{"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/114","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":114,"pages_in_order":140,"rows_per_page":100,"rows":[11301,11400],"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/113","next":"/method/transformer/papers/115","papers":[{"paper":null,"slug":"empirical-analysis-of-training-strategies-of-1","title":"Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-sign-language-translation-via","title":"End-To-End Sign Language Translation via Multitask Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-nonlinear-mutual-dependencies","title":"Enhancing the Nonlinear Mutual Dependencies in Transformers with Mutual Information","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ernie-sparse-learning-hierarchical-efficient","title":"ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-multi-label-text-classification-with-1","title":"Extreme Multi-label Text Classification with Multi-layer Experts","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-accurate-transformer-based","title":"Fast and Accurate Transformer-based Translation with Character-Level Encoding and Subword-Level Decoding","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fix-bugs-with-transformer-through-a-neural","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-diverse-and-high-quality","title":"Generating Diverse and High-Quality Abstractive Summaries with Variational Transformers","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"input-specific-attention-subnetworks-for","title":"Input-specific Attention Subnetworks for Adversarial Detection","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-guided-transformer-for-joint-theme","title":"Knowledge-guided Transformer for Joint Theme and Emotion Classification of Chinese Classical Poetry","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-methods-for-solving-astronomy-course","title":"Learning Methods for Solving Astronomy Course Problems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-non-autoregressive-models-from","title":"Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"listen-to-both-sides-and-be-enlightened","title":"Listen to Both Sides and be Enlightened! -- Hierarchical Modality Fusion Network for Entity and Relation Extraction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"making-transformers-solve-compositional-tasks-1","title":"Making Transformers Solve Compositional Tasks","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"marcqap-effective-context-modeling-for","title":"MarCQAp: Effective Context Modeling for Conversational Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/modeling-hierarchical-syntax-structure-with","slug":"modeling-hierarchical-syntax-structure-with","title":"Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-head-or-single-head-an-empirical-1","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"n-grammer-augmenting-transformers-with-latent","title":"N-grammer: Augmenting Transformers with latent n-grams","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-vision-features-in-multimodal-machine","title":"On Vision Features in Multimodal Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"online-advertising-revenue-forecasting-an","title":"Online Advertising Revenue Forecasting: An Interpretable Deep Learning Approach","date":"2021-11-16","arxiv_id":"2111.08840","n_code_links":0,"syntology":null},{"paper":null,"slug":"pesto-a-post-user-fusion-network-for-rumour","title":"PESTO: A Post-User Fusion Network for Rumour Detection on Social Media","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"polise-reinforcing-politeness-using-user","title":"PoliSe: Reinforcing Politeness using User Sentiment for Customer Care Response Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-based-layer-wise-adaptive","title":"Retrieval-based Layer-wise Adaptive Transformer for Source Code Summarization","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-to-sequence-amr-parsing-with","title":"Sequence-to-sequence AMR Parsing with Ancestor Information","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-to-sequence-knowledge-graph","title":"Sequence-to-Sequence Knowledge Graph Completion and Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shct-a-successively-hierarchical-conditional","title":"SHCT: A Successively Hierarchical Conditional Transformer for Controllable Paraphrase Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shrinknas-single-path-one-shot-operator","title":"ShrinkNAS : Single-Path One-Shot Operator Exploratory Training for Transformer with Dynamic Space Shrinking","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-probability-and-statistics-problems","title":"Solving Probability and Statistics Problems by Program Synthesis","date":"2021-11-16","arxiv_id":"2111.08267","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-probability-and-statistics-problems-1","title":"Solving Probability and Statistics Problems by Program Synthesis","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sparsifying-transformer-models-with-trainable","slug":"sparsifying-transformer-models-with-trainable","title":"Sparsifying Transformer Models with Trainable Representation Pooling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"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":"/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":"/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":"/paper/named-entity-recognition-for-entity-linking","slug":"named-entity-recognition-for-entity-linking","title":"Named Entity Recognition for Entity Linking: What Works and What’s Next","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/amendable-generation-for-dialogue-state","slug":"amendable-generation-for-dialogue-state","title":"Amendable Generation for Dialogue State Tracking","date":"2021-10-29","arxiv_id":"2110.15659","n_code_links":1,"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":"/paper/transformers-generalize-deepsets-and-can-be","slug":"transformers-generalize-deepsets-and-can-be","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","date":"2021-10-27","arxiv_id":"2110.14416","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["jw9730/hot"],"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":"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}],"record_sha256":"65c35ee46d6db1ed31351850ef3f981c75c409f9e2f5e198bbe36dfea354587b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}