Upscaling of Large Language Models","date":"2024-10-15","arxiv_id":"2410.11654","n_code_links":0,"syntology":null},{"paper":null,"slug":"umambatsf-a-u-shaped-multi-scale-long-term","title":"UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba","date":"2024-10-15","arxiv_id":"2410.11278","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-the-mystery-of-visual-attributes-of","slug":"unveiling-the-mystery-of-visual-attributes-of","title":"Unveiling the Mystery of Visual Attributes of Concrete and Abstract Concepts: Variability, Nearest Neighbors, and Challenging Categories","date":"2024-10-15","arxiv_id":"2410.11657","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-fixation-based-retinal-prosthetic","title":"Visual Fixation-Based Retinal Prosthetic Simulation","date":"2024-10-15","arxiv_id":"2410.11688","n_code_links":0,"syntology":null},{"paper":null,"slug":"yolo-ela-efficient-local-attention-modeling","title":"YOLO-ELA: Efficient Local Attention Modeling for High-Performance Real-Time Insulator Defect Detection","date":"2024-10-15","arxiv_id":"2410.11727","n_code_links":0,"syntology":null},{"paper":null,"slug":"4dstylegaussian-zero-shot-4d-style-transfer","title":"4DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splatting","date":"2024-10-14","arxiv_id":"2410.10412","n_code_links":0,"syntology":null},{"paper":"/paper/a-consistency-aware-spot-guided-transformer","slug":"a-consistency-aware-spot-guided-transformer","title":"A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration","date":"2024-10-14","arxiv_id":"2410.10295","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-few-shot-label-unlearning-in-vertical","title":"A few-shot Label Unlearning in Vertical Federated Learning","date":"2024-10-14","arxiv_id":"2410.10922","n_code_links":0,"syntology":null},{"paper":"/paper/an-annotated-dataset-of-errors-in-premodern","slug":"an-annotated-dataset-of-errors-in-premodern","title":"An Annotated Dataset of Errors in Premodern Greek and Baselines for Detecting Them","date":"2024-10-14","arxiv_id":"2410.11071","n_code_links":1,"syntology":null},{"paper":"/paper/audio-captioning-via-generative-pair-to-pair","slug":"audio-captioning-via-generative-pair-to-pair","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","date":"2024-10-14","arxiv_id":"2410.10913","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-rag-question-identification-and-answer","title":"Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations","date":"2024-10-14","arxiv_id":"2410.10136","n_code_links":0,"syntology":null},{"paper":null,"slug":"big-little-vision-transformer-for-efficient","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","date":"2024-10-14","arxiv_id":"2410.10267","n_code_links":0,"syntology":null},{"paper":null,"slug":"cavia-camera-controllable-multi-view-video","title":"Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention","date":"2024-10-14","arxiv_id":"2410.10774","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-mixer-ya-nahi-novel-approaches-to","title":"Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities","date":"2024-10-14","arxiv_id":"2410.11079","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-of-deep-learning-and-conventional","title":"Comparison of deep learning and conventional methods for disease onset prediction","date":"2024-10-14","arxiv_id":"2410.10505","n_code_links":0,"syntology":null},{"paper":"/paper/customize-your-visual-autoregressive-recipe","slug":"customize-your-visual-autoregressive-recipe","title":"Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling","date":"2024-10-14","arxiv_id":"2410.10511","n_code_links":1,"syntology":null},{"paper":null,"slug":"dissecting-embedding-method-learning-higher","title":"Dissecting embedding method: learning higher-order structures from data","date":"2024-10-14","arxiv_id":"2410.10917","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-we-need-more-complex-representations-for","title":"Do we need more complex representations for structure? A comparison of note duration representation for Music Transformers","date":"2024-10-14","arxiv_id":"2410.10515","n_code_links":0,"syntology":null},{"paper":"/paper/double-jeopardy-and-climate-impact-in-the-use","slug":"double-jeopardy-and-climate-impact-in-the-use","title":"Double Jeopardy and Climate Impact in the Use of Large Language Models: Socio-economic Disparities and Reduced Utility for Non-English Speakers","date":"2024-10-14","arxiv_id":"2410.10665","n_code_links":1,"syntology":null},{"paper":null,"slug":"drivingdojo-dataset-advancing-interactive-and","title":"DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model","date":"2024-10-14","arxiv_id":"2410.10738","n_code_links":0,"syntology":null},{"paper":"/paper/duoattention-efficient-long-context-llm","slug":"duoattention-efficient-long-context-llm","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","date":"2024-10-14","arxiv_id":"2410.10819","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["mit-han-lab/duo-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/easyrag-efficient-retrieval-augmented","slug":"easyrag-efficient-retrieval-augmented","title":"EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations","date":"2024-10-14","arxiv_id":"2410.10315","n_code_links":1,"syntology":null},{"paper":null,"slug":"embedding-self-correction-as-an-inherent","title":"Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning","date":"2024-10-14","arxiv_id":"2410.10735","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-attributed-graph-networks-with","slug":"enhancing-attributed-graph-networks-with","title":"Enhancing Attributed Graph Networks with Alignment and Uniformity Constraints for Session-based Recommendation","date":"2024-10-14","arxiv_id":"2410.10296","n_code_links":1,"syntology":null},{"paper":null,"slug":"et-former-efficient-triplane-deformable","title":"ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera","date":"2024-10-14","arxiv_id":"2410.11019","n_code_links":0,"syntology":null},{"paper":"/paper/fasterdit-towards-faster-diffusion","slug":"fasterdit-towards-faster-diffusion","title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","date":"2024-10-14","arxiv_id":"2410.10356","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 6 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) · 4 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/formalalign-automated-alignment-evaluation","slug":"formalalign-automated-alignment-evaluation","title":"FormalAlign: Automated Alignment Evaluation for Autoformalization","date":"2024-10-14","arxiv_id":"2410.10135","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rookie-joe/formalalign"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fsos-amc-few-shot-open-set-learning-for","title":"FSOS-AMC: Few-Shot Open-Set Learning for Automatic Modulation Classification","date":"2024-10-14","arxiv_id":"2410.10265","n_code_links":0,"syntology":null},{"paper":null,"slug":"funnelrag-a-coarse-to-fine-progressive","title":"FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG","date":"2024-10-14","arxiv_id":"2410.10293","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-bias-of-llm-in-economics-an","title":"Gender Bias of LLM in Economics: An Existentialism Perspective","date":"2024-10-14","arxiv_id":"2410.19775","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-and-its-impact-on-personalized","title":"Generative AI and Its Impact on Personalized Intelligent Tutoring Systems","date":"2024-10-14","arxiv_id":"2410.10650","n_code_links":0,"syntology":null},{"paper":"/paper/graph-of-records-boosting-retrieval-augmented","slug":"graph-of-records-boosting-retrieval-augmented","title":"Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs","date":"2024-10-14","arxiv_id":"2410.11001","n_code_links":1,"syntology":null},{"paper":"/paper/graphclip-enhancing-transferability-in-graph","slug":"graphclip-enhancing-transferability-in-graph","title":"GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs","date":"2024-10-14","arxiv_id":"2410.10329","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["zhuyun97/graphclip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/hart-efficient-visual-generation-with-hybrid","slug":"hart-efficient-visual-generation-with-hybrid","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","date":"2024-10-14","arxiv_id":"2410.10812","n_code_links":2,"syntology":{"ran":23,"of":27,"n_ran_checked":15,"n_instrument":8,"unverified":4,"pointer_only":4,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","official":{"repos":["mit-han-lab/hart","FoundationVision/VAR"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hsr-enhanced-sparse-attention-acceleration","title":"HSR-Enhanced Sparse Attention Acceleration","date":"2024-10-14","arxiv_id":"2410.10165","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-transformer-for-early-alzheimer-s","title":"Hybrid Transformer for Early Alzheimer's Detection: Integration of Handwriting-Based 2D Images and 1D Signal Features","date":"2024-10-14","arxiv_id":"2410.10547","n_code_links":0,"syntology":null},{"paper":"/paper/interaction-guided-two-branch-image-dehazing","slug":"interaction-guided-two-branch-image-dehazing","title":"Interaction-Guided Two-Branch Image Dehazing Network","date":"2024-10-14","arxiv_id":"2410.10121","n_code_links":1,"syntology":null},{"paper":"/paper/kblam-knowledge-base-augmented-language-model","slug":"kblam-knowledge-base-augmented-language-model","title":"KBLaM: Knowledge Base augmented Language Model","date":"2024-10-14","arxiv_id":"2410.10450","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":8,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/KBLaM"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knn-transformer-with-pyramid-prompts-for-few","title":"KNN Transformer with Pyramid Prompts for Few-Shot Learning","date":"2024-10-14","arxiv_id":"2410.10227","n_code_links":0,"syntology":null},{"paper":null,"slug":"lambda-skip-connections-the-architectural","title":"Lambda-Skip Connections: the architectural component that prevents Rank Collapse","date":"2024-10-14","arxiv_id":"2410.10609","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-linear-attention-in-polynomial-time","title":"Learning Linear Attention in Polynomial Time","date":"2024-10-14","arxiv_id":"2410.10101","n_code_links":0,"syntology":null},{"paper":null,"slug":"lkaseg-remote-sensing-image-semantic","title":"LKASeg:Remote-Sensing Image Semantic Segmentation with Large Kernel Attention and Full-Scale Skip Connections","date":"2024-10-14","arxiv_id":"2410.10433","n_code_links":0,"syntology":null},{"paper":"/paper/lolcats-on-low-rank-linearizing-of-large","slug":"lolcats-on-low-rank-linearizing-of-large","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10254","n_code_links":1,"syntology":{"ran":23,"of":32,"n_ran_checked":13,"n_instrument":10,"unverified":9,"pointer_only":0,"phrase":"23 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","official":{"repos":["hazyresearch/lolcats"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":9,"n_ran_no_instrument_failure":13,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/magiceraser-erasing-any-objects-via-semantics","slug":"magiceraser-erasing-any-objects-via-semantics","title":"MagicEraser: Erasing Any Objects via Semantics-Aware Control","date":"2024-10-14","arxiv_id":"2410.10207","n_code_links":1,"syntology":null},{"paper":"/paper/on-calibration-of-llm-based-guard-models-for","slug":"on-calibration-of-llm-based-guard-models-for","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","date":"2024-10-14","arxiv_id":"2410.10414","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["waffle-liu/calibration_guard_model"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/one-language-many-gaps-evaluating-dialect","slug":"one-language-many-gaps-evaluating-dialect","title":"One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks","date":"2024-10-14","arxiv_id":"2410.11005","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["fangru-lin/redial_dialect_robustness_fairness"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/out-of-bounding-box-triggers-a-stealthy","slug":"out-of-bounding-box-triggers-a-stealthy","title":"Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors","date":"2024-10-14","arxiv_id":"2410.10091","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lintotao/out-of-bbox-attack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"parameterize-structure-with-differentiable","title":"Parameterize Structure with Differentiable Template for 3D Shape Generation","date":"2024-10-14","arxiv_id":"2410.10399","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-deep-learning-and","title":"Performance Evaluation of Deep Learning and Transformer Models Using Multimodal Data for Breast Cancer Classification","date":"2024-10-14","arxiv_id":"2410.10146","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-in-a-dialectal-profiling-task-of","title":"Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese","date":"2024-10-14","arxiv_id":"2410.10991","n_code_links":0,"syntology":null},{"paper":"/paper/pointnet-with-kan-versus-pointnet-with-mlp","slug":"pointnet-with-kan-versus-pointnet-with-mlp","title":"PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets","date":"2024-10-14","arxiv_id":"2410.10084","n_code_links":1,"syntology":null},{"paper":null,"slug":"pubic-symphysis-fetal-head-segmentation","title":"Pubic Symphysis-Fetal Head Segmentation Network Using BiFormer Attention Mechanism and Multipath Dilated Convolution","date":"2024-10-14","arxiv_id":"2410.10352","n_code_links":0,"syntology":null},{"paper":"/paper/queryable-prototype-multiple-instance","slug":"queryable-prototype-multiple-instance","title":"Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification","date":"2024-10-14","arxiv_id":"2410.10573","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-legal-judgement-prediction-in-a","slug":"rethinking-legal-judgement-prediction-in-a","title":"Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10542","n_code_links":1,"syntology":null},{"paper":null,"slug":"reverse-refinement-network-for-narrow-rural","title":"Reverse Refinement Network for Narrow Rural Road Detection in High-Resolution Satellite Imagery","date":"2024-10-14","arxiv_id":"2410.10389","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-and-benchmarking-graph","slug":"revisiting-and-benchmarking-graph","title":"Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective","date":"2024-10-14","arxiv_id":"2410.10241","n_code_links":1,"syntology":null},{"paper":null,"slug":"roa-bev-2d-region-oriented-attention-for-bev","title":"ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object","date":"2024-10-14","arxiv_id":"2410.10298","n_code_links":0,"syntology":null},{"paper":"/paper/rocoft-efficient-finetuning-of-large-language","slug":"rocoft-efficient-finetuning-of-large-language","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","date":"2024-10-14","arxiv_id":"2410.10075","n_code_links":1,"syntology":null},{"paper":null,"slug":"saliency-guided-optimization-of-diffusion","title":"Saliency Guided Optimization of Diffusion Latents","date":"2024-10-14","arxiv_id":"2410.10257","n_code_links":0,"syntology":null},{"paper":"/paper/sana-efficient-high-resolution-image","slug":"sana-efficient-high-resolution-image","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","date":"2024-10-14","arxiv_id":"2410.10629","n_code_links":2,"syntology":null},{"paper":null,"slug":"slanc-static-layernorm-calibration","title":"SLaNC: Static LayerNorm Calibration","date":"2024-10-14","arxiv_id":"2410.10553","n_code_links":0,"syntology":null},{"paper":null,"slug":"stackfeed-structured-textual-actor-critic","title":"STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack","date":"2024-10-14","arxiv_id":"2410.10584","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-ingredients-for-robotic-diffusion","title":"The Ingredients for Robotic Diffusion Transformers","date":"2024-10-14","arxiv_id":"2410.10088","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-multi-head-attention-via","slug":"towards-better-multi-head-attention-via","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","date":"2024-10-14","arxiv_id":"2410.10914","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"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) · 3 unverified","official":{"repos":["dashenzi721/csp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transforming-game-play-a-comparative-study-of","title":"Transforming Game Play: A Comparative Study of DCQN and DTQN Architectures in Reinforcement Learning","date":"2024-10-14","arxiv_id":"2410.10660","n_code_links":0,"syntology":null},{"paper":"/paper/transparent-networks-for-multivariate-time","slug":"transparent-networks-for-multivariate-time","title":"Transparent Networks for Multivariate Time Series","date":"2024-10-14","arxiv_id":"2410.10535","n_code_links":1,"syntology":null},{"paper":"/paper/v2m-visual-2-dimensional-mamba-for-image","slug":"v2m-visual-2-dimensional-mamba-for-image","title":"V2M: Visual 2-Dimensional Mamba for Image Representation Learning","date":"2024-10-14","arxiv_id":"2410.10382","n_code_links":1,"syntology":null},{"paper":"/paper/visrag-vision-based-retrieval-augmented","slug":"visrag-vision-based-retrieval-augmented","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","date":"2024-10-14","arxiv_id":"2410.10594","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openbmb/visrag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/watching-the-watchers-exposing-gender","slug":"watching-the-watchers-exposing-gender","title":"Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation","date":"2024-10-14","arxiv_id":"2410.10995","n_code_links":1,"syntology":null},{"paper":"/paper/what-does-it-mean-to-be-a-transformer","slug":"what-does-it-mean-to-be-a-transformer","title":"What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis","date":"2024-10-14","arxiv_id":"2410.10986","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dalab/transformer-hessian"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/when-attention-sink-emerges-in-language","slug":"when-attention-sink-emerges-in-language","title":"When Attention Sink Emerges in Language Models: An Empirical View","date":"2024-10-14","arxiv_id":"2410.10781","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/attention-sink"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/will-llms-replace-the-encoder-only-models-in","slug":"will-llms-replace-the-encoder-only-models-in","title":"Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?","date":"2024-10-14","arxiv_id":"2410.10476","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["brownfortress/llms-trc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"3ds-decomposed-difficulty-data-selection-s","title":"3DS: Decomposed Difficulty Data Selection's Case Study on LLM Medical Domain Adaptation","date":"2024-10-13","arxiv_id":"2410.10901","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-pdf-parsing-tools","title":"A Comparative Study of PDF Parsing Tools Across Diverse Document Categories","date":"2024-10-13","arxiv_id":"2410.09871","n_code_links":0,"syntology":null},{"paper":null,"slug":"bidora-bi-level-optimization-based-weight","title":"BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation","date":"2024-10-13","arxiv_id":"2410.09758","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-in-context-learning-really-generalize-to","title":"Can In-context Learning Really Generalize to Out-of-distribution Tasks?","date":"2024-10-13","arxiv_id":"2410.09695","n_code_links":0,"syntology":null},{"paper":null,"slug":"collu-bench-a-benchmark-for-predicting","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","date":"2024-10-13","arxiv_id":"2410.09997","n_code_links":0,"syntology":null},{"paper":"/paper/dag-aware-transformer-for-causal-effect","slug":"dag-aware-transformer-for-causal-effect","title":"DAG-aware Transformer for Causal Effect Estimation","date":"2024-10-13","arxiv_id":"2410.10044","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-adaptive-few-shot-multi-label","title":"Data Adaptive Few-shot Multi Label Segmentation with Foundation Model","date":"2024-10-13","arxiv_id":"2410.09759","n_code_links":0,"syntology":null},{"paper":null,"slug":"dualformer-controllable-fast-and-slow","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","date":"2024-10-13","arxiv_id":"2410.09918","n_code_links":0,"syntology":null},{"paper":"/paper/easyjudge-an-easy-to-use-tool-for","slug":"easyjudge-an-easy-to-use-tool-for","title":"EasyJudge: an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs","date":"2024-10-13","arxiv_id":"2410.09775","n_code_links":1,"syntology":null},{"paper":null,"slug":"ebdm-exemplar-guided-image-translation-with","title":"EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models","date":"2024-10-13","arxiv_id":"2410.09802","n_code_links":0,"syntology":null},{"paper":null,"slug":"echoprime-a-multi-video-view-informed-vision","title":"EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation","date":"2024-10-13","arxiv_id":"2410.09704","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-dysarthric-speech-leveraging","title":"Empowering Dysarthric Speech: Leveraging Advanced LLMs for Accurate Speech Correction and Multimodal Emotion Analysis","date":"2024-10-13","arxiv_id":"2410.12867","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-bias-of-llms-in-making","title":"Evaluating Gender Bias of LLMs in Making Morality Judgements","date":"2024-10-13","arxiv_id":"2410.09992","n_code_links":0,"syntology":null},{"paper":"/paper/hardmath-a-benchmark-dataset-for-challenging","slug":"hardmath-a-benchmark-dataset-for-challenging","title":"HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics","date":"2024-10-13","arxiv_id":"2410.09988","n_code_links":1,"syntology":null},{"paper":"/paper/hasn-hybrid-attention-separable-network-for","slug":"hasn-hybrid-attention-separable-network-for","title":"HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution","date":"2024-10-13","arxiv_id":"2410.09844","n_code_links":1,"syntology":null},{"paper":null,"slug":"honest-ai-fine-tuning-small-language-models","title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","date":"2024-10-13","arxiv_id":"2410.09699","n_code_links":0,"syntology":null},{"paper":"/paper/intermask-3d-human-interaction-generation-via","slug":"intermask-3d-human-interaction-generation-via","title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modelling","date":"2024-10-13","arxiv_id":"2410.10010","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-implicit-bias-in-large-language","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","date":"2024-10-13","arxiv_id":"2410.12864","n_code_links":0,"syntology":null},{"paper":"/paper/joint-mixing-data-augmentation-for-skeleton","slug":"joint-mixing-data-augmentation-for-skeleton","title":"Joint Mixing Data Augmentation for Skeleton-based Action Recognition","date":"2024-10-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/learning-pattern-specific-experts-for-time","slug":"learning-pattern-specific-experts-for-time","title":"Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift","date":"2024-10-13","arxiv_id":"2410.09836","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-rank-for-multiple-retrieval","title":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","date":"2024-10-13","arxiv_id":"2410.09942","n_code_links":0,"syntology":null},{"paper":"/paper/libeer-a-comprehensive-benchmark-and","slug":"libeer-a-comprehensive-benchmark-and","title":"LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-based Emotion Recognition","date":"2024-10-13","arxiv_id":"2410.09767","n_code_links":2,"syntology":null}],"record_sha256":"d8269d6c526fe89b36a56607d585ce34e5de7b9aee7a7493b8ef2820c1b43228","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}