{"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/146","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":146,"pages_in_order":316,"rows_per_page":100,"rows":[14501,14600],"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/145","next":"/method/attention/papers/147","papers":[{"paper":"/paper/scene-adaptive-sparse-transformer-for-event","slug":"scene-adaptive-sparse-transformer-for-event","title":"Scene Adaptive Sparse Transformer for Event-based Object Detection","date":"2024-04-02","arxiv_id":"2404.01882","n_code_links":1,"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":["peterande/sast"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/sgsh-stimulate-large-language-models-with","slug":"sgsh-stimulate-large-language-models-with","title":"SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation","date":"2024-04-02","arxiv_id":"2404.01923","n_code_links":1,"syntology":null},{"paper":"/paper/spmamba-state-space-model-is-all-you-need-in","slug":"spmamba-state-space-model-is-all-you-need-in","title":"SPMamba: State-space model is all you need in speech separation","date":"2024-04-02","arxiv_id":"2404.02063","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jusperlee/spmamba"],"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/toward-informal-language-processing-knowledge","slug":"toward-informal-language-processing-knowledge","title":"Toward Informal Language Processing: Knowledge of Slang in Large Language Models","date":"2024-04-02","arxiv_id":"2404.02323","n_code_links":1,"syntology":null},{"paper":"/paper/wcdt-world-centric-diffusion-transformer-for","slug":"wcdt-world-centric-diffusion-transformer-for","title":"WcDT: World-centric Diffusion Transformer for Traffic Scene Generation","date":"2024-04-02","arxiv_id":"2404.02082","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["yangchen1997/wcdt"],"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":"action-detection-via-an-image-diffusion","title":"Action Detection via an Image Diffusion Process","date":"2024-04-01","arxiv_id":"2404.01051","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-ai-with-integrity-ethical","title":"Advancing AI with Integrity: Ethical Challenges and Solutions in Neural Machine Translation","date":"2024-04-01","arxiv_id":"2404.01070","n_code_links":0,"syntology":null},{"paper":"/paper/aragog-advanced-rag-output-grading","slug":"aragog-advanced-rag-output-grading","title":"ARAGOG: Advanced RAG Output Grading","date":"2024-04-01","arxiv_id":"2404.01037","n_code_links":1,"syntology":null},{"paper":null,"slug":"artificial-intelligence-and-the-spatial","title":"Artificial Intelligence and the Spatial Documentation of Languages","date":"2024-04-01","arxiv_id":"2404.01263","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-assessment-of-encouragement-and","title":"Automated Assessment of Encouragement and Warmth in Classrooms Leveraging Multimodal Emotional Features and ChatGPT","date":"2024-04-01","arxiv_id":"2404.15310","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-enhanced-retrieval-tool-for-homework","title":"BERT-Enhanced Retrieval Tool for Homework Plagiarism Detection System","date":"2024-04-01","arxiv_id":"2404.01582","n_code_links":0,"syntology":null},{"paper":"/paper/can-biases-in-imagenet-models-explain","slug":"can-biases-in-imagenet-models-explain","title":"Can Biases in ImageNet Models Explain Generalization?","date":"2024-04-01","arxiv_id":"2404.01509","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"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) · 3 unverified","official":{"repos":["paulgavrikov/biases_vs_generalization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cmt-cross-modulation-transformer-with-hybrid","title":"CMT: Cross Modulation Transformer with Hybrid Loss for Pansharpening","date":"2024-04-01","arxiv_id":"2404.01121","n_code_links":0,"syntology":null},{"paper":"/paper/fables-evaluating-faithfulness-and-content","slug":"fables-evaluating-faithfulness-and-content","title":"FABLES: Evaluating faithfulness and content selection in book-length summarization","date":"2024-04-01","arxiv_id":"2404.01261","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mungg/fables"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/flare-free-vision-empowering-uformer-with","slug":"flare-free-vision-empowering-uformer-with","title":"Flare-Free Vision: Empowering Uformer with Depth Insights","date":"2024-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"forklift-an-extensible-neural-lifter","title":"Forklift: An Extensible Neural Lifter","date":"2024-04-01","arxiv_id":"2404.16041","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-robustness-of-open-vocabulary","title":"Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts","date":"2024-04-01","arxiv_id":"2405.14874","n_code_links":0,"syntology":null},{"paper":null,"slug":"isobench-benchmarking-multimodal-foundation","title":"IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations","date":"2024-04-01","arxiv_id":"2404.01266","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-motion-model-for-unified-multi-modal","title":"Large Motion Model for Unified Multi-Modal Motion Generation","date":"2024-04-01","arxiv_id":"2404.01284","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-radjudge-achieving-radiologist-level","title":"LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation","date":"2024-04-01","arxiv_id":"2404.00998","n_code_links":0,"syntology":null},{"paper":"/paper/nerf-mae-masked-autoencoders-for-self","slug":"nerf-mae-masked-autoencoders-for-self","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","date":"2024-04-01","arxiv_id":"2404.01300","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zubair-irshad/NeRF-MAE"],"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":null,"slug":"on-the-faithfulness-of-vision-transformer","title":"On the Faithfulness of Vision Transformer Explanations","date":"2024-04-01","arxiv_id":"2404.01415","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-learning-for-oriented-power","title":"Prompt Learning for Oriented Power Transmission Tower Detection in High-Resolution SAR Images","date":"2024-04-01","arxiv_id":"2404.01074","n_code_links":0,"syntology":null},{"paper":null,"slug":"securing-social-spaces-harnessing-deep","title":"Securing Social Spaces: Harnessing Deep Learning to Eradicate Cyberbullying","date":"2024-04-01","arxiv_id":"2404.03686","n_code_links":0,"syntology":null},{"paper":"/paper/structured-initialization-for-attention-in","slug":"structured-initialization-for-attention-in","title":"Structured Initialization for Attention in Vision Transformers","date":"2024-04-01","arxiv_id":"2404.01139","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-curious-case-of-a31p-a-topology-switching","title":"The curious case of A31P, a topology-switching mutant of the Repressor of Primer protein : A molecular dynamics study of its folding and misfolding","date":"2024-04-01","arxiv_id":"2404.01405","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-divergent-inductive-biases-of-llms","slug":"unveiling-divergent-inductive-biases-of-llms","title":"Unveiling Divergent Inductive Biases of LLMs on Temporal Data","date":"2024-04-01","arxiv_id":"2404.01453","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-language-models-for-decoding-provider","title":"Vision-language models for decoding provider attention during neonatal resuscitation","date":"2024-04-01","arxiv_id":"2404.01207","n_code_links":0,"syntology":null},{"paper":"/paper/a-general-and-efficient-training-for","slug":"a-general-and-efficient-training-for","title":"A General and Efficient Training for Transformer via Token Expansion","date":"2024-03-31","arxiv_id":"2404.00672","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":3,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["osilly/tokenexpansion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-theory-for-length-generalization-in","title":"A Theory for Length Generalization in Learning to Reason","date":"2024-03-31","arxiv_id":"2404.00560","n_code_links":0,"syntology":null},{"paper":null,"slug":"algorithmic-collusion-by-large-language","title":"Algorithmic Collusion by Large Language Models","date":"2024-03-31","arxiv_id":"2404.00806","n_code_links":0,"syntology":null},{"paper":"/paper/chops-chat-with-customer-profile-systems-for","slug":"chops-chat-with-customer-profile-systems-for","title":"CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs","date":"2024-03-31","arxiv_id":"2404.01343","n_code_links":1,"syntology":null},{"paper":"/paper/couda-coherence-evaluation-via-unified-data","slug":"couda-coherence-evaluation-via-unified-data","title":"CoUDA: Coherence Evaluation via Unified Data Augmentation","date":"2024-03-31","arxiv_id":"2404.00681","n_code_links":1,"syntology":null},{"paper":"/paper/dmssn-distilled-mixed-spectral-spatial","slug":"dmssn-distilled-mixed-spectral-spatial","title":"DMSSN: Distilled Mixed Spectral-Spatial Network for Hyperspectral Salient Object Detection","date":"2024-03-31","arxiv_id":"2404.00694","n_code_links":1,"syntology":null},{"paper":"/paper/drct-saving-image-super-resolution-away-from","slug":"drct-saving-image-super-resolution-away-from","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","date":"2024-03-31","arxiv_id":"2404.00722","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":3,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ming053l/drct"],"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","unlocated"]}}},{"paper":"/paper/dual-detrs-for-multi-label-temporal-action","slug":"dual-detrs-for-multi-label-temporal-action","title":"Dual DETRs for Multi-Label Temporal Action Detection","date":"2024-03-31","arxiv_id":"2404.00653","n_code_links":0,"syntology":null},{"paper":"/paper/evocodebench-an-evolving-code-generation","slug":"evocodebench-an-evolving-code-generation","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-03-31","arxiv_id":"2404.00599","n_code_links":1,"syntology":{"ran":15,"of":15,"n_ran_checked":14,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["seketeam/evocodebench"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/extracting-social-determinants-of-health-from","slug":"extracting-social-determinants-of-health-from","title":"Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods","date":"2024-03-31","arxiv_id":"2404.00826","n_code_links":1,"syntology":null},{"paper":"/paper/how-much-are-llms-contaminated-a","slug":"how-much-are-llms-contaminated-a","title":"How Much are Large Language Models Contaminated? A Comprehensive Survey and the LLMSanitize Library","date":"2024-03-31","arxiv_id":"2404.00699","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ntunlp/llmsanitize"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/ktpformer-kinematics-and-trajectory-prior","slug":"ktpformer-kinematics-and-trajectory-prior","title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","date":"2024-03-31","arxiv_id":"2404.00658","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":5,"n_instrument":1,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["JihuaPeng/KTPFormer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mugennet-a-novel-combined-convolution-neural","title":"MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with its Application for Colonic Polyp Image Segmentation","date":"2024-03-31","arxiv_id":"2404.00726","n_code_links":0,"syntology":null},{"paper":null,"slug":"observations-on-building-rag-systems-for","title":"Observations on Building RAG Systems for Technical Documents","date":"2024-03-31","arxiv_id":"2404.00657","n_code_links":0,"syntology":null},{"paper":"/paper/on-difficulties-of-attention-factorization","slug":"on-difficulties-of-attention-factorization","title":"On Difficulties of Attention Factorization through Shared Memory","date":"2024-03-31","arxiv_id":"2404.00798","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":0,"n_instrument":3,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["vladyorsh/lra_efficient_transformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"revealing-trends-in-datasets-from-the-2022","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","date":"2024-03-31","arxiv_id":"2404.08666","n_code_links":0,"syntology":null},{"paper":"/paper/rq-rag-learning-to-refine-queries-for","slug":"rq-rag-learning-to-refine-queries-for","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","date":"2024-03-31","arxiv_id":"2404.00610","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-free-semantic-segmentation-via-llm","title":"Training-Free Semantic Segmentation via LLM-Supervision","date":"2024-03-31","arxiv_id":"2404.00701","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-pluralistic-image","slug":"transformer-based-pluralistic-image","title":"Transformer based Pluralistic Image Completion with Reduced Information Loss","date":"2024-03-31","arxiv_id":"2404.00513","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-on-nlp-data","title":"A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs","date":"2024-03-30","arxiv_id":"2404.00303","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-feature-map-enhancement-technique","title":"A Novel Feature Map Enhancement Technique Integrating Residual CNN and Transformer for Alzheimer Diseases Diagnosis","date":"2024-03-30","arxiv_id":"2405.12986","n_code_links":0,"syntology":null},{"paper":"/paper/can-llms-master-math-investigating-large","slug":"can-llms-master-math-investigating-large","title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","date":"2024-03-30","arxiv_id":"2404.00344","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["gipplab/llm-investig-mathstackexchange"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dependability-evaluation-of-stable-diffusion","title":"Dependability Evaluation of Stable Diffusion with Soft Errors on the Model Parameters","date":"2024-03-30","arxiv_id":"2404.00352","n_code_links":0,"syntology":null},{"paper":"/paper/edinburgh-clinical-nlp-at-semeval-2024-task-2","slug":"edinburgh-clinical-nlp-at-semeval-2024-task-2","title":"Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4","date":"2024-03-30","arxiv_id":"2404.00484","n_code_links":1,"syntology":null},{"paper":null,"slug":"injecting-new-knowledge-into-large-language","title":"Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning","date":"2024-03-30","arxiv_id":"2404.00213","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-pre-trained-and-transformer","title":"Leveraging Pre-trained and Transformer-derived Embeddings from EHRs to Characterize Heterogeneity Across Alzheimer's Disease and Related Dementias","date":"2024-03-30","arxiv_id":"2404.00464","n_code_links":0,"syntology":null},{"paper":"/paper/small-language-models-learn-enhanced","slug":"small-language-models-learn-enhanced","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","date":"2024-03-30","arxiv_id":"2404.00376","n_code_links":0,"syntology":null},{"paper":null,"slug":"spread-your-wings-a-radial-strip-transformer","title":"Spread Your Wings: A Radial Strip Transformer for Image Deblurring","date":"2024-03-30","arxiv_id":"2404.00358","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-parallel-attention-network-for-cattle-face","title":"A Parallel Attention Network for Cattle Face Recognition","date":"2024-03-29","arxiv_id":"2403.19980","n_code_links":0,"syntology":null},{"paper":"/paper/agileformer-spatially-agile-transformer-unet","slug":"agileformer-spatially-agile-transformer-unet","title":"AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation","date":"2024-03-29","arxiv_id":"2404.00122","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-v-s-media-bias-a-comparative-study-of","title":"ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models","date":"2024-03-29","arxiv_id":"2403.20158","n_code_links":0,"syntology":null},{"paper":"/paper/classifying-conspiratorial-narratives-at","slug":"classifying-conspiratorial-narratives-at","title":"Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connections","date":"2024-03-29","arxiv_id":"2404.00141","n_code_links":1,"syntology":null},{"paper":null,"slug":"dataagent-evaluating-large-language-models","title":"DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries","date":"2024-03-29","arxiv_id":"2404.00188","n_code_links":0,"syntology":null},{"paper":"/paper/decision-mamba-reinforcement-learning-via","slug":"decision-mamba-reinforcement-learning-via","title":"Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces","date":"2024-03-29","arxiv_id":"2403.19925","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":1,"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":["toshihiro-ota/decision-mamba"],"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":"/paper/dijiang-efficient-large-language-models","slug":"dijiang-efficient-large-language-models","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","date":"2024-03-29","arxiv_id":"2403.19928","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuchuantian/dijiang"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-the-general-agent-capabilities-of","slug":"enhancing-the-general-agent-capabilities-of","title":"Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning","date":"2024-03-29","arxiv_id":"2403.19962","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["haiv-lab/llm-tmbr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/latxa-an-open-language-model-and-evaluation","slug":"latxa-an-open-language-model-and-evaluation","title":"Latxa: An Open Language Model and Evaluation Suite for Basque","date":"2024-03-29","arxiv_id":"2403.20266","n_code_links":1,"syntology":null},{"paper":null,"slug":"layernorm-a-key-component-in-parameter","title":"LayerNorm: A key component in parameter-efficient fine-tuning","date":"2024-03-29","arxiv_id":"2403.20284","n_code_links":0,"syntology":null},{"paper":"/paper/localising-the-seizure-onset-zone-from-single","slug":"localising-the-seizure-onset-zone-from-single","title":"Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a CNN Transformer","date":"2024-03-29","arxiv_id":"2403.20324","n_code_links":1,"syntology":null},{"paper":"/paper/mango-a-benchmark-for-evaluating-mapping-and","slug":"mango-a-benchmark-for-evaluating-mapping-and","title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","date":"2024-03-29","arxiv_id":"2403.19913","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["oaklight/mango"],"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/on-the-fly-definition-augmentation-of-llms","slug":"on-the-fly-definition-augmentation-of-llms","title":"On-the-fly Definition Augmentation of LLMs for Biomedical NER","date":"2024-03-29","arxiv_id":"2404.00152","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":["allenai/beacon"],"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":"realm-reference-resolution-as-language","title":"ReALM: Reference Resolution As Language Modeling","date":"2024-03-29","arxiv_id":"2403.20329","n_code_links":0,"syntology":null},{"paper":"/paper/scenetracker-long-term-scene-flow-estimation","slug":"scenetracker-long-term-scene-flow-estimation","title":"SceneTracker: Long-term Scene Flow Estimation Network","date":"2024-03-29","arxiv_id":"2403.19924","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":["wwsource/scenetracker"],"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/shallow-cross-encoders-for-low-latency","slug":"shallow-cross-encoders-for-low-latency","title":"Shallow Cross-Encoders for Low-Latency Retrieval","date":"2024-03-29","arxiv_id":"2403.20222","n_code_links":1,"syntology":null},{"paper":null,"slug":"tdanet-a-novel-temporal-denoise-convolutional","title":"TDANet: A Novel Temporal Denoise Convolutional Neural Network With Attention for Fault Diagnosis","date":"2024-03-29","arxiv_id":"2403.19943","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-stochastic-transformer-based-approach","title":"A Novel Stochastic Transformer-based Approach for Post-Traumatic Stress Disorder Detection using Audio Recording of Clinical Interviews","date":"2024-03-28","arxiv_id":"2403.19441","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-review-of-multi-modal-large-language-and","title":"A Review of Multi-Modal Large Language and Vision Models","date":"2024-03-28","arxiv_id":"2404.01322","n_code_links":0,"syntology":null},{"paper":"/paper/aapmt-agi-assessment-through-prompt-and","slug":"aapmt-agi-assessment-through-prompt-and","title":"AAPMT: AGI Assessment Through Prompt and Metric Transformer","date":"2024-03-28","arxiv_id":"2403.19101","n_code_links":1,"syntology":null},{"paper":null,"slug":"alloybert-alloy-property-prediction-with","title":"AlloyBERT: Alloy Property Prediction with Large Language Models","date":"2024-03-28","arxiv_id":"2403.19783","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-good-at-utility","slug":"are-large-language-models-good-at-utility","title":"Are Large Language Models Good at Utility Judgments?","date":"2024-03-28","arxiv_id":"2403.19216","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"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) · 4 unverified","official":{"repos":["ict-bigdatalab/utility_judgments"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"checkpoint-merging-via-bayesian-optimization","title":"Checkpoint Merging via Bayesian Optimization in LLM Pretraining","date":"2024-03-28","arxiv_id":"2403.19390","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-comparison-tuning-for-code-large","title":"Code Comparison Tuning for Code Large Language Models","date":"2024-03-28","arxiv_id":"2403.19121","n_code_links":0,"syntology":null},{"paper":"/paper/densenets-reloaded-paradigm-shift-beyond","slug":"densenets-reloaded-paradigm-shift-beyond","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","date":"2024-03-28","arxiv_id":"2403.19588","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huggingface/pytorch-image-models","naver-ai/rdnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-efficiency-in-vision-transformer","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","date":"2024-03-28","arxiv_id":"2403.19882","n_code_links":0,"syntology":null},{"paper":null,"slug":"factoid-factual-entailment-for-hallucination","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","date":"2024-03-28","arxiv_id":"2403.19113","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-then-retrieve-conversational","title":"Generating Multi-Aspect Queries for Conversational Search","date":"2024-03-28","arxiv_id":"2403.19302","n_code_links":0,"syntology":null},{"paper":"/paper/genetic-quantization-aware-approximation-for","slug":"genetic-quantization-aware-approximation-for","title":"Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers","date":"2024-03-28","arxiv_id":"2403.19591","n_code_links":1,"syntology":null},{"paper":null,"slug":"intelligent-classification-and-personalized","title":"Intelligent Classification and Personalized Recommendation of E-commerce Products Based on Machine Learning","date":"2024-03-28","arxiv_id":"2403.19345","n_code_links":0,"syntology":null},{"paper":"/paper/interpreting-key-mechanisms-of-factual-recall","slug":"interpreting-key-mechanisms-of-factual-recall","title":"Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models","date":"2024-03-28","arxiv_id":"2403.19521","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":12,"n_instrument":0,"unverified":2,"pointer_only":14,"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) · 2 unverified","official":{"repos":["trestad/factual-recall-mechanism"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/jamba-a-hybrid-transformer-mamba-language","slug":"jamba-a-hybrid-transformer-mamba-language","title":"Jamba: A Hybrid Transformer-Mamba Language Model","date":"2024-03-28","arxiv_id":"2403.19887","n_code_links":3,"syntology":null},{"paper":null,"slug":"just-dna-seq-open-source-personal-genomics","title":"Just-DNA-Seq, open-source personal genomics platform: longevity science for everyone","date":"2024-03-28","arxiv_id":"2403.19087","n_code_links":0,"syntology":null},{"paper":null,"slug":"keypoint-action-tokens-enable-in-context","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","date":"2024-03-28","arxiv_id":"2403.19578","n_code_links":0,"syntology":null},{"paper":"/paper/mateval-a-multi-agent-discussion-framework","slug":"mateval-a-multi-agent-discussion-framework","title":"MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation","date":"2024-03-28","arxiv_id":"2403.19305","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-misleading-chain-of-thought","slug":"mitigating-misleading-chain-of-thought","title":"Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering","date":"2024-03-28","arxiv_id":"2403.19167","n_code_links":1,"syntology":null},{"paper":null,"slug":"patch-spatio-temporal-relation-prediction-for","title":"Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection","date":"2024-03-28","arxiv_id":"2403.19111","n_code_links":0,"syntology":null},{"paper":null,"slug":"risk-prediction-of-pathological-gambling-on","title":"Risk prediction of pathological gambling on social media","date":"2024-03-28","arxiv_id":"2403.19358","n_code_links":0,"syntology":null},{"paper":"/paper/siamese-vision-transformers-are-scalable","slug":"siamese-vision-transformers-are-scalable","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","date":"2024-03-28","arxiv_id":"2403.19638","n_code_links":1,"syntology":{"ran":15,"of":19,"n_ran_checked":15,"n_instrument":0,"unverified":4,"pointer_only":19,"phrase":"15 ran (of which 3 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["genjib/avsiam"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":3,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"single-shared-network-with-prior-inspired","title":"Single-Shared Network with Prior-Inspired Loss for Parameter-Efficient Multi-Modal Imaging Skin Lesion Classification","date":"2024-03-28","arxiv_id":"2403.19203","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-corpus-of-annotated-medical-imaging","slug":"a-novel-corpus-of-annotated-medical-imaging","title":"A Novel Corpus of Annotated Medical Imaging Reports and Information Extraction Results Using BERT-based Language Models","date":"2024-03-27","arxiv_id":"2403.18975","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-models-from","title":"A Survey on Large Language Models from Concept to Implementation","date":"2024-03-27","arxiv_id":"2403.18969","n_code_links":0,"syntology":null},{"paper":null,"slug":"acted-automatic-acquisition-of-typical-event","title":"AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA","date":"2024-03-27","arxiv_id":"2403.18504","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-aware-semantic-relevance-predicting","title":"Attention-aware semantic relevance predicting Chinese sentence reading","date":"2024-03-27","arxiv_id":"2403.18542","n_code_links":0,"syntology":null}],"record_sha256":"fa298f1c8daee96652c322696490fac628615738da7bb0eb3e9e343cfaa62fc0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}