{"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/116","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":116,"pages_in_order":140,"rows_per_page":100,"rows":[11501,11600],"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/115","next":"/method/transformer/papers/117","papers":[{"paper":null,"slug":"generative-pre-trained-transformer-for","title":"Generative Pre-Trained Transformer for Cardiac Abnormality Detection","date":"2021-10-07","arxiv_id":"2110.04071","n_code_links":0,"syntology":null},{"paper":"/paper/layer-wise-pruning-of-transformer-attention","slug":"layer-wise-pruning-of-transformer-attention","title":"Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling","date":"2021-10-07","arxiv_id":"2110.03252","n_code_links":1,"syntology":null},{"paper":null,"slug":"minimum-word-error-training-for-non","title":"Minimum word error training for non-autoregressive Transformer-based code-switching ASR","date":"2021-10-07","arxiv_id":"2110.03573","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-robustness-comparison-of-vision","slug":"adversarial-robustness-comparison-of-vision","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","date":"2021-10-06","arxiv_id":"2110.02797","n_code_links":1,"syntology":null},{"paper":"/paper/anomaly-transformer-time-series-anomaly","slug":"anomaly-transformer-time-series-anomaly","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","date":"2021-10-06","arxiv_id":"2110.02642","n_code_links":3,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["thuml/Anomaly-Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamically-decoding-source-domain-knowledge","title":"Dynamically Decoding Source Domain Knowledge for Domain Generalization","date":"2021-10-06","arxiv_id":"2110.03027","n_code_links":0,"syntology":null},{"paper":"/paper/geometric-transformers-for-protein-interface","slug":"geometric-transformers-for-protein-interface","title":"Geometric Transformers for Protein Interface Contact Prediction","date":"2021-10-06","arxiv_id":"2110.02423","n_code_links":2,"syntology":null},{"paper":null,"slug":"how-bpe-affects-memorization-in-transformers","title":"How BPE Affects Memorization in Transformers","date":"2021-10-06","arxiv_id":"2110.02782","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-iteratively-solve-routing","slug":"learning-to-iteratively-solve-routing","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","date":"2021-10-06","arxiv_id":"2110.02544","n_code_links":2,"syntology":{"ran":9,"of":16,"n_ran_checked":9,"n_instrument":0,"unverified":7,"pointer_only":0,"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) · 7 unverified","official":{"repos":["yining043/VRP-DACT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/on-neurons-invariant-to-sentence-structural","slug":"on-neurons-invariant-to-sentence-structural","title":"On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation","date":"2021-10-06","arxiv_id":"2110.03067","n_code_links":1,"syntology":null},{"paper":"/paper/ponet-pooling-network-for-efficient-token","slug":"ponet-pooling-network-for-efficient-token","title":"PoNet: Pooling Network for Efficient Token Mixing in Long Sequences","date":"2021-10-06","arxiv_id":"2110.02442","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":11,"phrase":"11 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lxchtan/ponet"],"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":["found_in_text"]}}},{"paper":"/paper/semantic-prediction-which-one-should-come","slug":"semantic-prediction-which-one-should-come","title":"Semantic Prediction: Which One Should Come First, Recognition or Prediction?","date":"2021-10-06","arxiv_id":"2110.02829","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-twitter-as-source-of-large-corpora","slug":"exploiting-twitter-as-source-of-large-corpora","title":"Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings","date":"2021-10-05","arxiv_id":"2110.02030","n_code_links":1,"syntology":null},{"paper":"/paper/sicilian-translator-a-recipe-for-low-resource","slug":"sicilian-translator-a-recipe-for-low-resource","title":"Sicilian Translator: A Recipe for Low-Resource NMT","date":"2021-10-05","arxiv_id":"2110.01938","n_code_links":1,"syntology":null},{"paper":"/paper/sound-event-detection-transformer-an-event","slug":"sound-event-detection-transformer-an-event","title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection","date":"2021-10-05","arxiv_id":"2110.02011","n_code_links":1,"syntology":null},{"paper":"/paper/top-n-equivariant-set-and-graph-generation","slug":"top-n-equivariant-set-and-graph-generation","title":"Top-N: Equivariant set and graph generation without exchangeability","date":"2021-10-05","arxiv_id":"2110.02096","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":6,"phrase":"4 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cvignac/top-n"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/word-acquisition-in-neural-language-models","slug":"word-acquisition-in-neural-language-models","title":"Word Acquisition in Neural Language Models","date":"2021-10-05","arxiv_id":"2110.02406","n_code_links":1,"syntology":null},{"paper":"/paper/3d-transformer-molecular-representation-with","slug":"3d-transformer-molecular-representation-with","title":"Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs","date":"2021-10-04","arxiv_id":"2110.01191","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["smiles724/3d-transformer","smiles724/molformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-free-lunch-from-vit-adaptive-attention","slug":"a-free-lunch-from-vit-adaptive-attention","title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","date":"2021-10-04","arxiv_id":"2110.01240","n_code_links":0,"syntology":null},{"paper":"/paper/vtamiq-transformers-for-attention-modulated","slug":"vtamiq-transformers-for-attention-modulated","title":"VTAMIQ: Transformers for Attention Modulated Image Quality Assessment","date":"2021-10-04","arxiv_id":"2110.01655","n_code_links":1,"syntology":null},{"paper":null,"slug":"music-playlist-title-generation-a-machine","title":"Music Playlist Title Generation: A Machine-Translation Approach","date":"2021-10-03","arxiv_id":"2110.07354","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-and-explicit-attention-for-zero-shot","slug":"implicit-and-explicit-attention-for-zero-shot","title":"Implicit and Explicit Attention for Zero-Shot Learning","date":"2021-10-02","arxiv_id":"2110.00860","n_code_links":1,"syntology":null},{"paper":"/paper/proto-program-guided-transformer-for-program","slug":"proto-program-guided-transformer-for-program","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","date":"2021-10-02","arxiv_id":"2110.00804","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":["sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks"],"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":"data-efficient-instance-segmentation-with-a","title":"3rd Place Scheme on Instance Segmentation Track of ICCV 2021 VIPriors Challenges","date":"2021-10-01","arxiv_id":"2110.00242","n_code_links":0,"syntology":null},{"paper":"/paper/geometry-attention-transformer-with-position","slug":"geometry-attention-transformer-with-position","title":"Geometry Attention Transformer with Position-aware LSTMs for Image Captioning","date":"2021-10-01","arxiv_id":"2110.00335","n_code_links":1,"syntology":null},{"paper":null,"slug":"bitcoin-transaction-strategy-construction","title":"Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.14789","n_code_links":0,"syntology":null},{"paper":"/paper/gt-u-net-a-u-net-like-group-transformer","slug":"gt-u-net-a-u-net-like-group-transformer","title":"GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation","date":"2021-09-30","arxiv_id":"2109.14813","n_code_links":1,"syntology":null},{"paper":"/paper/inducing-transformer-s-compositional","slug":"inducing-transformer-s-compositional","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","date":"2021-09-30","arxiv_id":"2109.15256","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-predict-trustworthiness-with","slug":"learning-to-predict-trustworthiness-with","title":"Learning to Predict Trustworthiness with Steep Slope Loss","date":"2021-09-30","arxiv_id":"2110.00054","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["luoyan407/predict_trustworthiness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mobtcast-leveraging-auxiliary-trajectory","title":"MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction","date":"2021-09-30","arxiv_id":"2110.01401","n_code_links":0,"syntology":null},{"paper":"/paper/prose2poem-the-blessing-of-transformer-based","slug":"prose2poem-the-blessing-of-transformer-based","title":"Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry","date":"2021-09-30","arxiv_id":"2109.14934","n_code_links":1,"syntology":null},{"paper":"/paper/redesigning-the-transformer-architecture-with","slug":"redesigning-the-transformer-architecture-with","title":"Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems","date":"2021-09-30","arxiv_id":"2109.15142","n_code_links":1,"syntology":null},{"paper":"/paper/scientific-evidence-extraction","slug":"scientific-evidence-extraction","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","date":"2021-09-30","arxiv_id":"2110.00061","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"11 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/table-transformer"],"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":"/paper/syntactic-persistence-in-language-models","slug":"syntactic-persistence-in-language-models","title":"Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations","date":"2021-09-30","arxiv_id":"2109.14989","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-collaborative-attention-adaptive-network","title":"A Collaborative Attention Adaptive Network for Financial Market Forecasting","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-dot-product-attention-free-transformer","slug":"a-dot-product-attention-free-transformer","title":"A Dot Product Attention Free Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-control-flow-in-transformers","title":"Adaptive Control Flow in Transformers Improves Systematic Generalization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-wavelet-transformer-network-for-3d","title":"Adaptive Wavelet Transformer Network for 3D Shape Representation Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-investigation-on-hardware-aware-vision","title":"An Investigation on Hardware-Aware Vision Transformer Scaling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-object-centric-sensitivity-analysis-of","title":"An object-centric sensitivity analysis of deep learning based instance segmentation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-implicit-position-encoding","title":"Analyzing the Implicit Position Encoding Ability of Transformer Decoder","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-vision-transformers-robust-to-patch-wise","title":"Are Vision Transformers Robust to Patch-wise Perturbations?","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"associated-learning-an-alternative-to-end-to","title":"Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-based-interpretability-with-concept","title":"Attention-based Interpretability with Concept Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-lottery-speech-recognition-made-ultra","title":"Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"coarformer-transformer-for-large-graph-via","title":"Coarformer: Transformer for large graph via graph coarsening","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"crossformer-transformer-with-alternated-cross","title":"Crossformer: Transformer with Alternated Cross-Layer Guidance","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"d-2-etr-decoder-only-detr-with","title":"D$^2$ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"distributional-decision-transformer-for","title":"Distributional Decision Transformer for Hindsight Information Matching","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-point-transformer-for-large-scale","title":"Efficient Point Transformer for Large-scale 3D Scene Understanding","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"equivariant-transformers-for-neural-network","title":"Equivariant Transformers for Neural Network based Molecular Potentials","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ernie-sparse-robust-efficient-transformer","title":"ERNIE-SPARSE: Robust Efficient Transformer Through Hierarchically Unifying Isolated Information","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fairness-in-representation-for-multilingual","title":"Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gental-generative-denoising-skip-gram","title":"GenTAL: Generative Denoising Skip-gram Transformer for Unsupervised Binary Code Similarity Detection","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"geometry-entangled-visual-semantic","title":"Geometry-Entangled Visual Semantic Transformer for Image Captioning","date":"2021-09-29","arxiv_id":"2109.14137","n_code_links":0,"syntology":null},{"paper":null,"slug":"graphix-a-pre-trained-graph-edit-model-for","title":"GRAPHIX: A Pre-trained Graph Edit Model for Automated Program Repair","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-language-representation-with-visual","title":"Grounding Language Representation with Visual Object Information via Cross Modal Pretraining","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-transformers-to-process-in-steps","title":"Guiding Transformers to Process in Steps","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hfsp-a-hardware-friendly-soft-pruning","title":"HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-character-tagger-for-short-text","title":"Hierarchical Character Tagger for Short Text Spelling Error Correction","date":"2021-09-29","arxiv_id":"2109.14259","n_code_links":0,"syntology":null},{"paper":null,"slug":"holoformer-deep-compression-of-pre-trained","title":"HoloFormer: Deep Compression of Pre-Trained Transforms via Unified Optimization of N:M Sparsity and Integer Quantization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"isotropic-contextual-representations-through","title":"Isotropic Contextual Representations through Variational Regularization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-schedule-learning-rate-with-graph","title":"Learning to Schedule Learning rate with Graph Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lmsa-low-relation-mutil-head-self-attention","title":"LMSA: Low-relation Mutil-head Self-Attention Mechanism in Visual Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/mait-integrating-spatial-locality-into-image","slug":"mait-integrating-spatial-locality-into-image","title":"MaiT: integrating spatial locality into image transformers with attention masks","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mlp-based-architecture-with-variable-length","title":"MLP-based architecture with variable length input for automatic speech recognition","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"non-autoregressive-models-are-better","title":"Non-Autoregressive Models are Better Multilingual Translators","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-pre-trained-multi-agent-decision","title":"Offline Pre-trained Multi-Agent Decision Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pretraining-for-language-conditioned","title":"Pretraining for Language Conditioned Imitation with Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/privacy-preserving-task-agnostic-vision","slug":"privacy-preserving-task-agnostic-vision","title":"Privacy-preserving Task-Agnostic Vision Transformer for Image Processing","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"scale-efficiently-insights-from-pretraining","title":"Scale Efficiently: Insights from Pretraining and Finetuning Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-the-depth-of-vision-transformers-via","title":"Scaling the Depth of Vision Transformers via the Fourier Domain Analysis","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-offline-reinforcement","title":"Semi-supervised Offline Reinforcement Learning with Pre-trained Decision Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sit-simulation-transformer-for-particle-based","title":"SiT: Simulation Transformer for Particle-based Physics Simulation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spanning-tree-based-graph-generation-for","title":"Spanning Tree-based Graph Generation for Molecules","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-attention-with-learning-to-hash","title":"Sparse Attention with Learning to Hash","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"specialized-transformers-faster-smaller-and","title":"Specialized Transformers: Faster, Smaller and more Accurate NLP Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/subdimensional-expansion-using-attention","slug":"subdimensional-expansion-using-attention","title":"Subdimensional Expansion Using Attention-Based Learning For Multi-Agent Path Finding","date":"2021-09-29","arxiv_id":"2109.14695","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-action-localization-with-global","title":"Temporal Action Localization with Global Segmentation Mask Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"topic-aware-neural-language-model-domain","title":"Topic Aware Neural Language Model: Domain Adaptation of Unconditional Text Generation Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transtcn-an-attention-based-tcn-framework-for","title":"TransTCN: An Attention-based TCN Framework for Sequential Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tuformer-data-driven-design-of-expressive","title":"Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ufo-vit-high-performance-linear-vision","slug":"ufo-vit-high-performance-linear-vision","title":"UFO-ViT: High Performance Linear Vision Transformer without Softmax","date":"2021-09-29","arxiv_id":"2109.14382","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-role-of-self-attention-for","title":"Understanding the Role of Self Attention for Efficient Speech Recognition","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"video-forgery-detection-using-multiple-cues","title":"Video Forgery Detection Using Multiple Cues on Fusion of EfficientNet and Swin Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vut-versatile-ui-transformer-for-multimodal","title":"VUT: Versatile UI Transformer for Multimodal Multi-Task User Interface Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-vision-transformers-for-the","title":"Fine-tuning Vision Transformers for the Prediction of State Variables in Ising Models","date":"2021-09-28","arxiv_id":"2109.13925","n_code_links":0,"syntology":null},{"paper":null,"slug":"nana-hdr-a-non-attentive-non-autoregressive","title":"Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS","date":"2021-09-28","arxiv_id":"2109.13673","n_code_links":0,"syntology":null},{"paper":"/paper/single-dataset-experts-for-multi-dataset","slug":"single-dataset-experts-for-multi-dataset","title":"Single-dataset Experts for Multi-dataset Question Answering","date":"2021-09-28","arxiv_id":"2109.13880","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":10,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/made"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-md-fast-multi-decoder-end-to-end-speech","slug":"fast-md-fast-multi-decoder-end-to-end-speech","title":"Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates","date":"2021-09-27","arxiv_id":"2109.12804","n_code_links":1,"syntology":null},{"paper":"/paper/improving-stack-overflow-question-title","slug":"improving-stack-overflow-question-title","title":"Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information","date":"2021-09-27","arxiv_id":"2109.13073","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrated-training-for-sequence-to-sequence","title":"Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer","date":"2021-09-27","arxiv_id":"2109.12950","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-spatial-transformers-for-few-shot","slug":"sparse-spatial-transformers-for-few-shot","title":"Sparse Spatial Transformers for Few-Shot Learning","date":"2021-09-27","arxiv_id":"2109.12932","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["chenhaoxing/ssformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-transformer-a-new-neural-network-based","slug":"multi-transformer-a-new-neural-network-based","title":"Multi-Transformer: A New Neural Network-Based Architecture for Forecasting S&P Volatility","date":"2021-09-26","arxiv_id":"2109.12621","n_code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-hashing-for-image","slug":"vision-transformer-hashing-for-image","title":"Vision Transformer Hashing for Image Retrieval","date":"2021-09-26","arxiv_id":"2109.12564","n_code_links":1,"syntology":null},{"paper":null,"slug":"vit-cane-visual-assistant-for-the-visually","title":"ViT Cane: Visual Assistant for the Visually Impaired","date":"2021-09-26","arxiv_id":"2109.13857","n_code_links":0,"syntology":null},{"paper":null,"slug":"temgnet-deep-transformer-based-decoding-of","title":"TEMGNet: Deep Transformer-based Decoding of Upperlimb sEMG for Hand Gestures Recognition","date":"2021-09-25","arxiv_id":"2109.12379","n_code_links":0,"syntology":null},{"paper":null,"slug":"dact-bert-differentiable-adaptive-computation","title":"DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference","date":"2021-09-24","arxiv_id":"2109.11745","n_code_links":0,"syntology":null},{"paper":null,"slug":"identification-of-enzymatic-active-sites-with","title":"Identification of Enzymatic Active Sites with Unsupervised Language Modeling","date":"2021-09-24","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"localizing-infinity-shaped-fishes-sketch","title":"Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild","date":"2021-09-24","arxiv_id":"2109.11874","n_code_links":0,"syntology":null}],"record_sha256":"db609b372a0cffb9aa4c88ff4bc6a699fe49ca555df6a82bd7cd76de94e3c605","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}