{"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/bpe/papers/164","list_of":"/method/bpe","method":"BPE","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":164,"pages_in_order":190,"rows_per_page":100,"rows":[16301,16400],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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/bpe","prev":"/method/bpe/papers/163","next":"/method/bpe/papers/165","papers":[{"paper":"/paper/emailsum-abstractive-email-thread","slug":"emailsum-abstractive-email-thread","title":"EmailSum: Abstractive Email Thread Summarization","date":"2021-07-30","arxiv_id":"2107.14691","n_code_links":1,"syntology":null},{"paper":null,"slug":"learnable-compression-network-with","title":"Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search","date":"2021-07-30","arxiv_id":"2107.14415","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-self-attention-via-vision","slug":"multi-head-self-attention-via-vision","title":"Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning","date":"2021-07-30","arxiv_id":"2108.00045","n_code_links":2,"syntology":null},{"paper":"/paper/product1m-towards-weakly-supervised-instance","slug":"product1m-towards-weakly-supervised-instance","title":"Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining","date":"2021-07-30","arxiv_id":"2107.14572","n_code_links":1,"syntology":null},{"paper":null,"slug":"real-time-streaming-perception-system-for","title":"Real-time Streaming Perception System for Autonomous Driving","date":"2021-07-30","arxiv_id":"2107.14388","n_code_links":0,"syntology":null},{"paper":"/paper/structural-guidance-for-transformer-language","slug":"structural-guidance-for-transformer-language","title":"Structural Guidance for Transformer Language Models","date":"2021-07-30","arxiv_id":"2108.00104","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":10,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["IBM/transformers-struct-guidance"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adapting-gpt-gpt-2-and-bert-language-models","title":"Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition","date":"2021-07-29","arxiv_id":"2108.07789","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-transformer-based-dual","title":"Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection","date":"2021-07-29","arxiv_id":"2107.13720","n_code_links":0,"syntology":null},{"paper":null,"slug":"ppt-fusion-pyramid-patch-transformerfor-a","title":"PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion","date":"2021-07-29","arxiv_id":"2107.13967","n_code_links":0,"syntology":null},{"paper":"/paper/reformer-the-relational-transformer-for-image","slug":"reformer-the-relational-transformer-for-image","title":"ReFormer: The Relational Transformer for Image Captioning","date":"2021-07-29","arxiv_id":"2107.14178","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-transformer-for-multivariate","slug":"self-supervised-transformer-for-multivariate","title":"Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series","date":"2021-07-29","arxiv_id":"2107.14293","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["sindhura97/STraTS"],"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":null,"slug":"using-perturbed-length-aware-positional","title":"Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation","date":"2021-07-29","arxiv_id":"2107.13689","n_code_links":0,"syntology":null},{"paper":"/paper/bi-bimodal-modality-fusion-for-correlation","slug":"bi-bimodal-modality-fusion-for-correlation","title":"Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis","date":"2021-07-28","arxiv_id":"2107.13669","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["declare-lab/multimodal-deep-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/goal-oriented-script-construction","slug":"goal-oriented-script-construction","title":"Goal-Oriented Script Construction","date":"2021-07-28","arxiv_id":"2107.13189","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-rule-execution-tracking-machine-for","title":"Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation","date":"2021-07-27","arxiv_id":"2107.13077","n_code_links":0,"syntology":null},{"paper":null,"slug":"pisltrc-position-informed-sign-language","title":"PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution","date":"2021-07-27","arxiv_id":"2107.12600","n_code_links":0,"syntology":null},{"paper":"/paper/contextual-transformer-networks-for-visual","slug":"contextual-transformer-networks-for-visual","title":"Contextual Transformer Networks for Visual Recognition","date":"2021-07-26","arxiv_id":"2107.12292","n_code_links":7,"syntology":null},{"paper":"/paper/go-wider-instead-of-deeper","slug":"go-wider-instead-of-deeper","title":"Go Wider Instead of Deeper","date":"2021-07-25","arxiv_id":"2107.11817","n_code_links":1,"syntology":null},{"paper":"/paper/h-transformer-1d-fast-one-dimensional","slug":"h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","date":"2021-07-25","arxiv_id":"2107.11906","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":6,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/confidence-aware-scheduled-sampling-for","slug":"confidence-aware-scheduled-sampling-for","title":"Confidence-Aware Scheduled Sampling for Neural Machine Translation","date":"2021-07-22","arxiv_id":"2107.10427","n_code_links":1,"syntology":null},{"paper":"/paper/ean-event-adaptive-network-for-enhanced","slug":"ean-event-adaptive-network-for-enhanced","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","date":"2021-07-22","arxiv_id":"2107.10771","n_code_links":1,"syntology":null},{"paper":"/paper/fnetar-mixing-tokens-with-autoregressive","slug":"fnetar-mixing-tokens-with-autoregressive","title":"FNetAR: Mixing Tokens with Autoregressive Fourier Transforms","date":"2021-07-22","arxiv_id":"2107.10932","n_code_links":1,"syntology":null},{"paper":"/paper/query2label-a-simple-transformer-way-to-multi","slug":"query2label-a-simple-transformer-way-to-multi","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","date":"2021-07-22","arxiv_id":"2107.10834","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SlongLiu/query2labels"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"spinning-sequence-to-sequence-models-with","title":"Spinning Sequence-to-Sequence Models with Meta-Backdoors","date":"2021-07-22","arxiv_id":"2107.10443","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsformer-time-series-transformer-for-tourism","title":"Tsformer: Time series Transformer for tourism demand forecasting","date":"2021-07-22","arxiv_id":"2107.10977","n_code_links":0,"syntology":null},{"paper":"/paper/audio-captioning-transformer","slug":"audio-captioning-transformer","title":"Audio Captioning Transformer","date":"2021-07-21","arxiv_id":"2107.09817","n_code_links":1,"syntology":null},{"paper":"/paper/cyclemlp-a-mlp-like-architecture-for-dense","slug":"cyclemlp-a-mlp-like-architecture-for-dense","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","date":"2021-07-21","arxiv_id":"2107.10224","n_code_links":8,"syntology":{"ran":10,"of":15,"n_ran_checked":10,"n_instrument":0,"unverified":5,"pointer_only":2,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ShoufaChen/CycleMLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/multi-stream-transformers","slug":"multi-stream-transformers","title":"Multi-Stream Transformers","date":"2021-07-21","arxiv_id":"2107.10342","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-scale-graph-network-with-multi-head","title":"A Multi-scale Graph Network with Multi-head Attention for Histopathology Image Diagnosis","date":"2021-07-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"crew-computation-reuse-and-efficient-weight","title":"CREW: Computation Reuse and Efficient Weight Storage for Hardware-accelerated MLPs and RNNs","date":"2021-07-20","arxiv_id":"2107.09408","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-video-transformer-can-objects-be","title":"Generative Video Transformer: Can Objects be the Words?","date":"2021-07-20","arxiv_id":"2107.09240","n_code_links":0,"syntology":null},{"paper":null,"slug":"weakly-supervised-global-local-feature","title":"Weakly Supervised Global-Local Feature Learning for Cervical Cytology Image Analysis","date":"2021-07-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clinical-relation-extraction-using","slug":"clinical-relation-extraction-using","title":"Clinical Relation Extraction Using Transformer-based Models","date":"2021-07-19","arxiv_id":"2107.08957","n_code_links":1,"syntology":null},{"paper":"/paper/image-fusion-transformer","slug":"image-fusion-transformer","title":"Image Fusion Transformer","date":"2021-07-19","arxiv_id":"2107.09011","n_code_links":1,"syntology":null},{"paper":"/paper/learning-attributed-graph-representations","slug":"learning-attributed-graph-representations","title":"Learning Attributed Graph Representations with Communicative Message Passing Transformer","date":"2021-07-19","arxiv_id":"2107.08773","n_code_links":1,"syntology":null},{"paper":"/paper/levit-unet-make-faster-encoders-with","slug":"levit-unet-make-faster-encoders-with","title":"LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation","date":"2021-07-19","arxiv_id":"2107.08623","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["apple1986/LeViT_UNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/long-term-series-forecasting-with-query","slug":"long-term-series-forecasting-with-query","title":"Long-term series forecasting with Query Selector -- efficient model of sparse attention","date":"2021-07-19","arxiv_id":"2107.08687","n_code_links":2,"syntology":null},{"paper":null,"slug":"residual-tree-aggregation-of-layers-for","title":"Residual Tree Aggregation of Layers for Neural Machine Translation","date":"2021-07-19","arxiv_id":"2107.14590","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-piano-transcription-with","slug":"sequence-to-sequence-piano-transcription-with","title":"Sequence-to-Sequence Piano Transcription with Transformers","date":"2021-07-19","arxiv_id":"2107.09142","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":null}},{"paper":null,"slug":"a-discriminative-semantic-ranker-for-question","title":"A Discriminative Semantic Ranker for Question Retrieval","date":"2021-07-18","arxiv_id":"2107.08345","n_code_links":0,"syntology":null},{"paper":"/paper/tfix-learning-to-fix-coding-errors-with-a","slug":"tfix-learning-to-fix-coding-errors-with-a","title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","date":"2021-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-transformer-for-efficient-machine","title":"Dynamic Transformer for Efficient Machine Translation on Embedded Devices","date":"2021-07-17","arxiv_id":"2107.08199","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-search-learning-query-and-product","title":"Neural Search: Learning Query and Product Representations in Fashion E-commerce","date":"2021-07-17","arxiv_id":"2107.08291","n_code_links":0,"syntology":null},{"paper":"/paper/is-attention-to-bounding-boxes-all-you-need","slug":"is-attention-to-bounding-boxes-all-you-need","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","date":"2021-07-16","arxiv_id":"2107.08031","n_code_links":0,"syntology":null},{"paper":"/paper/learning-sparse-interaction-graphs-of","slug":"learning-sparse-interaction-graphs-of","title":"Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction","date":"2021-07-15","arxiv_id":"2107.07056","n_code_links":1,"syntology":null},{"paper":"/paper/star-sparse-transformer-based-action","slug":"star-sparse-transformer-based-action","title":"STAR: Sparse Transformer-based Action Recognition","date":"2021-07-15","arxiv_id":"2107.07089","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-machine-learning-for-fast","slug":"transformer-based-machine-learning-for-fast","title":"Transformer-based Machine Learning for Fast SAT Solvers and Logic Synthesis","date":"2021-07-15","arxiv_id":"2107.07116","n_code_links":1,"syntology":null},{"paper":"/paper/turning-tables-generating-examples-from-semi","slug":"turning-tables-generating-examples-from-semi","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","date":"2021-07-15","arxiv_id":"2107.07261","n_code_links":1,"syntology":null},{"paper":"/paper/a-note-on-learning-rare-events-in-molecular","slug":"a-note-on-learning-rare-events-in-molecular","title":"A Note on Learning Rare Events in Molecular Dynamics using LSTM and Transformer","date":"2021-07-14","arxiv_id":"2107.06573","n_code_links":1,"syntology":null},{"paper":"/paper/chimera-efficiently-training-large-scale","slug":"chimera-efficiently-training-large-scale","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","date":"2021-07-14","arxiv_id":"2107.06925","n_code_links":1,"syntology":null},{"paper":"/paper/indonesia-s-fake-news-detection-using","slug":"indonesia-s-fake-news-detection-using","title":"Indonesia's Fake News Detection using Transformer Network","date":"2021-07-14","arxiv_id":"2107.06796","n_code_links":1,"syntology":null},{"paper":"/paper/scalable-memory-protection-in-the-penglai","slug":"scalable-memory-protection-in-the-penglai","title":"Scalable Memory Protection in the PENGLAI Enclave","date":"2021-07-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"serialized-multi-layer-multi-head-attention","title":"Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding","date":"2021-07-14","arxiv_id":"2107.06493","n_code_links":0,"syntology":null},{"paper":"/paper/hat-hierarchical-aggregation-transformers-for","slug":"hat-hierarchical-aggregation-transformers-for","title":"HAT: Hierarchical Aggregation Transformers for Person Re-identification","date":"2021-07-13","arxiv_id":"2107.05946","n_code_links":1,"syntology":null},{"paper":"/paper/the-piano-inpainting-application","slug":"the-piano-inpainting-application","title":"The Piano Inpainting Application","date":"2021-07-13","arxiv_id":"2107.05944","n_code_links":2,"syntology":null},{"paper":"/paper/mect-multi-metadata-embedding-based-cross","slug":"mect-multi-metadata-embedding-based-cross","title":"MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition","date":"2021-07-12","arxiv_id":"2107.05418","n_code_links":1,"syntology":null},{"paper":"/paper/midibert-piano-large-scale-pre-training-for","slug":"midibert-piano-large-scale-pre-training-for","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","date":"2021-07-12","arxiv_id":"2107.05223","n_code_links":1,"syntology":null},{"paper":"/paper/moocrep-a-unified-pre-trained-embedding-of","slug":"moocrep-a-unified-pre-trained-embedding-of","title":"MOOCRep: A Unified Pre-trained Embedding of MOOC Entities","date":"2021-07-12","arxiv_id":"2107.05154","n_code_links":1,"syntology":null},{"paper":"/paper/transattunet-multi-level-attention-guided-u","slug":"transattunet-multi-level-attention-guided-u","title":"TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation","date":"2021-07-12","arxiv_id":"2107.05274","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-transformer-with-statistical-test-for","title":"Visual Transformer with Statistical Test for COVID-19 Classification","date":"2021-07-12","arxiv_id":"2107.05334","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-with-multi-modal-features-and","slug":"transformers-with-multi-modal-features-and","title":"Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation","date":"2021-07-11","arxiv_id":"2107.05124","n_code_links":0,"syntology":null},{"paper":"/paper/consensual-collaborative-training-and","slug":"consensual-collaborative-training-and","title":"Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations","date":"2021-07-10","arxiv_id":"2107.04746","n_code_links":3,"syntology":null},{"paper":"/paper/few-shot-domain-adaptation-with-polymorphic","slug":"few-shot-domain-adaptation-with-polymorphic","title":"Few-Shot Domain Adaptation with Polymorphic Transformers","date":"2021-07-10","arxiv_id":"2107.04805","n_code_links":1,"syntology":null},{"paper":null,"slug":"local-to-global-self-attention-in-vision","title":"Local-to-Global Self-Attention in Vision Transformers","date":"2021-07-10","arxiv_id":"2107.04735","n_code_links":0,"syntology":null},{"paper":"/paper/can-deep-neural-networks-predict-data","slug":"can-deep-neural-networks-predict-data","title":"Can Deep Neural Networks Predict Data Correlations from Column Names?","date":"2021-07-09","arxiv_id":"2107.04553","n_code_links":1,"syntology":null},{"paper":"/paper/affect-expression-behaviour-analysis-in-the-1","slug":"affect-expression-behaviour-analysis-in-the-1","title":"Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training","date":"2021-07-08","arxiv_id":"2107.05736","n_code_links":1,"syntology":null},{"paper":null,"slug":"calliope-a-polyphonic-music-transformer","title":"Calliope -- A Polyphonic Music Transformer","date":"2021-07-08","arxiv_id":"2107.05546","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-delegate-for-large-scale-vehicle","slug":"learning-to-delegate-for-large-scale-vehicle","title":"Learning to Delegate for Large-scale Vehicle Routing","date":"2021-07-08","arxiv_id":"2107.04139","n_code_links":1,"syntology":{"ran":0,"of":6,"n_ran_checked":0,"n_instrument":0,"unverified":6,"pointer_only":6,"phrase":"0 ran · 6 unverified","official":{"repos":["mit-wu-lab/learning-to-delegate"],"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":"efficient-transformer-for-direct-speech","title":"Efficient Transformer for Direct Speech Translation","date":"2021-07-07","arxiv_id":"2107.03069","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","n_code_links":13,"syntology":{"ran":26,"of":39,"n_ran_checked":24,"n_instrument":2,"unverified":13,"pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"paper":"/paper/learning-vision-transformer-with-squeeze-and","slug":"learning-vision-transformer-with-squeeze-and","title":"Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition","date":"2021-07-07","arxiv_id":"2107.03107","n_code_links":0,"syntology":null},{"paper":null,"slug":"maccif-tdnn-multi-aspect-aggregation-of","title":"MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification","date":"2021-07-07","arxiv_id":"2107.03104","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-quite-ask-a-librarian-ai-on-the-nature","title":"Not Quite 'Ask a Librarian': AI on the Nature, Value, and Future of LIS","date":"2021-07-07","arxiv_id":"2107.05383","n_code_links":0,"syntology":null},{"paper":null,"slug":"scopeformer-n-cnn-vit-hybrid-model-for","title":"Scopeformer: n-CNN-ViT Hybrid Model for Intracranial Hemorrhage Classification","date":"2021-07-07","arxiv_id":"2107.04575","n_code_links":0,"syntology":null},{"paper":"/paper/trans4trans-efficient-transformer-for","slug":"trans4trans-efficient-transformer-for","title":"Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World","date":"2021-07-07","arxiv_id":"2107.03172","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-network-for-significant-stenosis","slug":"transformer-network-for-significant-stenosis","title":"Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries","date":"2021-07-07","arxiv_id":"2107.03035","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-size-and-pose-homogenization-with","title":"Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation","date":"2021-07-06","arxiv_id":"2107.02655","n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-pneumonia-severity-prediction-using","title":"COVID-19 Pneumonia Severity Prediction using Hybrid Convolution-Attention Neural Architectures","date":"2021-07-06","arxiv_id":"2107.02672","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-hypo-plastic-left-heart-syndrome-in","title":"Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound via Disease-specific Atlas Maps","date":"2021-07-06","arxiv_id":"2107.02643","n_code_links":0,"syntology":null},{"paper":"/paper/feature-fusion-vision-transformer-fine","slug":"feature-fusion-vision-transformer-fine","title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","date":"2021-07-06","arxiv_id":"2107.02341","n_code_links":1,"syntology":null},{"paper":"/paper/point-cloud-registration-using-representative","slug":"point-cloud-registration-using-representative","title":"Point Cloud Registration using Representative Overlapping Points","date":"2021-07-06","arxiv_id":"2107.02583","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhulf0804/ROPNet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/ernie-3-0-large-scale-knowledge-enhanced-pre","slug":"ernie-3-0-large-scale-knowledge-enhanced-pre","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-07-05","arxiv_id":"2107.02137","n_code_links":2,"syntology":null},{"paper":"/paper/long-short-transformer-efficient-transformers","slug":"long-short-transformer-efficient-transformers","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","date":"2021-07-05","arxiv_id":"2107.02192","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NVIDIA/transformer-ls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"test-time-personalization-with-a-transformer","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","date":"2021-07-05","arxiv_id":"2107.02133","n_code_links":0,"syntology":null},{"paper":"/paper/vision-xformers-efficient-attention-for-image","slug":"vision-xformers-efficient-attention-for-image","title":"Vision Xformers: Efficient Attention for Image Classification","date":"2021-07-05","arxiv_id":"2107.02239","n_code_links":2,"syntology":null},{"paper":"/paper/what-helps-transformers-recognize","slug":"what-helps-transformers-recognize","title":"What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition","date":"2021-07-05","arxiv_id":"2107.02294","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-makes-for-hierarchical-vision","title":"What Makes for Hierarchical Vision Transformer?","date":"2021-07-05","arxiv_id":"2107.02174","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-neural-coreference-resolution-1","title":"End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline","date":"2021-07-04","arxiv_id":"2107.01700","n_code_links":0,"syntology":null},{"paper":"/paper/improved-representation-learning-for-session","slug":"improved-representation-learning-for-session","title":"Introducing Self-Attention to Target Attentive Graph Neural Networks","date":"2021-07-04","arxiv_id":"2107.01516","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-transformers-jump-around-right-in-natural","title":"Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN","date":"2021-07-03","arxiv_id":"2107.01366","n_code_links":0,"syntology":null},{"paper":"/paper/supervised-off-policy-ranking","slug":"supervised-off-policy-ranking","title":"Supervised Off-Policy Ranking","date":"2021-07-03","arxiv_id":"2107.01360","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["SOPR-T/SOPR-T"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"case-relation-transformer-a-crossmodal","title":"Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions","date":"2021-07-02","arxiv_id":"2107.00789","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-view-geo-localization-with-evolving","title":"Cross-view Geo-localization with Evolving Transformer","date":"2021-07-02","arxiv_id":"2107.00842","n_code_links":0,"syntology":null},{"paper":"/paper/online-metro-origin-destination-prediction","slug":"online-metro-origin-destination-prediction","title":"Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation","date":"2021-07-02","arxiv_id":"2107.00946","n_code_links":1,"syntology":null},{"paper":"/paper/r2d2-recursive-transformer-based-on","slug":"r2d2-recursive-transformer-based-on","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","date":"2021-07-02","arxiv_id":"2107.00967","n_code_links":1,"syntology":null},{"paper":"/paper/relaxed-attention-a-simple-method-to-boost","slug":"relaxed-attention-a-simple-method-to-boost","title":"Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","date":"2021-07-02","arxiv_id":"2107.01275","n_code_links":1,"syntology":null},{"paper":null,"slug":"scarecrow-a-framework-for-scrutinizing","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","date":"2021-07-02","arxiv_id":"2107.01294","n_code_links":0,"syntology":null},{"paper":"/paper/solving-machine-learning-problems","slug":"solving-machine-learning-problems","title":"Solving Machine Learning Problems","date":"2021-07-02","arxiv_id":"2107.01238","n_code_links":1,"syntology":null},{"paper":null,"slug":"target-dependent-uniter-a-transformer-based","title":"Target-dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots","date":"2021-07-02","arxiv_id":"2107.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-f-a-transformer-network-with","title":"Transformer-F: A Transformer network with effective methods for learning universal sentence representation","date":"2021-07-02","arxiv_id":"2107.00653","n_code_links":0,"syntology":null}],"record_sha256":"48bae2c0e22eaa255bc2678d20a8be63bb393c791697aa10109f0e28735a82c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}