{"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/attention/papers/242","list_of":"/method/attention","method":"Attention","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":242,"pages_in_order":316,"rows_per_page":100,"rows":[24101,24200],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/241","next":"/method/attention/papers/243","papers":[{"paper":"/paper/himode-a-hybrid-monocular-omnidirectional","slug":"himode-a-hybrid-monocular-omnidirectional","title":"HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model","date":"2022-04-11","arxiv_id":"2204.05007","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-streaming-end-to-end-speech","slug":"large-scale-streaming-end-to-end-speech","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","date":"2022-04-11","arxiv_id":"2204.05352","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":null}},{"paper":"/paper/permutation-invariant-relational-network-for","slug":"permutation-invariant-relational-network-for","title":"Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation","date":"2022-04-11","arxiv_id":"2204.04913","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-vision-transformers-for-joint","slug":"self-supervised-vision-transformers-for-joint","title":"Self-supervised Vision Transformers for Joint SAR-optical Representation Learning","date":"2022-04-11","arxiv_id":"2204.05381","n_code_links":2,"syntology":null},{"paper":null,"slug":"sumd-super-u-shaped-matrix-decomposition","title":"SUMD: Super U-shaped Matrix Decomposition Convolutional neural network for Image denoising","date":"2022-04-11","arxiv_id":"2204.04861","n_code_links":0,"syntology":null},{"paper":null,"slug":"team-ufal-at-cmcl-2022-shared-task-figuring","title":"Team ÚFAL at CMCL 2022 Shared Task: Figuring out the correct recipe for predicting Eye-Tracking features using Pretrained Language Models","date":"2022-04-11","arxiv_id":"2204.04998","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenwise-contrastive-pretraining-for-finer","title":"Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems","date":"2022-04-11","arxiv_id":"2204.05188","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-generalizeable-semantic-product","title":"Towards Generalizable Semantic Product Search by Text Similarity Pre-training on Search Click Logs","date":"2022-04-11","arxiv_id":"2204.05231","n_code_links":0,"syntology":null},{"paper":"/paper/uniform-complexity-for-text-generation","slug":"uniform-complexity-for-text-generation","title":"Uniform Complexity for Text Generation","date":"2022-04-11","arxiv_id":"2204.05185","n_code_links":1,"syntology":null},{"paper":"/paper/confidence-estimation-transformer-for-long","slug":"confidence-estimation-transformer-for-long","title":"Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching","date":"2022-04-10","arxiv_id":"2204.04612","n_code_links":1,"syntology":null},{"paper":"/paper/dilemma-self-supervised-shape-and-texture","slug":"dilemma-self-supervised-shape-and-texture","title":"Representation Learning by Detecting Incorrect Location Embeddings","date":"2022-04-10","arxiv_id":"2204.04788","n_code_links":1,"syntology":null},{"paper":null,"slug":"fake-news-detection-using-parallel-bert-deep","title":"Fake news detection using parallel BERT deep neural networks","date":"2022-04-10","arxiv_id":"2204.04793","n_code_links":0,"syntology":null},{"paper":"/paper/fashionformer-a-simple-effective-and-unified","slug":"fashionformer-a-simple-effective-and-unified","title":"Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition","date":"2022-04-10","arxiv_id":"2204.04654","n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-cross-lingual-transfer-for-coarse","slug":"few-shot-cross-lingual-transfer-for-coarse","title":"Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts","date":"2022-04-10","arxiv_id":"2204.04775","n_code_links":1,"syntology":null},{"paper":"/paper/panoptic-partformer-learning-a-unified-model","slug":"panoptic-partformer-learning-a-unified-model","title":"Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation","date":"2022-04-10","arxiv_id":"2204.04655","n_code_links":1,"syntology":null},{"paper":null,"slug":"pushing-on-personality-detection-from-verbal","title":"Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features","date":"2022-04-10","arxiv_id":"2204.04629","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-audio-and-text-pre-training","slug":"self-supervised-audio-and-text-pre-training","title":"Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data","date":"2022-04-10","arxiv_id":"2204.04645","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-extraction-of-pathologies-from-c","title":"Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learning","date":"2022-04-09","arxiv_id":"2204.04544","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundationlayernorm-scaling-bert-and-gpt-to","title":"FoundationLayerNorm: Scaling BERT and GPT to 1,000 Layers","date":"2022-04-09","arxiv_id":"2204.04477","n_code_links":0,"syntology":null},{"paper":"/paper/modeling-multi-granularity-hierarchical-1","slug":"modeling-multi-granularity-hierarchical-1","title":"Modeling Multi-Granularity Hierarchical Features for Relation Extraction","date":"2022-04-09","arxiv_id":"2204.04437","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xnliang98/sms"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/bag-of-words-vs-sequence-vs-graph-vs","slug":"bag-of-words-vs-sequence-vs-graph-vs","title":"Are We Really Making Much Progress in Text Classification? A Comparative Review","date":"2022-04-08","arxiv_id":"2204.03954","n_code_links":1,"syntology":null},{"paper":"/paper/biobart-pretraining-and-evaluation-of-a","slug":"biobart-pretraining-and-evaluation-of-a","title":"BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model","date":"2022-04-08","arxiv_id":"2204.03905","n_code_links":1,"syntology":null},{"paper":"/paper/contextual-representation-learning-beyond-1","slug":"contextual-representation-learning-beyond-1","title":"Contextual Representation Learning beyond Masked Language Modeling","date":"2022-04-08","arxiv_id":"2204.04163","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-robustness-on-imagenet-transfer-to","title":"Does Robustness on ImageNet Transfer to Downstream Tasks?","date":"2022-04-08","arxiv_id":"2204.03934","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-tracking-of-team-sport-players-with","title":"Efficient tracking of team sport players with few game-specific annotations","date":"2022-04-08","arxiv_id":"2204.04049","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-incomplete-utterance-restoration-by","slug":"enhance-incomplete-utterance-restoration-by","title":"Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation","date":"2022-04-08","arxiv_id":"2204.03958","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-transformer-s-potential-on","title":"Exploring Transformer's potential on automatic piano transcription","date":"2022-04-08","arxiv_id":"2204.03898","n_code_links":0,"syntology":null},{"paper":"/paper/infusing-knowledge-from-wikipedia-to-enhance","slug":"infusing-knowledge-from-wikipedia-to-enhance","title":"Infusing Knowledge from Wikipedia to Enhance Stance Detection","date":"2022-04-08","arxiv_id":"2204.03839","n_code_links":2,"syntology":null},{"paper":"/paper/learning-trajectory-aware-transformer-for","slug":"learning-trajectory-aware-transformer-for","title":"Learning Trajectory-Aware Transformer for Video Super-Resolution","date":"2022-04-08","arxiv_id":"2204.04216","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["researchmm/TTVSR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mmtafrica-multilingual-machine-translation-1","slug":"mmtafrica-multilingual-machine-translation-1","title":"MMTAfrica: Multilingual Machine Translation for African Languages","date":"2022-04-08","arxiv_id":"2204.04306","n_code_links":1,"syntology":null},{"paper":"/paper/points-to-patches-enabling-the-use-of-self","slug":"points-to-patches-enabling-the-use-of-self","title":"Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition","date":"2022-04-08","arxiv_id":"2204.03957","n_code_links":1,"syntology":null},{"paper":null,"slug":"supernet-in-neural-architecture-search-a","title":"A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Search","date":"2022-04-08","arxiv_id":"2204.03916","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-large-scale-discourse-1","title":"Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models","date":"2022-04-08","arxiv_id":"2204.04289","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-self-supervised-learning","title":"Transformer-Based Self-Supervised Learning for Emotion Recognition","date":"2022-04-08","arxiv_id":"2204.05103","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformers-for-single-image-dehazing","slug":"vision-transformers-for-single-image-dehazing","title":"Vision Transformers for Single Image Dehazing","date":"2022-04-08","arxiv_id":"2204.03883","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":3,"n_instrument":2,"unverified":5,"pointer_only":3,"phrase":"5 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; 2 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"accelerating-attention-through-gradient-based","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","date":"2022-04-07","arxiv_id":"2204.03227","n_code_links":0,"syntology":null},{"paper":null,"slug":"autoencoding-language-model-based-ensemble","title":"Autoencoding Language Model Based Ensemble Learning for Commonsense Validation and Explanation","date":"2022-04-07","arxiv_id":"2204.03324","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertuit-understanding-spanish-language-in","title":"BERTuit: Understanding Spanish language in Twitter through a native transformer","date":"2022-04-07","arxiv_id":"2204.03465","n_code_links":0,"syntology":null},{"paper":null,"slug":"compositional-generalization-and","title":"Compositional Generalization and Decomposition in Neural Program Synthesis","date":"2022-04-07","arxiv_id":"2204.03758","n_code_links":0,"syntology":null},{"paper":"/paper/davit-dual-attention-vision-transformers","slug":"davit-dual-attention-vision-transformers","title":"DaViT: Dual Attention Vision Transformers","date":"2022-04-07","arxiv_id":"2204.03645","n_code_links":4,"syntology":{"ran":8,"of":15,"n_ran_checked":6,"n_instrument":2,"unverified":7,"pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["dingmyu/davit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-semantic-code-search-with","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","date":"2022-04-07","arxiv_id":"2204.03293","n_code_links":0,"syntology":null},{"paper":"/paper/event-transformer-a-sparse-aware-solution-for","slug":"event-transformer-a-sparse-aware-solution-for","title":"Event Transformer. A sparse-aware solution for efficient event data processing","date":"2022-04-07","arxiv_id":"2204.03355","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-dose-ct-denoising-via-sinogram-inner","title":"Low-Dose CT Denoising via Sinogram Inner-Structure Transformer","date":"2022-04-07","arxiv_id":"2204.03163","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-distributed-learning-using-vision","title":"Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutation","date":"2022-04-07","arxiv_id":"2204.03500","n_code_links":0,"syntology":null},{"paper":"/paper/palbert-teaching-albert-to-ponder-1","slug":"palbert-teaching-albert-to-ponder-1","title":"PALBERT: Teaching ALBERT to Ponder","date":"2022-04-07","arxiv_id":"2204.03276","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["tinkoff-ai/palbert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pretraining-text-encoders-with-adversarial-1","slug":"pretraining-text-encoders-with-adversarial-1","title":"Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators","date":"2022-04-07","arxiv_id":"2204.03243","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["microsoft/amos"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"t4pdm-a-deep-neural-network-based-on-the","title":"T4PdM: a Deep Neural Network based on the Transformer Architecture for Fault Diagnosis of Rotating Machinery","date":"2022-04-07","arxiv_id":"2204.03725","n_code_links":0,"syntology":null},{"paper":"/paper/testing-the-limits-of-natural-language-models","slug":"testing-the-limits-of-natural-language-models","title":"Testing the limits of natural language models for predicting human language judgments","date":"2022-04-07","arxiv_id":"2204.03592","n_code_links":1,"syntology":null},{"paper":"/paper/unified-contrastive-learning-in-image-text","slug":"unified-contrastive-learning-in-image-text","title":"Unified Contrastive Learning in Image-Text-Label Space","date":"2022-04-07","arxiv_id":"2204.03610","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/unicl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/zero-shot-category-level-object-pose","slug":"zero-shot-category-level-object-pose","title":"Zero-Shot Category-Level Object Pose Estimation","date":"2022-04-07","arxiv_id":"2204.03635","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-study-of-remote-sensing","slug":"an-empirical-study-of-remote-sensing","title":"An Empirical Study of Remote Sensing Pretraining","date":"2022-04-06","arxiv_id":"2204.02825","n_code_links":2,"syntology":null},{"paper":"/paper/byt5-model-for-massively-multilingual","slug":"byt5-model-for-massively-multilingual","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","date":"2022-04-06","arxiv_id":"2204.03067","n_code_links":1,"syntology":null},{"paper":null,"slug":"ccat-net-a-novel-transformer-based-semi","title":"CCAT-NET: A Novel Transformer Based Semi-supervised Framework for Covid-19 Lung Lesion Segmentation","date":"2022-04-06","arxiv_id":"2204.02839","n_code_links":0,"syntology":null},{"paper":"/paper/dagam-data-augmentation-with-generation-and","slug":"dagam-data-augmentation-with-generation-and","title":"DAGAM: Data Augmentation with Generation And Modification","date":"2022-04-06","arxiv_id":"2204.02633","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-specific-fine-tuning-of-denoising","title":"Domain Specific Fine-tuning of Denoising Sequence-to-Sequence Models for Natural Language Summarization","date":"2022-04-06","arxiv_id":"2204.09716","n_code_links":0,"syntology":null},{"paper":null,"slug":"drsphelps-at-semeval-2022-task-2-learning","title":"drsphelps at SemEval-2022 Task 2: Learning idiom representations using BERTRAM","date":"2022-04-06","arxiv_id":"2204.02821","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-infused-decoding-1","slug":"knowledge-infused-decoding-1","title":"Knowledge Infused Decoding","date":"2022-04-06","arxiv_id":"2204.03084","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/kid"],"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":["official"]}}},{"paper":"/paper/mixformer-mixing-features-across-windows-and","slug":"mixformer-mixing-features-across-windows-and","title":"MixFormer: Mixing Features across Windows and Dimensions","date":"2022-04-06","arxiv_id":"2204.02557","n_code_links":3,"syntology":{"ran":10,"of":14,"n_ran_checked":10,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["PaddlePaddle/PaddleClas"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"paying-more-attention-to-self-attention","title":"Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding","date":"2022-04-06","arxiv_id":"2204.02922","n_code_links":0,"syntology":null},{"paper":"/paper/smdt-cross-view-geo-localization-with-image","slug":"smdt-cross-view-geo-localization-with-image","title":"SMDT: Cross-View Geo-Localization with Image Alignment and Transformer","date":"2022-04-06","arxiv_id":null,"n_code_links":4,"syntology":null},{"paper":"/paper/unleashing-vanilla-vision-transformer-with","slug":"unleashing-vanilla-vision-transformer-with","title":"Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection","date":"2022-04-06","arxiv_id":"2204.02964","n_code_links":2,"syntology":null},{"paper":null,"slug":"using-synthetic-data-for-conversational","title":"Using Synthetic Data for Conversational Response Generation in Low-resource Settings","date":"2022-04-06","arxiv_id":"2204.02653","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-hospitalisation","title":"Abstractive summarization of hospitalisation histories with transformer networks","date":"2022-04-05","arxiv_id":"2204.02208","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploratory-study-on-code-attention-in","title":"An Exploratory Study on Code Attention in BERT","date":"2022-04-05","arxiv_id":"2204.10200","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-for-intent-classification-1","slug":"data-augmentation-for-intent-classification-1","title":"Data Augmentation for Intent Classification with Off-the-shelf Large Language Models","date":"2022-04-05","arxiv_id":"2204.01959","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["elementai/data-augmentation-with-llms"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"detector-free-weakly-supervised-group","title":"Detector-Free Weakly Supervised Group Activity Recognition","date":"2022-04-05","arxiv_id":"2204.02139","n_code_links":0,"syntology":null},{"paper":"/paper/fact-checking-with-insufficient-evidence","slug":"fact-checking-with-insufficient-evidence","title":"Fact Checking with Insufficient Evidence","date":"2022-04-05","arxiv_id":"2204.02007","n_code_links":1,"syntology":null},{"paper":"/paper/gp-bart-a-novel-bayesian-additive-regression","slug":"gp-bart-a-novel-bayesian-additive-regression","title":"GP-BART: a novel Bayesian additive regression trees approach using Gaussian processes","date":"2022-04-05","arxiv_id":"2204.02112","n_code_links":1,"syntology":null},{"paper":"/paper/how-different-are-pre-trained-transformers","slug":"how-different-are-pre-trained-transformers","title":"How Different are Pre-trained Transformers for Text Ranking?","date":"2022-04-05","arxiv_id":"2204.07233","n_code_links":1,"syntology":null},{"paper":"/paper/multi-view-transformer-for-3d-visual","slug":"multi-view-transformer-for-3d-visual","title":"Multi-View Transformer for 3D Visual Grounding","date":"2022-04-05","arxiv_id":"2204.02174","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sega-hsj/mvt-3dvg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/multilinguals-at-semeval-2022-task-11","slug":"multilinguals-at-semeval-2022-task-11","title":"Multilinguals at SemEval-2022 Task 11: Transformer Based Architecture for Complex NER","date":"2022-04-05","arxiv_id":"2204.02173","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-effectiveness-of-pretrained-models-for","title":"On the Effectiveness of Pretrained Models for API Learning","date":"2022-04-05","arxiv_id":"2204.03498","n_code_links":0,"syntology":null},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","n_code_links":7,"syntology":{"ran":32,"of":37,"n_ran_checked":24,"n_instrument":8,"unverified":5,"pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":"/paper/parameter-efficient-neural-reranking-for","slug":"parameter-efficient-neural-reranking-for","title":"Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval","date":"2022-04-05","arxiv_id":"2204.02292","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-transformer-equipped-with-neural","title":"Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task","date":"2022-04-05","arxiv_id":"2204.02181","n_code_links":0,"syntology":null},{"paper":"/paper/batchformerv2-exploring-sample-relationships","slug":"batchformerv2-exploring-sample-relationships","title":"BatchFormerV2: Exploring Sample Relationships for Dense Representation Learning","date":"2022-04-04","arxiv_id":"2204.01254","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-focus-aware-positional-queries-for","slug":"dynamic-focus-aware-positional-queries-for","title":"Dynamic Focus-aware Positional Queries for Semantic Segmentation","date":"2022-04-04","arxiv_id":"2204.01244","n_code_links":2,"syntology":null},{"paper":null,"slug":"hit-dvae-human-motion-generation-via","title":"HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE","date":"2022-04-04","arxiv_id":"2204.01565","n_code_links":0,"syntology":null},{"paper":"/paper/joint-hand-motion-and-interaction-hotspots","slug":"joint-hand-motion-and-interaction-hotspots","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","date":"2022-04-04","arxiv_id":"2204.01696","n_code_links":1,"syntology":{"ran":9,"of":14,"n_ran_checked":6,"n_instrument":3,"unverified":5,"pointer_only":1,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["stevenlsw/hoi-forecast"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/long-movie-clip-classification-with-state","slug":"long-movie-clip-classification-with-state","title":"Long Movie Clip Classification with State-Space Video Models","date":"2022-04-04","arxiv_id":"2204.01692","n_code_links":1,"syntology":{"ran":11,"of":18,"n_ran_checked":3,"n_instrument":8,"unverified":7,"pointer_only":2,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","official":{"repos":["md-mohaiminul/ViS4mer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/tallformer-temporal-action-localization-with","slug":"tallformer-temporal-action-localization-with","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","date":"2022-04-04","arxiv_id":"2204.01680","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["klauscc/tallformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-sequence-to-sequence-approach-for-document","slug":"a-sequence-to-sequence-approach-for-document","title":"A sequence-to-sequence approach for document-level relation extraction","date":"2022-04-03","arxiv_id":"2204.01098","n_code_links":2,"syntology":null},{"paper":"/paper/binsformer-revisiting-adaptive-bins-for","slug":"binsformer-revisiting-adaptive-bins-for","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","date":"2022-04-03","arxiv_id":"2204.00987","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["zhyever/monocular-depth-estimation-toolbox"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-vision-transformers-by-revisiting","slug":"improving-vision-transformers-by-revisiting","title":"Improving Vision Transformers by Revisiting High-frequency Components","date":"2022-04-03","arxiv_id":"2204.00993","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":9,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jiawangbai/HAT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/pos-bert-point-cloud-one-stage-bert-pre","slug":"pos-bert-point-cloud-one-stage-bert-pre","title":"POS-BERT: Point Cloud One-Stage BERT Pre-Training","date":"2022-04-03","arxiv_id":"2204.00989","n_code_links":1,"syntology":null},{"paper":"/paper/bert-assisted-semantic-annotation-correction","slug":"bert-assisted-semantic-annotation-correction","title":"BERT-Assisted Semantic Annotation Correction for Emotion-Related Questions","date":"2022-04-02","arxiv_id":"2204.00916","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-comparison-of-sentence-embeddings","title":"Efficient comparison of sentence embeddings","date":"2022-04-02","arxiv_id":"2204.00820","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploiting-local-and-global-features-in","title":"Exploiting Local and Global Features in Transformer-based Extreme Multi-label Text Classification","date":"2022-04-02","arxiv_id":"2204.00933","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-how-bert-performs-entity-matching","slug":"analyzing-how-bert-performs-entity-matching","title":"Analyzing how BERT performs entity matching","date":"2022-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"cat-det-contrastively-augmented-transformer","title":"CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection","date":"2022-04-01","arxiv_id":"2204.00325","n_code_links":0,"syntology":null},{"paper":"/paper/characterbert-and-self-teaching-for-improving","slug":"characterbert-and-self-teaching-for-improving","title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos","date":"2022-04-01","arxiv_id":"2204.00716","n_code_links":1,"syntology":null},{"paper":"/paper/cipherdaug-ciphertext-based-data-augmentation","slug":"cipherdaug-ciphertext-based-data-augmentation","title":"CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation","date":"2022-04-01","arxiv_id":"2204.00665","n_code_links":1,"syntology":null},{"paper":null,"slug":"cyberbullying-detection-across-social-media","title":"Cyberbullying detection across social media platforms via platform-aware adversarial encoding","date":"2022-04-01","arxiv_id":"2204.00334","n_code_links":0,"syntology":null},{"paper":"/paper/dfnet-enhance-aboslute-pose-regression-with","slug":"dfnet-enhance-aboslute-pose-regression-with","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","date":"2022-04-01","arxiv_id":"2204.00559","n_code_links":1,"syntology":{"ran":15,"of":17,"n_ran_checked":13,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["activevisionlab/dfnet"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"effect-and-analysis-of-large-scale-language","title":"Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems","date":"2022-04-01","arxiv_id":"2204.00212","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-learnable-diversity-aware-news","title":"End-to-end Learnable Diversity-aware News Recommendation","date":"2022-04-01","arxiv_id":"2204.00539","n_code_links":0,"syntology":null},{"paper":"/paper/feature-structure-distillation-for-bert-1","slug":"feature-structure-distillation-for-bert-1","title":"Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring","date":"2022-04-01","arxiv_id":"2204.08922","n_code_links":1,"syntology":null},{"paper":"/paper/monarch-expressive-structured-matrices-for","slug":"monarch-expressive-structured-matrices-for","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","date":"2022-04-01","arxiv_id":"2204.00595","n_code_links":2,"syntology":{"ran":15,"of":15,"n_ran_checked":14,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hazyresearch/monarch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"syntax-informed-question-answering-with","title":"Syntax-informed Question Answering with Heterogeneous Graph Transformer","date":"2022-04-01","arxiv_id":"2204.09655","n_code_links":0,"syntology":null},{"paper":"/paper/template-aware-transformer-for-person","slug":"template-aware-transformer-for-person","title":"Template-Aware Transformer for Person Reidentification","date":"2022-04-01","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"185178b3e60f38710716004cf6e2634a573e3f41f4729f535b9e76861f97b844","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}