{"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/150","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":150,"pages_in_order":316,"rows_per_page":100,"rows":[14901,15000],"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/149","next":"/method/attention/papers/151","papers":[{"paper":"/paper/switch-diffusion-transformer-synergizing","slug":"switch-diffusion-transformer-synergizing","title":"Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts","date":"2024-03-14","arxiv_id":"2403.09176","n_code_links":2,"syntology":{"ran":15,"of":18,"n_ran_checked":9,"n_instrument":6,"unverified":3,"pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["byeongjun-park/Switch-DiT"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"visiongpt-3d-a-generalized-multimodal-agent","title":"VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding","date":"2024-03-14","arxiv_id":"2403.09530","n_code_links":0,"syntology":null},{"paper":"/paper/vm-unet-v2-rethinking-vision-mamba-unet-for","slug":"vm-unet-v2-rethinking-vision-mamba-unet-for","title":"VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation","date":"2024-03-14","arxiv_id":"2403.09157","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multimodal-fusion-network-for-student","title":"A Multimodal Fusion Network For Student Emotion Recognition Based on Transformer and Tensor Product","date":"2024-03-13","arxiv_id":"2403.08511","n_code_links":0,"syntology":null},{"paper":null,"slug":"authorship-verification-based-on-the","title":"Authorship Verification based on the Likelihood Ratio of Grammar Models","date":"2024-03-13","arxiv_id":"2403.08462","n_code_links":0,"syntology":null},{"paper":"/paper/autoregressive-score-generation-for-multi","slug":"autoregressive-score-generation-for-multi","title":"Autoregressive Score Generation for Multi-trait Essay Scoring","date":"2024-03-13","arxiv_id":"2403.08332","n_code_links":1,"syntology":null},{"paper":"/paper/can-large-language-models-identify-authorship","slug":"can-large-language-models-identify-authorship","title":"Can Large Language Models Identify Authorship?","date":"2024-03-13","arxiv_id":"2403.08213","n_code_links":1,"syntology":null},{"paper":"/paper/content-aware-masked-image-modeling","slug":"content-aware-masked-image-modeling","title":"CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression","date":"2024-03-13","arxiv_id":"2403.08505","n_code_links":1,"syntology":null},{"paper":"/paper/devbench-a-comprehensive-benchmark-for","slug":"devbench-a-comprehensive-benchmark-for","title":"Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study","date":"2024-03-13","arxiv_id":"2403.08604","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["open-compass/devbench","open-compass/deveval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"distilling-named-entity-recognition-models","title":"Distilling Named Entity Recognition Models for Endangered Species from Large Language Models","date":"2024-03-13","arxiv_id":"2403.15430","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-language-models-care-about-text-quality","title":"Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages","date":"2024-03-13","arxiv_id":"2403.08693","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-geometric-markov-chain-monte-carlo","slug":"efficient-geometric-markov-chain-monte-carlo","title":"Derivative-informed neural operator acceleration of geometric MCMC for infinite-dimensional Bayesian inverse problems","date":"2024-03-13","arxiv_id":"2403.08220","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hippylib/hippyflow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"embedded-translations-for-low-resource","title":"Embedded Translations for Low-resource Automated Glossing","date":"2024-03-13","arxiv_id":"2403.08189","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-application-of-large-language","title":"Evaluating the Application of Large Language Models to Generate Feedback in Programming Education","date":"2024-03-13","arxiv_id":"2403.09744","n_code_links":0,"syntology":null},{"paper":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","n_code_links":2,"syntology":{"ran":4,"of":7,"n_ran_checked":3,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"gpt-ontology-and-caabac-a-tripartite","title":"GPT, Ontology, and CAABAC: A Tripartite Personalized Access Control Model Anchored by Compliance, Context and Attribute","date":"2024-03-13","arxiv_id":"2403.08264","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-contrastive","slug":"large-language-models-are-contrastive","title":"Large Language Models are Contrastive Reasoners","date":"2024-03-13","arxiv_id":"2403.08211","n_code_links":1,"syntology":null},{"paper":"/paper/meter-a-mobile-vision-transformer","slug":"meter-a-mobile-vision-transformer","title":"METER: a mobile vision transformer architecture for monocular depth estimation","date":"2024-03-13","arxiv_id":"2403.08368","n_code_links":1,"syntology":null},{"paper":null,"slug":"onevos-unifying-video-object-segmentation","title":"OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework","date":"2024-03-13","arxiv_id":"2403.08682","n_code_links":0,"syntology":null},{"paper":null,"slug":"p2lhap-wearable-sensor-based-human-activity","title":"P2LHAP:Wearable sensor-based human activity recognition, segmentation and forecast through Patch-to-Label Seq2Seq Transformer","date":"2024-03-13","arxiv_id":"2403.08214","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-the-application-of-deep-learning","title":"Research on the Application of Deep Learning-based BERT Model in Sentiment Analysis","date":"2024-03-13","arxiv_id":"2403.08217","n_code_links":0,"syntology":null},{"paper":null,"slug":"rich-semantic-knowledge-enhanced-large","title":"Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking","date":"2024-03-13","arxiv_id":"2403.08492","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-garden-of-forking-paths-observing-dynamic","title":"The Garden of Forking Paths: Observing Dynamic Parameters Distribution in Large Language Models","date":"2024-03-13","arxiv_id":"2403.08739","n_code_links":0,"syntology":null},{"paper":"/paper/verifix-post-training-correction-to-improve","slug":"verifix-post-training-correction-to-improve","title":"SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness","date":"2024-03-13","arxiv_id":"2403.08618","n_code_links":1,"syntology":null},{"paper":"/paper/vit-comer-vision-transformer-with","slug":"vit-comer-vision-transformer-with","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","date":"2024-03-13","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"a-survey-of-vision-transformers-in-autonomous","title":"A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions","date":"2024-03-12","arxiv_id":"2403.07542","n_code_links":0,"syntology":null},{"paper":"/paper/chai-clustered-head-attention-for-efficient","slug":"chai-clustered-head-attention-for-efficient","title":"CHAI: Clustered Head Attention for Efficient LLM Inference","date":"2024-03-12","arxiv_id":"2403.08058","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":["facebookresearch/chai"],"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/chronos-learning-the-language-of-time-series","slug":"chronos-learning-the-language-of-time-series","title":"Chronos: Learning the Language of Time Series","date":"2024-03-12","arxiv_id":"2403.07815","n_code_links":6,"syntology":{"ran":23,"of":28,"n_ran_checked":22,"n_instrument":1,"unverified":5,"pointer_only":5,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 3 honoured, 1 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["SalesforceAIResearch/uni2ts","amazon-science/chronos-forecasting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/contextual-clarity-generating-sentences-with","slug":"contextual-clarity-generating-sentences-with","title":"Contextual Clarity: Generating Sentences with Transformer Models using Context-Reverso Data","date":"2024-03-12","arxiv_id":"2403.08103","n_code_links":1,"syntology":null},{"paper":"/paper/decomposing-disease-descriptions-for-enhanced","slug":"decomposing-disease-descriptions-for-enhanced","title":"Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework","date":"2024-03-12","arxiv_id":"2403.07636","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hieuphan33/mavl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-readmission-prediction-with-deep","title":"Enhancing Readmission Prediction with Deep Learning: Extracting Biomedical Concepts from Clinical Texts","date":"2024-03-12","arxiv_id":"2403.09722","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-safety-generalization-challenges-of","slug":"exploring-safety-generalization-challenges-of","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","date":"2024-03-12","arxiv_id":"2403.07865","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["renqibing/CodeAttack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-generated-text-detection-benchmark","slug":"gpt-generated-text-detection-benchmark","title":"GPT-generated Text Detection: Benchmark Dataset and Tensor-based Detection Method","date":"2024-03-12","arxiv_id":"2403.07321","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["madlab-ucr/grid"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gujarati-english-code-switching-speech","title":"Gujarati-English Code-Switching Speech Recognition using ensemble prediction of spoken language","date":"2024-03-12","arxiv_id":"2403.08011","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-context-learning-enables-multimodal-large","title":"In-context learning enables multimodal large language models to classify cancer pathology images","date":"2024-03-12","arxiv_id":"2403.07407","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-the-performance-of-retrieval","slug":"investigating-the-performance-of-retrieval","title":"Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems","date":"2024-03-12","arxiv_id":"2403.09727","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-correction-errors-via-frequency-self","title":"Learning Correction Errors via Frequency-Self Attention for Blind Image Super-Resolution","date":"2024-03-12","arxiv_id":"2403.07390","n_code_links":0,"syntology":null},{"paper":"/paper/lookupffn-making-transformers-compute-lite","slug":"lookupffn-making-transformers-compute-lite","title":"LookupFFN: Making Transformers Compute-lite for CPU inference","date":"2024-03-12","arxiv_id":"2403.07221","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mlpen/lookupffn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/moralbert-detecting-moral-values-in-social","slug":"moralbert-detecting-moral-values-in-social","title":"MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social Discussions","date":"2024-03-12","arxiv_id":"2403.07678","n_code_links":1,"syntology":null},{"paper":null,"slug":"q-slam-quadric-representations-for-monocular","title":"Q-SLAM: Quadric Representations for Monocular SLAM","date":"2024-03-12","arxiv_id":"2403.08125","n_code_links":0,"syntology":null},{"paper":"/paper/reinforced-sequential-decision-making-for","slug":"reinforced-sequential-decision-making-for","title":"Reinforced Sequential Decision-Making for Sepsis Treatment: The POSNEGDM Framework with Mortality Classifier and Transformer","date":"2024-03-12","arxiv_id":"2403.07309","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dipeshtamboli/posnegdm-reinforced-sequential-decision-making-for-sepsis-treatment"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rethinking-aste-a-minimalist-tagging-scheme","title":"Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning","date":"2024-03-12","arxiv_id":"2403.07342","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-generative-large-language-model","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","date":"2024-03-12","arxiv_id":"2403.07872","n_code_links":0,"syntology":null},{"paper":null,"slug":"sifid-reassess-summary-factual-inconsistency","title":"SIFiD: Reassess Summary Factual Inconsistency Detection with LLM","date":"2024-03-12","arxiv_id":"2403.07557","n_code_links":0,"syntology":null},{"paper":"/paper/stabletoolbench-towards-stable-large-scale","slug":"stabletoolbench-towards-stable-large-scale","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models","date":"2024-03-12","arxiv_id":"2403.07714","n_code_links":4,"syntology":{"ran":11,"of":15,"n_ran_checked":9,"n_instrument":2,"unverified":4,"pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["thunlp-mt/stabletoolbench","zhichengg/stabletoolbench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"stress-index-strategy-enhanced-with-financial","title":"Stress index strategy enhanced with financial news sentiment analysis for the equity markets","date":"2024-03-12","arxiv_id":"2404.00012","n_code_links":0,"syntology":null},{"paper":"/paper/textual-knowledge-matters-cross-modality-co","slug":"textual-knowledge-matters-cross-modality-co","title":"Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery","date":"2024-03-12","arxiv_id":"2403.07369","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":4,"n_instrument":3,"unverified":4,"pointer_only":11,"phrase":"7 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; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["haiyangzheng/textgcd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-future-of-document-indexing-gpt-and-donut","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","date":"2024-03-12","arxiv_id":"2403.07553","n_code_links":0,"syntology":null},{"paper":"/paper/training-small-multimodal-models-to-bridge","slug":"training-small-multimodal-models-to-bridge","title":"Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation","date":"2024-03-12","arxiv_id":"2403.08002","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":8,"phrase":"7 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/llava-rad"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/unleashing-hydra-hybrid-fusion-depth","slug":"unleashing-hydra-hybrid-fusion-depth","title":"Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception","date":"2024-03-12","arxiv_id":"2403.07746","n_code_links":1,"syntology":null},{"paper":"/paper/vanp-learning-where-to-see-for-navigation","slug":"vanp-learning-where-to-see-for-navigation","title":"VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training","date":"2024-03-12","arxiv_id":"2403.08109","n_code_links":1,"syntology":null},{"paper":"/paper/vit-comer-vision-transformer-with-1","slug":"vit-comer-vision-transformer-with-1","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","date":"2024-03-12","arxiv_id":"2403.07392","n_code_links":1,"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":["Traffic-X/ViT-CoMer"],"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":"a-multi-cohort-study-on-prediction-of-acute","title":"A multi-cohort study on prediction of acute brain dysfunction states using selective state space models","date":"2024-03-11","arxiv_id":"2403.07201","n_code_links":0,"syntology":null},{"paper":"/paper/amharic-llama-and-llava-multimodal-llms-for","slug":"amharic-llama-and-llava-multimodal-llms-for","title":"Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource Languages","date":"2024-03-11","arxiv_id":"2403.06354","n_code_links":1,"syntology":null},{"paper":null,"slug":"development-of-a-reliable-and-accessible","title":"Development of a Reliable and Accessible Caregiving Language Model (CaLM)","date":"2024-03-11","arxiv_id":"2403.06857","n_code_links":0,"syntology":null},{"paper":"/paper/gritv2-efficient-and-light-weight-social","slug":"gritv2-efficient-and-light-weight-social","title":"GRITv2: Efficient and Light-weight Social Relation Recognition","date":"2024-03-11","arxiv_id":"2403.06895","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-clinical-reasoning-with-large","title":"Guiding Clinical Reasoning with Large Language Models via Knowledge Seeds","date":"2024-03-11","arxiv_id":"2403.06609","n_code_links":0,"syntology":null},{"paper":null,"slug":"hdrtransdc-high-dynamic-range-image","title":"HDRTransDC: High Dynamic Range Image Reconstruction with Transformer Deformation Convolution","date":"2024-03-11","arxiv_id":"2403.06831","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-human-llm-corpus-construction-and-llm","title":"Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena","date":"2024-03-11","arxiv_id":"2403.06965","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-context-exploration-exploitation-for","title":"In-context Exploration-Exploitation for Reinforcement Learning","date":"2024-03-11","arxiv_id":"2403.06826","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-implicit-transformer-with-re","title":"Multi-Scale Implicit Transformer with Re-parameterize for Arbitrary-Scale Super-Resolution","date":"2024-03-11","arxiv_id":"2403.06536","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-turn-taking-prediction-using","title":"Multilingual Turn-taking Prediction Using Voice Activity Projection","date":"2024-03-11","arxiv_id":"2403.06487","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrating-causal-graphs-with-large-language","title":"Narrating Causal Graphs with Large Language Models","date":"2024-03-11","arxiv_id":"2403.07118","n_code_links":0,"syntology":null},{"paper":"/paper/smart-automatically-scaling-down-language","slug":"smart-automatically-scaling-down-language","title":"SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees","date":"2024-03-11","arxiv_id":"2403.13835","n_code_links":1,"syntology":null},{"paper":"/paper/the-pitfalls-of-next-token-prediction","slug":"the-pitfalls-of-next-token-prediction","title":"The pitfalls of next-token prediction","date":"2024-03-11","arxiv_id":"2403.06963","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"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) · 1 unverified","official":{"repos":["gregorbachmann/next-token-failures"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unraveling-the-mystery-of-scaling-laws-part-i","title":"Unraveling the Mystery of Scaling Laws: Part I","date":"2024-03-11","arxiv_id":"2403.06563","n_code_links":0,"syntology":null},{"paper":null,"slug":"attacking-transformers-with-feature-diversity","title":"Attacking Transformers with Feature Diversity Adversarial Perturbation","date":"2024-03-10","arxiv_id":"2403.07942","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-is-all-you-need-for-boosting-graph","title":"Attention is all you need for boosting graph convolutional neural network","date":"2024-03-10","arxiv_id":"2403.15419","n_code_links":0,"syntology":null},{"paper":"/paper/finding-visual-saliency-in-continuous-spike","slug":"finding-visual-saliency-in-continuous-spike","title":"Finding Visual Saliency in Continuous Spike Stream","date":"2024-03-10","arxiv_id":"2403.06233","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["bit-vision/svs"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/framequant-flexible-low-bit-quantization-for","slug":"framequant-flexible-low-bit-quantization-for","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","date":"2024-03-10","arxiv_id":"2403.06082","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":11,"n_instrument":1,"unverified":6,"pointer_only":18,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["vsingh-group/framequant"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/target-constrained-bidirectional-planning-for","slug":"target-constrained-bidirectional-planning-for","title":"Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue","date":"2024-03-10","arxiv_id":"2403.06063","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-in-vehicle-multi-task-facial","title":"Towards In-Vehicle Multi-Task Facial Attribute Recognition: Investigating Synthetic Data and Vision Foundation Models","date":"2024-03-10","arxiv_id":"2403.06088","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-audio-textual-diffusion-model-for","title":"An Audio-textual Diffusion Model For Converting Speech Signals Into Ultrasound Tongue Imaging Data","date":"2024-03-09","arxiv_id":"2403.05820","n_code_links":0,"syntology":null},{"paper":"/paper/autoeval-done-right-using-synthetic-data-for","slug":"autoeval-done-right-using-synthetic-data-for","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","date":"2024-03-09","arxiv_id":"2403.07008","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":["pierreboyeau/autoeval"],"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/clinicalmamba-a-generative-clinical-language","slug":"clinicalmamba-a-generative-clinical-language","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","date":"2024-03-09","arxiv_id":"2403.05795","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["whaleloops/clinicalmamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-multi-hop-knowledge-graph-reasoning","title":"Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques","date":"2024-03-09","arxiv_id":"2403.05801","n_code_links":0,"syntology":null},{"paper":"/paper/general-surgery-vision-transformer-a-video","slug":"general-surgery-vision-transformer-a-video","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","date":"2024-03-09","arxiv_id":"2403.05949","n_code_links":1,"syntology":null},{"paper":null,"slug":"hufu-a-modality-agnositc-watermarking-system","title":"TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers","date":"2024-03-09","arxiv_id":"2403.05842","n_code_links":0,"syntology":null},{"paper":"/paper/long-term-frame-event-visual-tracking","slug":"long-term-frame-event-visual-tracking","title":"Long-term Frame-Event Visual Tracking: Benchmark Dataset and Baseline","date":"2024-03-09","arxiv_id":"2403.05839","n_code_links":4,"syntology":null},{"paper":null,"slug":"segmentation-guided-sparse-transformer-for","title":"Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration","date":"2024-03-09","arxiv_id":"2403.05906","n_code_links":0,"syntology":null},{"paper":"/paper/a-benchmark-of-domain-adapted-large-language","slug":"a-benchmark-of-domain-adapted-large-language","title":"A Dataset and Benchmark for Hospital Course Summarization with Adapted Large Language Models","date":"2024-03-08","arxiv_id":"2403.05720","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-nuanced-conversation-evaluation","title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","date":"2024-03-08","arxiv_id":"2403.09705","n_code_links":0,"syntology":null},{"paper":null,"slug":"actformer-scalable-collaborative-perception","title":"ActFormer: Scalable Collaborative Perception via Active Queries","date":"2024-03-08","arxiv_id":"2403.04968","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-in-depth-evaluation-of-gpt-4-in-sentence","title":"An In-depth Evaluation of GPT-4 in Sentence Simplification with Error-based Human Assessment","date":"2024-03-08","arxiv_id":"2403.04963","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-aligned-with-people","slug":"are-large-language-models-aligned-with-people","title":"Are Large Language Models Aligned with People's Social Intuitions for Human-Robot Interactions?","date":"2024-03-08","arxiv_id":"2403.05701","n_code_links":1,"syntology":null},{"paper":"/paper/bias-augmented-consistency-training-reduces","slug":"bias-augmented-consistency-training-reduces","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","date":"2024-03-08","arxiv_id":"2403.05518","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["raybears/cot-transparency"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/binaural-speech-enhancement-using-deep","slug":"binaural-speech-enhancement-using-deep","title":"Binaural Speech Enhancement Using Deep Complex Convolutional Transformer Networks","date":"2024-03-08","arxiv_id":"2403.05393","n_code_links":1,"syntology":null},{"paper":"/paper/can-t-remember-details-in-long-documents-you","slug":"can-t-remember-details-in-long-documents-you","title":"Can't Remember Details in Long Documents? You Need Some R&R","date":"2024-03-08","arxiv_id":"2403.05004","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["casetext/r-and-r"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/commitbench-a-benchmark-for-commit-message","slug":"commitbench-a-benchmark-for-commit-message","title":"CommitBench: A Benchmark for Commit Message Generation","date":"2024-03-08","arxiv_id":"2403.05188","n_code_links":1,"syntology":null},{"paper":"/paper/considering-nonstationary-within-multivariate","slug":"considering-nonstationary-within-multivariate","title":"Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting","date":"2024-03-08","arxiv_id":"2403.05406","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":12,"n_instrument":0,"unverified":5,"pointer_only":17,"phrase":"12 ran (of which 10 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) · 5 unverified","official":{"repos":["flare200020/HTV_Trans"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":10,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cost-performance-optimization-for-processing","title":"Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs","date":"2024-03-08","arxiv_id":"2403.05434","n_code_links":0,"syntology":null},{"paper":null,"slug":"decomposing-vision-based-llm-predictions-for","title":"How Well Do Multi-modal LLMs Interpret CT Scans? An Auto-Evaluation Framework for Analyses","date":"2024-03-08","arxiv_id":"2403.05680","n_code_links":0,"syntology":null},{"paper":null,"slug":"denoising-autoregressive-representation","title":"Denoising Autoregressive Representation Learning","date":"2024-03-08","arxiv_id":"2403.05196","n_code_links":0,"syntology":null},{"paper":"/paper/dualbev-cnn-is-all-you-need-in-view","slug":"dualbev-cnn-is-all-you-need-in-view","title":"DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences","date":"2024-03-08","arxiv_id":"2403.05402","n_code_links":1,"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":["peidongli/dualbev"],"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-automatic-modulation-recognition-1","title":"Enhancing Automatic Modulation Recognition for IoT Applications Using Transformers","date":"2024-03-08","arxiv_id":"2403.15417","n_code_links":0,"syntology":null},{"paper":"/paper/erbench-an-entity-relationship-based","slug":"erbench-an-entity-relationship-based","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","date":"2024-03-08","arxiv_id":"2403.05266","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dilab-kaist/erbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gemini-1-5-unlocking-multimodal-understanding","slug":"gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","arxiv_id":"2403.05530","n_code_links":1,"syntology":null},{"paper":null,"slug":"inverse-design-of-photonic-crystal-surface","title":"Inverse Design of Photonic Crystal Surface Emitting Lasers is a Sequence Modeling Problem","date":"2024-03-08","arxiv_id":"2403.05149","n_code_links":0,"syntology":null},{"paper":"/paper/jointmotion-joint-self-supervision-for-joint","slug":"jointmotion-joint-self-supervision-for-joint","title":"JointMotion: Joint Self-Supervision for Joint Motion Prediction","date":"2024-03-08","arxiv_id":"2403.05489","n_code_links":1,"syntology":null},{"paper":"/paper/lightm-unet-mamba-assists-in-lightweight-unet","slug":"lightm-unet-mamba-assists-in-lightweight-unet","title":"LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation","date":"2024-03-08","arxiv_id":"2403.05246","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mrblankness/lightm-unet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"3b2881c7455ff569021be47ec60d77e9a9ab33e4312d4bfd40a602844da91bed","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}