{"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/transformer/papers/78","list_of":"/method/transformer","method":"Transformer","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":78,"pages_in_order":140,"rows_per_page":100,"rows":[7701,7800],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/77","next":"/method/transformer/papers/79","papers":[{"paper":"/paper/deepfake-video-detection-using-generative","slug":"deepfake-video-detection-using-generative","title":"Deepfake Video Detection Using Generative Convolutional Vision Transformer","date":"2023-07-13","arxiv_id":"2307.07036","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-integration-of-large-language","title":"Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study","date":"2023-07-13","arxiv_id":"2307.06530","n_code_links":0,"syntology":null},{"paper":null,"slug":"mpr-net-multi-scale-pattern-reproduction","title":"MPR-Net:Multi-Scale Pattern Reproduction Guided Universality Time Series Interpretable Forecasting","date":"2023-07-13","arxiv_id":"2307.06736","n_code_links":0,"syntology":null},{"paper":"/paper/video-focalnets-spatio-temporal-focal","slug":"video-focalnets-spatio-temporal-focal","title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition","date":"2023-07-13","arxiv_id":"2307.06947","n_code_links":3,"syntology":{"ran":23,"of":32,"n_ran_checked":22,"n_instrument":1,"unverified":9,"pointer_only":21,"phrase":"23 ran (of which 7 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["talalwasim/video-focalnets"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"convnext-charm-convnext-based-transform-for","title":"ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression","date":"2023-07-12","arxiv_id":"2307.06342","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-large-language-models-for","title":"Distilling Large Language Models for Biomedical Knowledge Extraction: A Case Study on Adverse Drug Events","date":"2023-07-12","arxiv_id":"2307.06439","n_code_links":0,"syntology":null},{"paper":"/paper/patch-n-pack-navit-a-vision-transformer-for","slug":"patch-n-pack-navit-a-vision-transformer-for","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","date":"2023-07-12","arxiv_id":"2307.06304","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"prompt-generate-train-pgt-a-framework-for-few","title":"Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering","date":"2023-07-12","arxiv_id":"2307.05915","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-distilled-quantization-achieving-high","title":"Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models","date":"2023-07-12","arxiv_id":"2307.05972","n_code_links":0,"syntology":null},{"paper":"/paper/swift-swin-4d-fmri-transformer-1","slug":"swift-swin-4d-fmri-transformer-1","title":"SwiFT: Swin 4D fMRI Transformer","date":"2023-07-12","arxiv_id":"2307.05916","n_code_links":1,"syntology":{"ran":25,"of":42,"n_ran_checked":21,"n_instrument":4,"unverified":17,"pointer_only":16,"phrase":"25 ran (of which 4 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 17 unverified","official":{"repos":["transconnectome/swift"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/3d-medical-image-segmentation-based-on-multi","slug":"3d-medical-image-segmentation-based-on-multi","title":"3D Medical Image Segmentation based on multi-scale MPU-Net","date":"2023-07-11","arxiv_id":"2307.05799","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-hierarchical-transformer-encoder-to-improve","title":"A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma","date":"2023-07-11","arxiv_id":"2307.05800","n_code_links":0,"syntology":null},{"paper":null,"slug":"argumentative-segmentation-enhancement-for","title":"Argumentative Segmentation Enhancement for Legal Summarization","date":"2023-07-11","arxiv_id":"2307.05081","n_code_links":0,"syntology":null},{"paper":"/paper/co-attention-gated-vision-language-embedding","slug":"co-attention-gated-vision-language-embedding","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-07-11","arxiv_id":"2307.05182","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["longbai1006/cat-vil"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"explaining-competitive-level-programming","title":"Explaining Competitive-Level Programming Solutions using LLMs","date":"2023-07-11","arxiv_id":"2307.05337","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-reconstruction-using-enhanced-vision","title":"Image Reconstruction using Enhanced Vision Transformer","date":"2023-07-11","arxiv_id":"2307.05616","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-hierarchical-transformers-for-pedestrian","title":"Non-Hierarchical Transformers for Pedestrian Segmentation","date":"2023-07-11","arxiv_id":"2311.02506","n_code_links":0,"syntology":null},{"paper":null,"slug":"proggp-from-guitarpro-tablature-neural","title":"ProgGP: From GuitarPro Tablature Neural Generation To Progressive Metal Production","date":"2023-07-11","arxiv_id":"2307.05328","n_code_links":0,"syntology":null},{"paper":null,"slug":"transaction-fraud-detection-via-spatial","title":"Transaction Fraud Detection via Spatial-Temporal-Aware Graph Transformer","date":"2023-07-11","arxiv_id":"2307.05121","n_code_links":0,"syntology":null},{"paper":"/paper/unleashing-cognitive-synergy-in-large","slug":"unleashing-cognitive-synergy-in-large","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","date":"2023-07-11","arxiv_id":"2307.05300","n_code_links":2,"syntology":null},{"paper":"/paper/writer-adaptation-for-offline-text","slug":"writer-adaptation-for-offline-text","title":"Writer adaptation for offline text recognition: An exploration of neural network-based methods","date":"2023-07-11","arxiv_id":"2307.15071","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-diagnosis-of-knee-osteoarthritis","title":"Automatic diagnosis of knee osteoarthritis severity using Swin transformer","date":"2023-07-10","arxiv_id":"2307.04442","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-piano-transcription-with","slug":"automatic-piano-transcription-with","title":"Automatic Piano Transcription with Hierarchical Frequency-Time Transformer","date":"2023-07-10","arxiv_id":"2307.04305","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["sony/hft-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chatgpt-for-digital-forensic-investigation","slug":"chatgpt-for-digital-forensic-investigation","title":"ChatGPT for Digital Forensic Investigation: The Good, The Bad, and The Unknown","date":"2023-07-10","arxiv_id":"2307.10195","n_code_links":1,"syntology":null},{"paper":null,"slug":"cluster-induced-mask-transformers-for","title":"Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans","date":"2023-07-10","arxiv_id":"2307.04525","n_code_links":0,"syntology":null},{"paper":null,"slug":"echovest-real-time-sound-classification-and","title":"EchoVest: Real-Time Sound Classification and Depth Perception Expressed through Transcutaneous Electrical Nerve Stimulation","date":"2023-07-10","arxiv_id":"2307.04604","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-solve-constraint-satisfaction","slug":"learning-to-solve-constraint-satisfaction","title":"Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer","date":"2023-07-10","arxiv_id":"2307.04895","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["azreasoners/recurrent_transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/mivolo-multi-input-transformer-for-age-and","slug":"mivolo-multi-input-transformer-for-age-and","title":"MiVOLO: Multi-input Transformer for Age and Gender Estimation","date":"2023-07-10","arxiv_id":"2307.04616","n_code_links":2,"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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wildchlamydia/mivolo"],"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":"assessing-the-efficacy-of-large-language","title":"Assessing the efficacy of large language models in generating accurate teacher responses","date":"2023-07-09","arxiv_id":"2307.04274","n_code_links":0,"syntology":null},{"paper":"/paper/cross-modal-orthogonal-high-rank-augmentation","slug":"cross-modal-orthogonal-high-rank-augmentation","title":"Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers","date":"2023-07-09","arxiv_id":"2307.04129","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["ZHU-Zhiyu/High-Rank_RGB-Event_Tracker"],"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/svit-scaling-up-visual-instruction-tuning","slug":"svit-scaling-up-visual-instruction-tuning","title":"SVIT: Scaling up Visual Instruction Tuning","date":"2023-07-09","arxiv_id":"2307.04087","n_code_links":2,"syntology":null},{"paper":"/paper/camouflaged-object-detection-with-feature-1","slug":"camouflaged-object-detection-with-feature-1","title":"Camouflaged Object Detection with Feature Grafting and Distractor Aware","date":"2023-07-08","arxiv_id":"2307.03943","n_code_links":1,"syntology":null},{"paper":null,"slug":"vs-transgru-a-novel-transformer-gru-based","title":"VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation","date":"2023-07-08","arxiv_id":"2307.03918","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-self-supervised-vision-1","title":"Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation","date":"2023-07-07","arxiv_id":"2307.03407","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-and-characterizing-large-language","title":"Exploring and Characterizing Large Language Models For Embedded System Development and Debugging","date":"2023-07-07","arxiv_id":"2307.03817","n_code_links":0,"syntology":null},{"paper":null,"slug":"houghlanenet-lane-detection-with-deep-hough","title":"HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolution","date":"2023-07-07","arxiv_id":"2307.03494","n_code_links":0,"syntology":null},{"paper":null,"slug":"intformer-a-time-embedded-attention-based","title":"inTformer: A Time-Embedded Attention-Based Transformer for Crash Likelihood Prediction at Intersections Using Connected Vehicle Data","date":"2023-07-07","arxiv_id":"2307.03854","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-batteries-included","title":"Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers","date":"2023-07-07","arxiv_id":"2307.03539","n_code_links":0,"syntology":null},{"paper":"/paper/non-iterative-coarse-to-fine-transformer","slug":"non-iterative-coarse-to-fine-transformer","title":"Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registration","date":"2023-07-07","arxiv_id":"2307.03421","n_code_links":1,"syntology":null},{"paper":"/paper/teaching-arithmetic-to-small-transformers","slug":"teaching-arithmetic-to-small-transformers","title":"Teaching Arithmetic to Small Transformers","date":"2023-07-07","arxiv_id":"2307.03381","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":["lee-ny/teaching_arithmetic"],"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/unsupervised-3d-out-of-distribution-detection","slug":"unsupervised-3d-out-of-distribution-detection","title":"Unsupervised 3D out-of-distribution detection with latent diffusion models","date":"2023-07-07","arxiv_id":"2307.03777","n_code_links":1,"syntology":null},{"paper":"/paper/when-do-transformers-shine-in-rl-decoupling-1","slug":"when-do-transformers-shine-in-rl-decoupling-1","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","date":"2023-07-07","arxiv_id":"2307.03864","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["twni2016/memory-rl","twni2016/pomdp-baselines"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"acdnet-attention-guided-collaborative","title":"ACDNet: Attention-guided Collaborative Decision Network for Effective Medication Recommendation","date":"2023-07-06","arxiv_id":"2307.03332","n_code_links":0,"syntology":null},{"paper":null,"slug":"art-authentication-with-vision-transformers","title":"Art Authentication with Vision Transformers","date":"2023-07-06","arxiv_id":"2307.03039","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrast-is-all-you-need","title":"Contrast Is All You Need","date":"2023-07-06","arxiv_id":"2307.02882","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-spatial-pixel-integration-and-cross","title":"Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based Transformer Network for Remote Sensing Image Super-Resolution","date":"2023-07-06","arxiv_id":"2307.02974","n_code_links":0,"syntology":null},{"paper":"/paper/focused-transformer-contrastive-training-for","slug":"focused-transformer-contrastive-training-for","title":"Focused Transformer: Contrastive Training for Context Scaling","date":"2023-07-06","arxiv_id":"2307.03170","n_code_links":1,"syntology":{"ran":9,"of":14,"n_ran_checked":5,"n_instrument":4,"unverified":5,"pointer_only":0,"phrase":"9 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; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["cstankonrad/long_llama"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-empowered-autonomous","title":"Large Language Models Empowered Autonomous Edge AI for Connected Intelligence","date":"2023-07-06","arxiv_id":"2307.02779","n_code_links":0,"syntology":null},{"paper":"/paper/lea-improving-sentence-similarity-robustness","slug":"lea-improving-sentence-similarity-robustness","title":"LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias","date":"2023-07-06","arxiv_id":"2307.02912","n_code_links":1,"syntology":null},{"paper":null,"slug":"structure-guided-multi-modal-pre-trained","title":"Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning","date":"2023-07-06","arxiv_id":"2307.03591","n_code_links":0,"syntology":null},{"paper":null,"slug":"track-mix-generation-on-music-streaming","title":"Track Mix Generation on Music Streaming Services using Transformers","date":"2023-07-06","arxiv_id":"2307.03045","n_code_links":0,"syntology":null},{"paper":null,"slug":"uit-saviors-at-medvqa-gi-2023-improving","title":"UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answering","date":"2023-07-06","arxiv_id":"2307.02783","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-language-transformers-a-survey","title":"Vision Language Transformers: A Survey","date":"2023-07-06","arxiv_id":"2307.03254","n_code_links":0,"syntology":null},{"paper":"/paper/building-cooperative-embodied-agents","slug":"building-cooperative-embodied-agents","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","date":"2023-07-05","arxiv_id":"2307.02485","n_code_links":2,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-gpt-4-and-human","title":"Comparative Analysis of GPT-4 and Human Graders in Evaluating Praise Given to Students in Synthetic Dialogues","date":"2023-07-05","arxiv_id":"2307.02018","n_code_links":0,"syntology":null},{"paper":null,"slug":"elastic-decision-transformer-1","title":"Elastic Decision Transformer","date":"2023-07-05","arxiv_id":"2307.02484","n_code_links":0,"syntology":null},{"paper":"/paper/external-reasoning-towards-multi-large","slug":"external-reasoning-towards-multi-large","title":"External Reasoning: Towards Multi-Large-Language-Models Interchangeable Assistance with Human Feedback","date":"2023-07-05","arxiv_id":"2307.12057","n_code_links":1,"syntology":null},{"paper":"/paper/hoodwinked-deception-and-cooperation-in-a","slug":"hoodwinked-deception-and-cooperation-in-a","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","date":"2023-07-05","arxiv_id":"2308.01404","n_code_links":1,"syntology":null},{"paper":"/paper/improving-automatic-parallel-training-via","slug":"improving-automatic-parallel-training-via","title":"Improving Automatic Parallel Training via Balanced Memory Workload Optimization","date":"2023-07-05","arxiv_id":"2307.02031","n_code_links":1,"syntology":null},{"paper":"/paper/jailbroken-how-does-llm-safety-training-fail","slug":"jailbroken-how-does-llm-safety-training-fail","title":"Jailbroken: How Does LLM Safety Training Fail?","date":"2023-07-05","arxiv_id":"2307.02483","n_code_links":1,"syntology":null},{"paper":"/paper/longnet-scaling-transformers-to-1000000000","slug":"longnet-scaling-transformers-to-1000000000","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","date":"2023-07-05","arxiv_id":"2307.02486","n_code_links":3,"syntology":null},{"paper":"/paper/mae-dfer-efficient-masked-autoencoder-for","slug":"mae-dfer-efficient-masked-autoencoder-for","title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition","date":"2023-07-05","arxiv_id":"2307.02227","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":12,"n_instrument":1,"unverified":1,"pointer_only":7,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sunlicai/mae-dfer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-scale-prototypical-transformer-for","title":"Multi-Scale Prototypical Transformer for Whole Slide Image Classification","date":"2023-07-05","arxiv_id":"2307.02308","n_code_links":0,"syntology":null},{"paper":"/paper/natural-language-deduction-with-incomplete-1","slug":"natural-language-deduction-with-incomplete-1","title":"Deductive Additivity for Planning of Natural Language Proofs","date":"2023-07-05","arxiv_id":"2307.02472","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-source-large-language-models-outperform","title":"Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning","date":"2023-07-05","arxiv_id":"2307.02179","n_code_links":0,"syntology":null},{"paper":null,"slug":"sumformer-universal-approximation-for","title":"Sumformer: Universal Approximation for Efficient Transformers","date":"2023-07-05","arxiv_id":"2307.02301","n_code_links":0,"syntology":null},{"paper":"/paper/task-specific-alignment-and-multiple-level","slug":"task-specific-alignment-and-multiple-level","title":"Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition","date":"2023-07-05","arxiv_id":"2307.01985","n_code_links":1,"syntology":null},{"paper":"/paper/deep-attention-q-network-for-personalized","slug":"deep-attention-q-network-for-personalized","title":"Deep Attention Q-Network for Personalized Treatment Recommendation","date":"2023-07-04","arxiv_id":"2307.01519","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-features-for-contactless-fingerprint","title":"Deep Features for Contactless Fingerprint Presentation Attack Detection: Can They Be Generalized?","date":"2023-07-04","arxiv_id":"2307.01845","n_code_links":0,"syntology":null},{"paper":"/paper/dit-3d-exploring-plain-diffusion-transformers-1","slug":"dit-3d-exploring-plain-diffusion-transformers-1","title":"DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation","date":"2023-07-04","arxiv_id":"2307.01831","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/edgeface-efficient-face-recognition-model-for","slug":"edgeface-efficient-face-recognition-model-for","title":"EdgeFace: Efficient Face Recognition Model for Edge Devices","date":"2023-07-04","arxiv_id":"2307.01838","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["otroshi/edgeface"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-transformers-for-on-line","title":"Exploring Transformers for On-Line Handwritten Signature Verification","date":"2023-07-04","arxiv_id":"2307.01663","n_code_links":0,"syntology":null},{"paper":"/paper/h-denseformer-an-efficient-hybrid-densely","slug":"h-denseformer-an-efficient-hybrid-densely","title":"H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation","date":"2023-07-04","arxiv_id":"2307.01486","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-graph-for-nlg-in-the-context-of","title":"Knowledge Graph for NLG in the context of conversational agents","date":"2023-07-04","arxiv_id":"2307.01548","n_code_links":0,"syntology":null},{"paper":null,"slug":"last-layer-state-space-model-for","title":"Last layer state space model for representation learning and uncertainty quantification","date":"2023-07-04","arxiv_id":"2307.01566","n_code_links":0,"syntology":null},{"paper":"/paper/pretraining-is-all-you-need-a-multi-atlas","slug":"pretraining-is-all-you-need-a-multi-atlas","title":"Pretraining is All You Need: A Multi-Atlas Enhanced Transformer Framework for Autism Spectrum Disorder Classification","date":"2023-07-04","arxiv_id":"2307.01759","n_code_links":1,"syntology":null},{"paper":"/paper/sageformer-series-aware-graph-enhanced","slug":"sageformer-series-aware-graph-enhanced","title":"SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecasting","date":"2023-07-04","arxiv_id":"2307.01616","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhangzw16/SageFormer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"selffed-self-supervised-federated-learning","title":"SelfFed: Self-supervised Federated Learning for Data Heterogeneity and Label Scarcity in IoMT","date":"2023-07-04","arxiv_id":"2307.01514","n_code_links":0,"syntology":null},{"paper":"/paper/spike-driven-transformer-1","slug":"spike-driven-transformer-1","title":"Spike-driven Transformer","date":"2023-07-04","arxiv_id":"2307.01694","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["biclab/spike-driven-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/transformed-protoform-reconstruction","slug":"transformed-protoform-reconstruction","title":"Transformed Protoform Reconstruction","date":"2023-07-04","arxiv_id":"2307.01896","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-the-snapshot-brain-tokenized-graph","slug":"beyond-the-snapshot-brain-tokenized-graph","title":"Beyond the Snapshot: Brain Tokenized Graph Transformer for Longitudinal Brain Functional Connectome Embedding","date":"2023-07-03","arxiv_id":"2307.00858","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-prediction-of-knee-osteoarthritis","slug":"end-to-end-prediction-of-knee-osteoarthritis","title":"End-To-End Prediction of Knee Osteoarthritis Progression With Multi-Modal Transformers","date":"2023-07-03","arxiv_id":"2307.00873","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-shutdown-avoidance-of-language","slug":"evaluating-shutdown-avoidance-of-language","title":"Evaluating Shutdown Avoidance of Language Models in Textual Scenarios","date":"2023-07-03","arxiv_id":"2307.00787","n_code_links":1,"syntology":null},{"paper":null,"slug":"guided-patch-grouping-wavelet-transformer","title":"Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation","date":"2023-07-03","arxiv_id":"2307.00711","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-memory-transformer-for","slug":"implicit-memory-transformer-for","title":"Implicit Memory Transformer for Computationally Efficient Simultaneous Speech Translation","date":"2023-07-03","arxiv_id":"2307.01381","n_code_links":1,"syntology":null},{"paper":null,"slug":"population-age-group-sensitivity-for-covid-19","title":"Population Age Group Sensitivity for COVID-19 Infections with Deep Learning","date":"2023-07-03","arxiv_id":"2307.00751","n_code_links":0,"syntology":null},{"paper":"/paper/shiftable-context-addressing-training","slug":"shiftable-context-addressing-training","title":"Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation","date":"2023-07-03","arxiv_id":"2307.01377","n_code_links":1,"syntology":null},{"paper":"/paper/trainable-transformer-in-transformer","slug":"trainable-transformer-in-transformer","title":"Trainable Transformer in Transformer","date":"2023-07-03","arxiv_id":"2307.01189","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":["abhishekpanigrahi1996/transformer_in_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"volta-diverse-and-controllable-question","title":"VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder","date":"2023-07-03","arxiv_id":"2307.00852","n_code_links":0,"syntology":null},{"paper":"/paper/biocpt-contrastive-pre-trained-transformers","slug":"biocpt-contrastive-pre-trained-transformers","title":"MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval","date":"2023-07-02","arxiv_id":"2307.00589","n_code_links":2,"syntology":null},{"paper":"/paper/clipsitu-effectively-leveraging-clip-for","slug":"clipsitu-effectively-leveraging-clip-for","title":"ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition","date":"2023-07-02","arxiv_id":"2307.00586","n_code_links":1,"syntology":null},{"paper":null,"slug":"conformer-llms-convolution-augmented-large","title":"Conformer LLMs -- Convolution Augmented Large Language Models","date":"2023-07-02","arxiv_id":"2307.00461","n_code_links":0,"syntology":null},{"paper":null,"slug":"referring-video-object-segmentation-with","title":"Bidirectional Correlation-Driven Inter-Frame Interaction Transformer for Referring Video Object Segmentation","date":"2023-07-02","arxiv_id":"2307.00536","n_code_links":0,"syntology":null},{"paper":"/paper/autost-training-free-neural-architecture","slug":"autost-training-free-neural-architecture","title":"AutoST: Training-free Neural Architecture Search for Spiking Transformers","date":"2023-07-01","arxiv_id":"2307.00293","n_code_links":1,"syntology":null},{"paper":null,"slug":"effective-matching-of-patients-to-clinical","title":"Effective Matching of Patients to Clinical Trials using Entity Extraction and Neural Re-ranking","date":"2023-07-01","arxiv_id":"2307.00381","n_code_links":0,"syntology":null},{"paper":null,"slug":"general-part-assembly-planning","title":"Rearrangement Planning for General Part Assembly","date":"2023-07-01","arxiv_id":"2307.00206","n_code_links":0,"syntology":null},{"paper":"/paper/learning-content-enhanced-mask-transformer","slug":"learning-content-enhanced-mask-transformer","title":"Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation","date":"2023-07-01","arxiv_id":"2307.00371","n_code_links":1,"syntology":null},{"paper":null,"slug":"more-for-less-compact-convolutional","title":"More for Less: Compact Convolutional Transformers Enable Robust Medical Image Classification with Limited Data","date":"2023-07-01","arxiv_id":"2307.00213","n_code_links":0,"syntology":null},{"paper":null,"slug":"pm-detr-domain-adaptive-prompt-memory-for","title":"PM-DETR: Domain Adaptive Prompt Memory for Object Detection with Transformers","date":"2023-07-01","arxiv_id":"2307.00313","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-temporal-enhanced-transformer-towards","slug":"spatial-temporal-enhanced-transformer-towards","title":"Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection","date":"2023-07-01","arxiv_id":"2307.00347","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eaphan/stemd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"13feceec406044530c59a80a6c97b38a5d90a243fb6c42c6db523b9e690355ff","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}