{"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/position-wise-feed-forward-layer/papers/113","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward Layer","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":113,"pages_in_order":139,"rows_per_page":100,"rows":[11201,11300],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/112","next":"/method/position-wise-feed-forward-layer/papers/114","papers":[{"paper":null,"slug":"speaker-profiling-in-multi-party","title":"Speaker Profiling in Multi-party Conversations","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-pruning-learns-compact-and","title":"Structured Pruning Learns Compact and Accurate Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"supershaper-task-agnostic-super-pre-training-1","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taco-pre-training-of-deep-transformers-with","title":"TACO: Pre-training of Deep Transformers with Attention Convolution using Disentangled Positional Representation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"teaching-bert-to-wait-balancing-accuracy-and","title":"Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"wets-a-benchmark-for-translation-suggestion-1","title":"WeTS: A Benchmark for Translation Suggestion","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-works-and-doesn-t-work-a-deep-decoder","title":"What Works and Doesn't Work, A Deep Decoder for Neural Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-in-games-techniques-challenges-and","title":"AI in Human-computer Gaming: Techniques, Challenges and Opportunities","date":"2021-11-15","arxiv_id":"2111.07631","n_code_links":0,"syntology":null},{"paper":null,"slug":"faketransformer-exposing-face-forgery-from","title":"FakeTransformer: Exposing Face Forgery From Spatial-Temporal Representation Modeled By Facial Pixel Variations","date":"2021-11-15","arxiv_id":"2111.07601","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-prosody-for-unseen-texts-in-speech","title":"Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data","date":"2021-11-15","arxiv_id":"2111.07549","n_code_links":0,"syntology":null},{"paper":"/paper/mask-guided-spectral-wise-transformer-for","slug":"mask-guided-spectral-wise-transformer-for","title":"Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction","date":"2021-11-15","arxiv_id":"2111.07910","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["caiyuanhao1998/MST"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"monaural-source-separation-from-anechoic-to","title":"Monaural source separation: From anechoic to reverberant environments","date":"2021-11-15","arxiv_id":"2111.07578","n_code_links":0,"syntology":null},{"paper":"/paper/local-multi-head-channel-self-attention-for","slug":"local-multi-head-channel-self-attention-for","title":"Local Multi-Head Channel Self-Attention for Facial Expression Recognition","date":"2021-11-14","arxiv_id":"2111.07224","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-image-compression","title":"Transformer-based Image Compression","date":"2021-11-12","arxiv_id":"2111.06707","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-visual-transformers","slug":"a-survey-of-visual-transformers","title":"A Survey of Visual Transformers","date":"2021-11-11","arxiv_id":"2111.06091","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-relation-transformer-incorporating","title":"Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture","date":"2021-11-11","arxiv_id":"2111.06075","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-large-scale-language-models-and","title":"Improving Large-scale Language Models and Resources for Filipino","date":"2021-11-11","arxiv_id":"2111.06053","n_code_links":0,"syntology":null},{"paper":"/paper/attention-approximates-sparse-distributed","slug":"attention-approximates-sparse-distributed","title":"Attention Approximates Sparse Distributed Memory","date":"2021-11-10","arxiv_id":"2111.05498","n_code_links":1,"syntology":{"ran":12,"of":19,"n_ran_checked":11,"n_instrument":1,"unverified":7,"pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["trentbrick/attention-approximates-sdm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/multimodal-transformer-with-variable-length","slug":"multimodal-transformer-with-variable-length","title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation","date":"2021-11-10","arxiv_id":"2111.05759","n_code_links":1,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","n_code_links":2,"syntology":null},{"paper":"/paper/soft-sensing-transformer-hundreds-of-sensors","slug":"soft-sensing-transformer-hundreds-of-sensors","title":"Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word","date":"2021-11-10","arxiv_id":"2111.05973","n_code_links":1,"syntology":null},{"paper":null,"slug":"fpm-a-collection-of-large-scale-foundation","title":"FPM: A Collection of Large-scale Foundation Pre-trained Language Models","date":"2021-11-09","arxiv_id":"2111.04909","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-prediction-of-clinical-outcomes-in","title":"Multi-Task Prediction of Clinical Outcomes in the Intensive Care Unit using Flexible Multimodal Transformers","date":"2021-11-09","arxiv_id":"2111.05431","n_code_links":0,"syntology":null},{"paper":"/paper/sliced-recursive-transformer-1","slug":"sliced-recursive-transformer-1","title":"Sliced Recursive Transformer","date":"2021-11-09","arxiv_id":"2111.05297","n_code_links":1,"syntology":null},{"paper":"/paper/guiding-multi-step-rearrangement-tasks-with","slug":"guiding-multi-step-rearrangement-tasks-with","title":"Guiding Multi-Step Rearrangement Tasks with Natural Language Instructions","date":"2021-11-08","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/mixed-transformer-u-net-for-medical-image","slug":"mixed-transformer-u-net-for-medical-image","title":"Mixed Transformer U-Net For Medical Image Segmentation","date":"2021-11-08","arxiv_id":"2111.04734","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dootmaan/mt-unet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/are-we-ready-for-a-new-paradigm-shift-a","slug":"are-we-ready-for-a-new-paradigm-shift-a","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","date":"2021-11-07","arxiv_id":"2111.04060","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-architectures-for-neural-machine","title":"Analyzing Architectures for Neural Machine Translation Using Low Computational Resources","date":"2021-11-06","arxiv_id":"2111.03813","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-data-driven-surrogate-simulators","slug":"benchmarking-data-driven-surrogate-simulators","title":"Benchmarking Data-driven Surrogate Simulators for Artificial Electromagnetic Materials","date":"2021-11-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-gated-mlp-combining","title":"Convolutional Gated MLP: Combining Convolutions & gMLP","date":"2021-11-06","arxiv_id":"2111.03940","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-visual-quality-of-image-synthesis","title":"Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers","date":"2021-11-05","arxiv_id":"2111.03481","n_code_links":0,"syntology":null},{"paper":null,"slug":"oracle-teacher-towards-better-knowledge","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","date":"2021-11-05","arxiv_id":"2111.03664","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-the-effectiveness-of-an","slug":"an-empirical-study-of-the-effectiveness-of-an","title":"An Empirical Study of the Effectiveness of an Ensemble of Stand-alone Sentiment Detection Tools for Software Engineering Datasets","date":"2021-11-04","arxiv_id":"2111.03196","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-multimodal-automl-for-tabular","slug":"benchmarking-multimodal-automl-for-tabular","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","date":"2021-11-04","arxiv_id":"2111.02705","n_code_links":2,"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":["sxjscience/automl_multimodal_benchmark","awslabs/autogluon"],"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":"/paper/mt3-multi-task-multitrack-music-transcription-1","slug":"mt3-multi-task-multitrack-music-transcription-1","title":"MT3: Multi-Task Multitrack Music Transcription","date":"2021-11-04","arxiv_id":"2111.03017","n_code_links":3,"syntology":{"ran":0,"of":6,"n_ran_checked":0,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"0 ran · 6 unverified","official":{"repos":["magenta/mt3"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"paper":null,"slug":"multi-airport-delay-prediction-with","title":"Multi-Airport Delay Prediction with Transformers","date":"2021-11-04","arxiv_id":"2111.04494","n_code_links":0,"syntology":null},{"paper":"/paper/an-explanation-of-in-context-learning-as-1","slug":"an-explanation-of-in-context-learning-as-1","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","date":"2021-11-03","arxiv_id":"2111.02080","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["p-lambda/incontext-learning"],"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":["official"]}}},{"paper":null,"slug":"prostformer-pre-trained-progressive-space","title":"ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting","date":"2021-11-03","arxiv_id":"2111.03459","n_code_links":0,"syntology":null},{"paper":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","n_code_links":2,"syntology":null},{"paper":null,"slug":"can-vision-transformers-perform-convolution-1","title":"Can Vision Transformers Perform Convolution?","date":"2021-11-02","arxiv_id":"2111.01353","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-documents-relevance-to-search","title":"Explaining Documents' Relevance to Search Queries","date":"2021-11-02","arxiv_id":"2111.01314","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-split-vision-transformer-for-covid","title":"Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training","date":"2021-11-02","arxiv_id":"2111.01338","n_code_links":0,"syntology":null},{"paper":"/paper/relational-self-attention-what-s-missing-in","slug":"relational-self-attention-what-s-missing-in","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","date":"2021-11-02","arxiv_id":"2111.01673","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["KimManjin/RSA"],"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":"accounting-for-dependencies-in-deep-learning","title":"Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging","date":"2021-11-01","arxiv_id":"2111.01556","n_code_links":0,"syntology":null},{"paper":"/paper/arch-net-model-distillation-for-architecture","slug":"arch-net-model-distillation-for-architecture","title":"Arch-Net: Model Distillation for Architecture Agnostic Model Deployment","date":"2021-11-01","arxiv_id":"2111.01135","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-lingual-hate-speech-detection-using","title":"Cross-lingual Hate Speech Detection using Transformer Models","date":"2021-11-01","arxiv_id":"2111.00981","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-generate-piano-music-with-sustain","slug":"learning-to-generate-piano-music-with-sustain","title":"Learning To Generate Piano Music With Sustain Pedals","date":"2021-11-01","arxiv_id":"2111.01216","n_code_links":1,"syntology":null},{"paper":"/paper/maple-masking-words-to-generate-blackout","slug":"maple-masking-words-to-generate-blackout","title":"MAPLE – MAsking words to generate blackout Poetry using sequence-to-sequence LEarning","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"vsec-transformer-based-model-for-vietnamese","title":"VSEC: Transformer-based Model for Vietnamese Spelling Correction","date":"2021-11-01","arxiv_id":"2111.00640","n_code_links":0,"syntology":null},{"paper":"/paper/wino-x-multilingual-winograd-schemas-for","slug":"wino-x-multilingual-winograd-schemas-for","title":"Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/cross-modality-fusion-transformer-for","slug":"cross-modality-fusion-transformer-for","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","date":"2021-10-30","arxiv_id":"2111.00273","n_code_links":1,"syntology":null},{"paper":"/paper/patchformer-a-versatile-3d-transformer-based","slug":"patchformer-a-versatile-3d-transformer-based","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","date":"2021-10-30","arxiv_id":"2111.00207","n_code_links":0,"syntology":null},{"paper":"/paper/delayed-propagation-transformer-a-universal","slug":"delayed-propagation-transformer-a-universal","title":"Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems","date":"2021-10-29","arxiv_id":"2110.15926","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vita-group/dept"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/structure-aware-fine-tuning-of-sequence-to","slug":"structure-aware-fine-tuning-of-sequence-to","title":"Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing","date":"2021-10-29","arxiv_id":"2110.15534","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-sequence-to-sequence-model-for-extracting","title":"A Sequence to Sequence Model for Extracting Multiple Product Name Entities from Dialog","date":"2021-10-28","arxiv_id":"2110.14843","n_code_links":0,"syntology":null},{"paper":"/paper/colossal-ai-a-unified-deep-learning-system","slug":"colossal-ai-a-unified-deep-learning-system","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","date":"2021-10-28","arxiv_id":"2110.14883","n_code_links":1,"syntology":null},{"paper":null,"slug":"dispensed-transformer-network-for","title":"Dispensed Transformer Network for Unsupervised Domain Adaptation","date":"2021-10-28","arxiv_id":"2110.14944","n_code_links":0,"syntology":null},{"paper":null,"slug":"nxmtransformer-semi-structured-sparsification","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","date":"2021-10-28","arxiv_id":"2110.15766","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-attention-heads-of-transformer-models","title":"Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures","date":"2021-10-28","arxiv_id":"2110.15225","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-representation-learning-on-1","slug":"self-supervised-representation-learning-on-1","title":"Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction","date":"2021-10-28","arxiv_id":"2110.15288","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"pointer_only":15,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hsg-aiml/neurips_2021-weight_space_learning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"detecting-dementia-from-speech-and","title":"Detecting Dementia from Speech and Transcripts using Transformers","date":"2021-10-27","arxiv_id":"2110.14769","n_code_links":0,"syntology":null},{"paper":"/paper/discovering-non-monotonic-autoregressive","slug":"discovering-non-monotonic-autoregressive","title":"Discovering Non-monotonic Autoregressive Orderings with Variational Inference","date":"2021-10-27","arxiv_id":"2110.15797","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":1,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["xuanlinli17/autoregressive_inference"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transfer-learning-with-causal-counterfactual","title":"Transfer learning with causal counterfactual reasoning in Decision Transformers","date":"2021-10-27","arxiv_id":"2110.14355","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-for-classification-of","title":"Vision Transformer for Classification of Breast Ultrasound Images","date":"2021-10-27","arxiv_id":"2110.14731","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-t-fool-me-adversarially-robust","title":"Can't Fool Me: Adversarially Robust Transformer for Video Understanding","date":"2021-10-26","arxiv_id":"2110.13950","n_code_links":0,"syntology":null},{"paper":"/paper/geometric-transformer-for-end-to-end-molecule","slug":"geometric-transformer-for-end-to-end-molecule","title":"Geometric Transformer for End-to-End Molecule Properties Prediction","date":"2021-10-26","arxiv_id":"2110.13721","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: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yoniLc/GeometricTransformerMolecule"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hierarchical-transformers-are-more-efficient","slug":"hierarchical-transformers-are-more-efficient","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2021-10-26","arxiv_id":"2110.13711","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google/trax"],"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"]}}},{"paper":null,"slug":"leveraging-local-temporal-information-for","title":"Leveraging Local Temporal Information for Multimodal Scene Classification","date":"2021-10-26","arxiv_id":"2110.13992","n_code_links":0,"syntology":null},{"paper":"/paper/wavlm-large-scale-self-supervised-pre","slug":"wavlm-large-scale-self-supervised-pre","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","date":"2021-10-26","arxiv_id":"2110.13900","n_code_links":9,"syntology":null},{"paper":"/paper/actions-speak-louder-than-listening","slug":"actions-speak-louder-than-listening","title":"Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience","date":"2021-10-25","arxiv_id":"2110.12855","n_code_links":1,"syntology":null},{"paper":"/paper/doctr-document-image-transformer-for","slug":"doctr-document-image-transformer-for","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","date":"2021-10-25","arxiv_id":"2110.12942","n_code_links":2,"syntology":null},{"paper":null,"slug":"gophormer-ego-graph-transformer-for-node","title":"Gophormer: Ego-Graph Transformer for Node Classification","date":"2021-10-25","arxiv_id":"2110.13094","n_code_links":0,"syntology":null},{"paper":"/paper/history-aware-multimodal-transformer-for","slug":"history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","arxiv_id":"2110.13309","n_code_links":1,"syntology":{"ran":7,"of":15,"n_ran_checked":7,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"7 ran (of which 3 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) · 8 unverified","official":null}},{"paper":"/paper/iconqa-a-new-benchmark-for-abstract-diagram","slug":"iconqa-a-new-benchmark-for-abstract-diagram","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","date":"2021-10-25","arxiv_id":"2110.13214","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lupantech/iconqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mvt-multi-view-vision-transformer-for-3d","slug":"mvt-multi-view-vision-transformer-for-3d","title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","date":"2021-10-25","arxiv_id":"2110.13083","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shanshuo/MVT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"revisiting-cnn-for-highly-inflected-bengali","title":"Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language","date":"2021-10-25","arxiv_id":"2110.13032","n_code_links":0,"syntology":null},{"paper":null,"slug":"stransgan-an-empirical-study-on-transformer-1","title":"The Nuts and Bolts of Adopting Transformer in GANs","date":"2021-10-25","arxiv_id":"2110.13107","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-source-separation-by-steering","slug":"unsupervised-source-separation-by-steering","title":"Unsupervised Source Separation By Steering Pretrained Music Models","date":"2021-10-25","arxiv_id":"2110.13071","n_code_links":1,"syntology":null},{"paper":"/paper/cvt-assd-convolutional-vision-transformer","slug":"cvt-assd-convolutional-vision-transformer","title":"CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox Detector","date":"2021-10-24","arxiv_id":"2110.12364","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-countable-armed-bandit-with-vanishing","title":"Bandits with Dynamic Arm-acquisition Costs","date":"2021-10-23","arxiv_id":"2110.12118","n_code_links":0,"syntology":null},{"paper":"/paper/3d-anas-v2-grafting-transformer-module-on","slug":"3d-anas-v2-grafting-transformer-module-on","title":"Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification","date":"2021-10-21","arxiv_id":"2110.11084","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-acceleration-with-dynamic-sparse","title":"Transformer Acceleration with Dynamic Sparse Attention","date":"2021-10-21","arxiv_id":"2110.11299","n_code_links":0,"syntology":null},{"paper":null,"slug":"vis-top-visual-transformer-overlay-processor","title":"Vis-TOP: Visual Transformer Overlay Processor","date":"2021-10-21","arxiv_id":"2110.10957","n_code_links":0,"syntology":null},{"paper":null,"slug":"after-unet-axial-fusion-transformer-unet-for","title":"AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation","date":"2021-10-20","arxiv_id":"2110.10403","n_code_links":0,"syntology":null},{"paper":"/paper/aniformer-data-driven-3d-animation-with","slug":"aniformer-data-driven-3d-animation-with","title":"AniFormer: Data-driven 3D Animation with Transformer","date":"2021-10-20","arxiv_id":"2110.10533","n_code_links":1,"syntology":null},{"paper":null,"slug":"continual-learning-in-multilingual-nmt-via","title":"Continual Learning in Multilingual NMT via Language-Specific Embeddings","date":"2021-10-20","arxiv_id":"2110.10478","n_code_links":0,"syntology":null},{"paper":null,"slug":"esod-edge-based-task-scheduling-for-object","title":"ESOD:Edge-based Task Scheduling for Object Detection","date":"2021-10-20","arxiv_id":"2110.11342","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-temporal-action-localization-with","slug":"few-shot-temporal-action-localization-with","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","date":"2021-10-20","arxiv_id":"2110.10552","n_code_links":1,"syntology":null},{"paper":null,"slug":"sea-graph-shell-attention-in-graph-neural","title":"SEA: Graph Shell Attention in Graph Neural Networks","date":"2021-10-20","arxiv_id":"2110.10674","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-accurate-and-reliable-iris","title":"Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning","date":"2021-10-20","arxiv_id":"2110.10334","n_code_links":0,"syntology":null},{"paper":null,"slug":"vldeformer-learning-visual-semantic","title":"VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval","date":"2021-10-20","arxiv_id":"2110.11338","n_code_links":0,"syntology":null},{"paper":"/paper/a-picture-is-worth-a-thousand-words-a-unified","slug":"a-picture-is-worth-a-thousand-words-a-unified","title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation","date":"2021-10-19","arxiv_id":"2110.09756","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-framework-of-transformer-by","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","date":"2021-10-19","arxiv_id":"2110.10030","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilateral-vit-for-robust-fovea-localization","title":"Bilateral-ViT for Robust Fovea Localization","date":"2021-10-19","arxiv_id":"2110.09860","n_code_links":0,"syntology":null},{"paper":null,"slug":"detectornet-transformer-enhanced-spatial","title":"DetectorNet: Transformer-enhanced Spatial Temporal Graph Neural Network for Traffic Prediction","date":"2021-10-19","arxiv_id":"2111.00869","n_code_links":0,"syntology":null},{"paper":"/paper/generating-symbolic-reasoning-problems-with-1","slug":"generating-symbolic-reasoning-problems-with-1","title":"Generating Symbolic Reasoning Problems with Transformer GANs","date":"2021-10-19","arxiv_id":"2110.10054","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["reactive-systems/TGAN-SR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"inductive-biases-and-variable-creation-in-1","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","date":"2021-10-19","arxiv_id":"2110.10090","n_code_links":0,"syntology":null},{"paper":"/paper/permutation-invariant-graph-to-sequence-model-1","slug":"permutation-invariant-graph-to-sequence-model-1","title":"Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction","date":"2021-10-19","arxiv_id":"2110.09681","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":{"repos":["coleygroup/graph2smiles"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"spatial-temporal-transformer-for-3d-point","title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","date":"2021-10-19","arxiv_id":"2110.09783","n_code_links":0,"syntology":null},{"paper":"/paper/ssast-self-supervised-audio-spectrogram","slug":"ssast-self-supervised-audio-spectrogram","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","date":"2021-10-19","arxiv_id":"2110.09784","n_code_links":3,"syntology":{"ran":13,"of":16,"n_ran_checked":13,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["YuanGongND/ssast"],"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"]}}}],"record_sha256":"ac92a5e46b4900dfe84ddcbcf3472cb504affe11040ae05986fee5bbf281a75a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}