{"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/120","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":120,"pages_in_order":140,"rows_per_page":100,"rows":[11901,12000],"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/119","next":"/method/transformer/papers/121","papers":[{"paper":"/paper/long-short-transformer-efficient-transformers","slug":"long-short-transformer-efficient-transformers","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","date":"2021-07-05","arxiv_id":"2107.02192","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NVIDIA/transformer-ls"],"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":["listed","official","unlocated"]}}},{"paper":null,"slug":"test-time-personalization-with-a-transformer","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","date":"2021-07-05","arxiv_id":"2107.02133","n_code_links":0,"syntology":null},{"paper":"/paper/vision-xformers-efficient-attention-for-image","slug":"vision-xformers-efficient-attention-for-image","title":"Vision Xformers: Efficient Attention for Image Classification","date":"2021-07-05","arxiv_id":"2107.02239","n_code_links":2,"syntology":null},{"paper":null,"slug":"what-makes-for-hierarchical-vision","title":"What Makes for Hierarchical Vision Transformer?","date":"2021-07-05","arxiv_id":"2107.02174","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-neural-coreference-resolution-1","title":"End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline","date":"2021-07-04","arxiv_id":"2107.01700","n_code_links":0,"syntology":null},{"paper":"/paper/improved-representation-learning-for-session","slug":"improved-representation-learning-for-session","title":"Introducing Self-Attention to Target Attentive Graph Neural Networks","date":"2021-07-04","arxiv_id":"2107.01516","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-transformers-jump-around-right-in-natural","title":"Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN","date":"2021-07-03","arxiv_id":"2107.01366","n_code_links":0,"syntology":null},{"paper":"/paper/supervised-off-policy-ranking","slug":"supervised-off-policy-ranking","title":"Supervised Off-Policy Ranking","date":"2021-07-03","arxiv_id":"2107.01360","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["SOPR-T/SOPR-T"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"case-relation-transformer-a-crossmodal","title":"Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions","date":"2021-07-02","arxiv_id":"2107.00789","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-view-geo-localization-with-evolving","title":"Cross-view Geo-localization with Evolving Transformer","date":"2021-07-02","arxiv_id":"2107.00842","n_code_links":0,"syntology":null},{"paper":"/paper/online-metro-origin-destination-prediction","slug":"online-metro-origin-destination-prediction","title":"Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation","date":"2021-07-02","arxiv_id":"2107.00946","n_code_links":1,"syntology":null},{"paper":"/paper/r2d2-recursive-transformer-based-on","slug":"r2d2-recursive-transformer-based-on","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","date":"2021-07-02","arxiv_id":"2107.00967","n_code_links":1,"syntology":null},{"paper":"/paper/relaxed-attention-a-simple-method-to-boost","slug":"relaxed-attention-a-simple-method-to-boost","title":"Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","date":"2021-07-02","arxiv_id":"2107.01275","n_code_links":1,"syntology":null},{"paper":"/paper/solving-machine-learning-problems","slug":"solving-machine-learning-problems","title":"Solving Machine Learning Problems","date":"2021-07-02","arxiv_id":"2107.01238","n_code_links":1,"syntology":null},{"paper":null,"slug":"target-dependent-uniter-a-transformer-based","title":"Target-dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots","date":"2021-07-02","arxiv_id":"2107.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-f-a-transformer-network-with","title":"Transformer-F: A Transformer network with effective methods for learning universal sentence representation","date":"2021-07-02","arxiv_id":"2107.00653","n_code_links":0,"syntology":null},{"paper":"/paper/utnet-a-hybrid-transformer-architecture-for","slug":"utnet-a-hybrid-transformer-architecture-for","title":"UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation","date":"2021-07-02","arxiv_id":"2107.00781","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-relationship-forecasting-in-videos","title":"Visual Relationship Forecasting in Videos","date":"2021-07-02","arxiv_id":"2107.01181","n_code_links":0,"syntology":null},{"paper":"/paper/action-transformer-a-self-attention-model-for","slug":"action-transformer-a-self-attention-model-for","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","date":"2021-07-01","arxiv_id":"2107.00606","n_code_links":4,"syntology":null},{"paper":null,"slug":"cross-lingual-adaptation-for-type-inference","title":"Cross-Lingual Transfer Learning for Statistical Type Inference","date":"2021-07-01","arxiv_id":"2107.00157","n_code_links":0,"syntology":null},{"paper":"/paper/cswin-transformer-a-general-vision","slug":"cswin-transformer-a-general-vision","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","date":"2021-07-01","arxiv_id":"2107.00652","n_code_links":7,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/CSWin-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/focal-self-attention-for-local-global","slug":"focal-self-attention-for-local-global","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","date":"2021-07-01","arxiv_id":"2107.00641","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/Focal-Transformer"],"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":null,"slug":"glyphcrm-bidirectional-encoder-representation","title":"GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph","date":"2021-07-01","arxiv_id":"2107.00395","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-graph-based-transformer-framework","slug":"multimodal-graph-based-transformer-framework","title":"Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction","date":"2021-07-01","arxiv_id":"2107.00596","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-generative-model-for-raw-audio-using","title":"A Generative Model for Raw Audio Using Transformer Architectures","date":"2021-06-30","arxiv_id":"2106.16036","n_code_links":0,"syntology":null},{"paper":"/paper/dual-aspect-self-attention-based-on","slug":"dual-aspect-self-attention-based-on","title":"Dual Aspect Self-Attention based on Transformer for Remaining Useful Life Prediction","date":"2021-06-30","arxiv_id":"2106.15842","n_code_links":1,"syntology":null},{"paper":"/paper/an-efficient-cervical-whole-slide-image","slug":"an-efficient-cervical-whole-slide-image","title":"An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Location Deep Features","date":"2021-06-29","arxiv_id":"2106.15113","n_code_links":1,"syntology":null},{"paper":"/paper/fastpitchformant-source-filter-based","slug":"fastpitchformant-source-filter-based","title":"FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis","date":"2021-06-29","arxiv_id":"2106.15123","n_code_links":1,"syntology":null},{"paper":"/paper/geometry-aware-transformer-for-molecular","slug":"geometry-aware-transformer-for-molecular","title":"GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning","date":"2021-06-29","arxiv_id":"2106.15516","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-context-aware-transformers-for","title":"Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech","date":"2021-06-29","arxiv_id":"2106.15144","n_code_links":0,"syntology":null},{"paper":"/paper/looking-outside-the-window-wider-context","slug":"looking-outside-the-window-wider-context","title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","date":"2021-06-29","arxiv_id":"2106.15754","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-exit-vision-transformer-for-dynamic","title":"Multi-Exit Vision Transformer for Dynamic Inference","date":"2021-06-29","arxiv_id":"2106.15183","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-the-evaluation-of-neural-machine","title":"Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space","date":"2021-06-29","arxiv_id":"2106.15217","n_code_links":0,"syntology":null},{"paper":"/paper/unified-questioner-transformer-for","slug":"unified-questioner-transformer-for","title":"Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue","date":"2021-06-29","arxiv_id":"2106.15550","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-knowledge-grounded-dialog-system-based-on","title":"A Knowledge-Grounded Dialog System Based on Pre-Trained Language Models","date":"2021-06-28","arxiv_id":"2106.14444","n_code_links":0,"syntology":null},{"paper":null,"slug":"complexity-based-partitioning-of-csfi-problem","title":"Complexity-based partitioning of CSFI problem instances with Transformers","date":"2021-06-28","arxiv_id":"2106.14481","n_code_links":0,"syntology":null},{"paper":"/paper/multi-compound-transformer-for-accurate","slug":"multi-compound-transformer-for-accurate","title":"Multi-Compound Transformer for Accurate Biomedical Image Segmentation","date":"2021-06-28","arxiv_id":"2106.14385","n_code_links":1,"syntology":null},{"paper":"/paper/r-drop-regularized-dropout-for-neural","slug":"r-drop-regularized-dropout-for-neural","title":"R-Drop: Regularized Dropout for Neural Networks","date":"2021-06-28","arxiv_id":"2106.14448","n_code_links":8,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dropreg/R-Drop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"rethinking-token-mixing-mlp-for-mlp-based","title":"Rethinking Token-Mixing MLP for MLP-based Vision Backbone","date":"2021-06-28","arxiv_id":"2106.14882","n_code_links":0,"syntology":null},{"paper":"/paper/tent-tensorized-encoder-transformer-for","slug":"tent-tensorized-encoder-transformer-for","title":"TENT: Tensorized Encoder Transformer for Temperature Forecasting","date":"2021-06-28","arxiv_id":"2106.14742","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-reinforcement-learning-approach-for-4","title":"A Reinforcement Learning Approach for Sequential Spatial Transformer Networks","date":"2021-06-27","arxiv_id":"2106.14295","n_code_links":0,"syntology":null},{"paper":"/paper/power-law-graph-transformer-for-machine","slug":"power-law-graph-transformer-for-machine","title":"Power Law Graph Transformer for Machine Translation and Representation Learning","date":"2021-06-27","arxiv_id":"2107.02039","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-picture-may-be-worth-a-hundred-words-for","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","date":"2021-06-25","arxiv_id":"2106.13445","n_code_links":0,"syntology":null},{"paper":"/paper/np-draw-a-non-parametric-structured-latent","slug":"np-draw-a-non-parametric-structured-latent","title":"NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation","date":"2021-06-25","arxiv_id":"2106.13435","n_code_links":1,"syntology":null},{"paper":null,"slug":"privileged-zero-shot-automl","title":"Privileged Zero-Shot AutoML","date":"2021-06-25","arxiv_id":"2106.13743","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-inter-modality-visual-parsing-with","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","date":"2021-06-25","arxiv_id":"2106.13488","n_code_links":0,"syntology":null},{"paper":"/paper/pvtv2-improved-baselines-with-pyramid-vision","slug":"pvtv2-improved-baselines-with-pyramid-vision","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","date":"2021-06-25","arxiv_id":"2106.13797","n_code_links":18,"syntology":null},{"paper":null,"slug":"to-the-point-efficient-3d-object-detection-in","title":"To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels","date":"2021-06-25","arxiv_id":"2106.13381","n_code_links":0,"syntology":null},{"paper":null,"slug":"bidding-via-clustering-ads-intentions-an","title":"An Efficient Group-based Search Engine Marketing System for E-Commerce","date":"2021-06-24","arxiv_id":"2106.12700","n_code_links":0,"syntology":null},{"paper":"/paper/learning-multiple-stock-trading-patterns-with","slug":"learning-multiple-stock-trading-patterns-with","title":"Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport","date":"2021-06-24","arxiv_id":"2106.12950","n_code_links":1,"syntology":null},{"paper":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","n_code_links":15,"syntology":{"ran":19,"of":32,"n_ran_checked":14,"n_instrument":5,"unverified":13,"pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/you-are-allset-a-multiset-function-framework","slug":"you-are-allset-a-multiset-function-framework","title":"You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks","date":"2021-06-24","arxiv_id":"2106.13264","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["jianhao2016/AllSet"],"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/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","n_code_links":2,"syntology":{"ran":7,"of":10,"n_ran_checked":4,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 3 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) · 3 unverified","official":{"repos":["google-research/google-research"],"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/instance-based-vision-transformer-for","slug":"instance-based-vision-transformer-for","title":"Instance-based Vision Transformer for Subtyping of Papillary Renal Cell Carcinoma in Histopathological Image","date":"2021-06-23","arxiv_id":"2106.12265","n_code_links":1,"syntology":null},{"paper":null,"slug":"stable-fast-and-accurate-kernelized-attention","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","date":"2021-06-23","arxiv_id":"2106.12566","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-meets-convolution-a-bilateral","slug":"transformer-meets-convolution-a-bilateral","title":"Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images","date":"2021-06-23","arxiv_id":"2106.12413","n_code_links":1,"syntology":null},{"paper":"/paper/p2t-pyramid-pooling-transformer-for-scene","slug":"p2t-pyramid-pooling-transformer-for-scene","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","date":"2021-06-22","arxiv_id":"2106.12011","n_code_links":4,"syntology":null},{"paper":"/paper/revisiting-deep-learning-models-for-tabular","slug":"revisiting-deep-learning-models-for-tabular","title":"Revisiting Deep Learning Models for Tabular Data","date":"2021-06-22","arxiv_id":"2106.11959","n_code_links":11,"syntology":{"ran":18,"of":22,"n_ran_checked":15,"n_instrument":3,"unverified":4,"pointer_only":1,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yandex-research/tabular-dl-revisiting-models","Yura52/tabular-dl-revisiting-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"hi-behrt-hierarchical-transformer-based-model","title":"Hi-BEHRT: Hierarchical Transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records","date":"2021-06-21","arxiv_id":"2106.11360","n_code_links":0,"syntology":null},{"paper":null,"slug":"modetr-moving-object-detection-with","title":"MODETR: Moving Object Detection with Transformers","date":"2021-06-21","arxiv_id":"2106.11422","n_code_links":0,"syntology":null},{"paper":null,"slug":"tcic-theme-concepts-learning-cross-language","title":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","date":"2021-06-21","arxiv_id":"2106.10936","n_code_links":0,"syntology":null},{"paper":"/paper/cpm-2-large-scale-cost-effective-pre-trained","slug":"cpm-2-large-scale-cost-effective-pre-trained","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","date":"2021-06-20","arxiv_id":"2106.10715","n_code_links":2,"syntology":null},{"paper":"/paper/solution-for-large-scale-long-tailed","slug":"solution-for-large-scale-long-tailed","title":"Solution for Large-scale Long-tailed Recognition with Noisy Labels","date":"2021-06-20","arxiv_id":"2106.10683","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-image-transformer-for-one-shot","title":"Adaptive Image Transformer for One-Shot Object Detection","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clusformer-a-transformer-based-clustering","slug":"clusformer-a-transformer-based-clustering","title":"Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/exploring-vision-transformers-for-fine","slug":"exploring-vision-transformers-for-fine","title":"Exploring Vision Transformers for Fine-grained Classification","date":"2021-06-19","arxiv_id":"2106.10587","n_code_links":1,"syntology":null},{"paper":null,"slug":"gaussian-context-transformer","title":"Gaussian Context Transformer","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-compositional-generalization-in-1","title":"Improving Compositional Generalization in Classification Tasks via Structure Annotations","date":"2021-06-19","arxiv_id":"2106.10434","n_code_links":0,"syntology":null},{"paper":"/paper/jointgt-graph-text-joint-representation","slug":"jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","arxiv_id":"2106.10502","n_code_links":1,"syntology":null},{"paper":"/paper/point-4d-transformer-networks-for-spatio","slug":"point-4d-transformer-networks-for-spatio","title":"Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/rstnet-captioning-with-adaptive-attention-on","slug":"rstnet-captioning-with-adaptive-attention-on","title":"RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/all-you-can-embed-natural-language-based","slug":"all-you-can-embed-natural-language-based","title":"All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers","date":"2021-06-18","arxiv_id":"2106.10153","n_code_links":1,"syntology":null},{"paper":"/paper/anomaly-detection-in-dynamic-graphs-via","slug":"anomaly-detection-in-dynamic-graphs-via","title":"Anomaly Detection in Dynamic Graphs via Transformer","date":"2021-06-18","arxiv_id":"2106.09876","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/end-to-end-temporal-action-detection-with","slug":"end-to-end-temporal-action-detection-with","title":"End-to-end Temporal Action Detection with Transformer","date":"2021-06-18","arxiv_id":"2106.10271","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["xlliu7/TadTR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"recurrent-stacking-of-layers-in-neural","title":"Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation","date":"2021-06-18","arxiv_id":"2106.10002","n_code_links":0,"syntology":null},{"paper":"/paper/dual-view-molecule-pre-training","slug":"dual-view-molecule-pre-training","title":"Dual-view Molecule Pre-training","date":"2021-06-17","arxiv_id":"2106.10234","n_code_links":1,"syntology":null},{"paper":null,"slug":"long-short-temporal-contrastive-learning-of","title":"Long-Short Temporal Contrastive Learning of Video Transformers","date":"2021-06-17","arxiv_id":"2106.09212","n_code_links":0,"syntology":null},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","n_code_links":74,"syntology":{"ran":51,"of":84,"n_ran_checked":44,"n_instrument":7,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 where Syntology's instrument failed) · 33 unverified","official":{"repos":["microsoft/LoRA"],"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/multi-head-or-single-head-an-empirical","slug":"multi-head-or-single-head-an-empirical","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","date":"2021-06-17","arxiv_id":"2106.09650","n_code_links":1,"syntology":null},{"paper":"/paper/semi-autoregressive-transformer-for-image","slug":"semi-autoregressive-transformer-for-image","title":"Semi-Autoregressive Transformer for Image Captioning","date":"2021-06-17","arxiv_id":"2106.09436","n_code_links":1,"syntology":null},{"paper":"/paper/time-series-is-a-special-sequence-forecasting","slug":"time-series-is-a-special-sequence-forecasting","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","date":"2021-06-17","arxiv_id":"2106.09305","n_code_links":6,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["WenjieDu/PyPOTS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper"]}}},{"paper":"/paper/end-to-end-semi-supervised-object-detection","slug":"end-to-end-semi-supervised-object-detection","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","date":"2021-06-16","arxiv_id":"2106.09018","n_code_links":8,"syntology":null},{"paper":"/paper/grounding-spatio-temporal-language-with","slug":"grounding-spatio-temporal-language-with","title":"Grounding Spatio-Temporal Language with Transformers","date":"2021-06-16","arxiv_id":"2106.08858","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-evaluation-and-improvement-of-tail-label","title":"On Evaluation and Improvement of Tail Label Performance for Multi-label Text Classification","date":"2021-06-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shuffle-transformer-with-feature-alignment","title":"Shuffle Transformer with Feature Alignment for Video Face Parsing","date":"2021-06-16","arxiv_id":"2106.08650","n_code_links":0,"syntology":null},{"paper":null,"slug":"simultaneous-training-of-partially-masked","title":"Masked Training of Neural Networks with Partial Gradients","date":"2021-06-16","arxiv_id":"2106.08895","n_code_links":0,"syntology":null},{"paper":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"pairconnect-a-compute-efficient-mlp","title":"PairConnect: A Compute-Efficient MLP Alternative to Attention","date":"2021-06-15","arxiv_id":"2106.08235","n_code_links":0,"syntology":null},{"paper":"/paper/scene-transformer-a-unified-multi-task-model","slug":"scene-transformer-a-unified-multi-task-model","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","date":"2021-06-15","arxiv_id":"2106.08417","n_code_links":4,"syntology":{"ran":2,"of":6,"n_ran_checked":1,"n_instrument":1,"unverified":4,"pointer_only":6,"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) · 4 unverified","official":null}},{"paper":null,"slug":"end-to-end-neural-diarization-from","title":"End-to-end Neural Diarization: From Transformer to Conformer","date":"2021-06-14","arxiv_id":"2106.07167","n_code_links":0,"syntology":null},{"paper":"/paper/improved-transformer-for-high-resolution-gans","slug":"improved-transformer-for-high-resolution-gans","title":"Improved Transformer for High-Resolution GANs","date":"2021-06-14","arxiv_id":"2106.07631","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/hit-gan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ng-a-multi-step-matrix-product-natural","slug":"ng-a-multi-step-matrix-product-natural","title":"NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning","date":"2021-06-14","arxiv_id":"2106.07454","n_code_links":1,"syntology":null},{"paper":"/paper/s-2-mlp-spatial-shift-mlp-architecture-for","slug":"s-2-mlp-spatial-shift-mlp-architecture-for","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","date":"2021-06-14","arxiv_id":"2106.07477","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-can-you-lay-off-heads-investigating-how","title":"Why Can You Lay Off Heads? Investigating How BERT Heads Transfer","date":"2021-06-14","arxiv_id":"2106.07137","n_code_links":0,"syntology":null},{"paper":null,"slug":"infobehavior-self-supervised-representation","title":"InfoBehavior: Self-supervised Representation Learning for Ultra-long Behavior Sequence via Hierarchical Grouping","date":"2021-06-13","arxiv_id":"2106.06905","n_code_links":0,"syntology":null},{"paper":"/paper/reinforcement-learning-as-one-big-sequence-1","slug":"reinforcement-learning-as-one-big-sequence-1","title":"Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/the-deformer-an-order-agnostic-distribution","slug":"the-deformer-an-order-agnostic-distribution","title":"The DEformer: An Order-Agnostic Distribution Estimating Transformer","date":"2021-06-13","arxiv_id":"2106.06989","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["airalcorn2/deformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/thinking-like-transformers-1","slug":"thinking-like-transformers-1","title":"Thinking Like Transformers","date":"2021-06-13","arxiv_id":"2106.06981","n_code_links":5,"syntology":{"ran":11,"of":18,"n_ran_checked":7,"n_instrument":4,"unverified":7,"pointer_only":5,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["tech-srl/RASP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"curriculum-pre-training-heterogeneous","title":"Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation","date":"2021-06-12","arxiv_id":"2106.06722","n_code_links":0,"syntology":null},{"paper":"/paper/ds-transunet-dual-swin-transformer-u-net-for","slug":"ds-transunet-dual-swin-transformer-u-net-for","title":"DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation","date":"2021-06-12","arxiv_id":"2106.06716","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["TianBaoGe/DS-TransUNet"],"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","unlocated"]}}}],"record_sha256":"994caa8a1c880262fdbdf5da582390980e7c655a6278d8b502a1712ee8827d8d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}