{"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/linear-layer/papers/198","list_of":"/method/linear-layer","method":"Linear Layer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":198,"pages_in_order":255,"rows_per_page":100,"rows":[19701,19800],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/197","next":"/method/linear-layer/papers/199","papers":[{"paper":"/paper/mait-integrating-spatial-locality-into-image","slug":"mait-integrating-spatial-locality-into-image","title":"MaiT: integrating spatial locality into image transformers with attention masks","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mapping-language-models-to-grounded","title":"Mapping Language Models to Grounded Conceptual Spaces","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mlp-based-architecture-with-variable-length","title":"MLP-based architecture with variable length input for automatic speech recognition","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-label-correlations-implicitly","title":"Modeling label correlations implicitly through latent label encodings for multi-label text classification","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"non-autoregressive-models-are-better","title":"Non-Autoregressive Models are Better Multilingual Translators","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-pre-trained-multi-agent-decision","title":"Offline Pre-trained Multi-Agent Decision Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-reinforcement-learning-for-large","title":"Offline Reinforcement Learning for Large Scale Language Action Spaces","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pretraining-for-language-conditioned","title":"Pretraining for Language Conditioned Imitation with Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/privacy-preserving-task-agnostic-vision","slug":"privacy-preserving-task-agnostic-vision","title":"Privacy-preserving Task-Agnostic Vision Transformer for Image Processing","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"rank4class-examining-multiclass","title":"Rank4Class: Examining Multiclass Classification through the Lens of Learning to Rank","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robot-intent-recognition-method-based-on","title":"Robot Intent Recognition Method Based on State Grid Business Office","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/salt-sharing-attention-between-linear-layer","slug":"salt-sharing-attention-between-linear-layer","title":"SALT : Sharing Attention between Linear layer and Transformer for tabular dataset","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"scala-speeding-up-fine-tuning-of-pre-trained","title":"ScaLA: Speeding-Up Fine-tuning of Pre-trained Transformer Networks via Efficient and Scalable Adversarial Perturbation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scale-efficiently-insights-from-pretraining","title":"Scale Efficiently: Insights from Pretraining and Finetuning Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-the-depth-of-vision-transformers-via","title":"Scaling the Depth of Vision Transformers via the Fourier Domain Analysis","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-offline-reinforcement","title":"Semi-supervised Offline Reinforcement Learning with Pre-trained Decision Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"seqpate-differentially-private-text","title":"SeqPATE: Differentially Private Text Generation via Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sit-simulation-transformer-for-particle-based","title":"SiT: Simulation Transformer for Particle-based Physics Simulation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spanning-tree-based-graph-generation-for","title":"Spanning Tree-based Graph Generation for Molecules","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-attention-with-learning-to-hash","title":"Sparse Attention with Learning to Hash","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-unbalanced-gan-training-with-in-time","title":"Sparse Unbalanced GAN Training with In-Time Over-Parameterization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"specialized-transformers-faster-smaller-and","title":"Specialized Transformers: Faster, Smaller and more Accurate NLP Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/subdimensional-expansion-using-attention","slug":"subdimensional-expansion-using-attention","title":"Subdimensional Expansion Using Attention-Based Learning For Multi-Agent Path Finding","date":"2021-09-29","arxiv_id":"2109.14695","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-action-localization-with-global","title":"Temporal Action Localization with Global Segmentation Mask Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"test-time-robustification-of-deep-models-via","title":"Test Time Robustification of Deep Models via Adaptation and Augmentation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"topic-aware-neural-language-model-domain","title":"Topic Aware Neural Language Model: Domain Adaptation of Unconditional Text Generation Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"training-sequence-labeling-models-using-prior","title":"Training sequence labeling models using prior knowledge","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transliteration-a-simple-technique-for","title":"Transliteration: A Simple Technique For Improving Multilingual Language Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transslowdown-efficiency-attacks-on-neural","title":"TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transtcn-an-attention-based-tcn-framework-for","title":"TransTCN: An Attention-based TCN Framework for Sequential Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tuformer-data-driven-design-of-expressive","title":"Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ufo-vit-high-performance-linear-vision","slug":"ufo-vit-high-performance-linear-vision","title":"UFO-ViT: High Performance Linear Vision Transformer without Softmax","date":"2021-09-29","arxiv_id":"2109.14382","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-role-of-self-attention-for","title":"Understanding the Role of Self Attention for Efficient Speech Recognition","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"video-forgery-detection-using-multiple-cues","title":"Video Forgery Detection Using Multiple Cues on Fusion of EfficientNet and Swin Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vut-versatile-ui-transformer-for-multimodal","title":"VUT: Versatile UI Transformer for Multimodal Multi-Task User Interface Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-vision-transformers-for-the","title":"Fine-tuning Vision Transformers for the Prediction of State Variables in Ising Models","date":"2021-09-28","arxiv_id":"2109.13925","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-different-text-preprocessing-techniques","title":"How Different Text-preprocessing Techniques Using The BERT Model Affect The Gender Profiling of Authors","date":"2021-09-28","arxiv_id":"2109.13890","n_code_links":0,"syntology":null},{"paper":null,"slug":"nana-hdr-a-non-attentive-non-autoregressive","title":"Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS","date":"2021-09-28","arxiv_id":"2109.13673","n_code_links":0,"syntology":null},{"paper":"/paper/raft-a-real-world-few-shot-text","slug":"raft-a-real-world-few-shot-text","title":"RAFT: A Real-World Few-Shot Text Classification Benchmark","date":"2021-09-28","arxiv_id":"2109.14076","n_code_links":1,"syntology":null},{"paper":"/paper/single-dataset-experts-for-multi-dataset","slug":"single-dataset-experts-for-multi-dataset","title":"Single-dataset Experts for Multi-dataset Question Answering","date":"2021-09-28","arxiv_id":"2109.13880","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":10,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/made"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-to-prioritize-natural-language","title":"What to Prioritize? Natural Language Processing for the Development of a Modern Bug Tracking Solution in Hardware Development","date":"2021-09-28","arxiv_id":"2109.13825","n_code_links":0,"syntology":null},{"paper":"/paper/effective-use-of-graph-convolution-network","slug":"effective-use-of-graph-convolution-network","title":"Effective Use of Graph Convolution Network and Contextual Sub-Tree forCommodity News Event Extraction","date":"2021-09-27","arxiv_id":"2109.12781","n_code_links":1,"syntology":null},{"paper":"/paper/fast-md-fast-multi-decoder-end-to-end-speech","slug":"fast-md-fast-multi-decoder-end-to-end-speech","title":"Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates","date":"2021-09-27","arxiv_id":"2109.12804","n_code_links":1,"syntology":null},{"paper":"/paper/improving-stack-overflow-question-title","slug":"improving-stack-overflow-question-title","title":"Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information","date":"2021-09-27","arxiv_id":"2109.13073","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrated-training-for-sequence-to-sequence","title":"Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer","date":"2021-09-27","arxiv_id":"2109.12950","n_code_links":0,"syntology":null},{"paper":"/paper/pass-an-imagenet-replacement-for-self","slug":"pass-an-imagenet-replacement-for-self","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","date":"2021-09-27","arxiv_id":"2109.13228","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":10,"n_instrument":1,"unverified":3,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["yukimasano/PASS"],"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/patterns-of-lexical-ambiguity-in","slug":"patterns-of-lexical-ambiguity-in","title":"Patterns of Lexical Ambiguity in Contextualised Language Models","date":"2021-09-27","arxiv_id":"2109.13032","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-spatial-transformers-for-few-shot","slug":"sparse-spatial-transformers-for-few-shot","title":"Sparse Spatial Transformers for Few-Shot Learning","date":"2021-09-27","arxiv_id":"2109.12932","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["chenhaoxing/ssformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/turingbench-a-benchmark-environment-for","slug":"turingbench-a-benchmark-environment-for","title":"TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation","date":"2021-09-27","arxiv_id":"2109.13296","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"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":null}},{"paper":"/paper/understanding-and-overcoming-the-challenges","slug":"understanding-and-overcoming-the-challenges","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","date":"2021-09-27","arxiv_id":"2109.12948","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qualcomm-ai-research/transformer-quantization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deminet-dependency-aware-multi-interest","title":"DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction","date":"2021-09-26","arxiv_id":"2109.12512","n_code_links":0,"syntology":null},{"paper":"/paper/improving-question-answering-performance","slug":"improving-question-answering-performance","title":"Improving Question Answering Performance Using Knowledge Distillation and Active Learning","date":"2021-09-26","arxiv_id":"2109.12662","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 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) · 1 unverified","official":{"repos":["mirbostani/QA-KD-AL"],"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/multi-transformer-a-new-neural-network-based","slug":"multi-transformer-a-new-neural-network-based","title":"Multi-Transformer: A New Neural Network-Based Architecture for Forecasting S&P Volatility","date":"2021-09-26","arxiv_id":"2109.12621","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-prunability-of-attention-heads-in","title":"On the Prunability of Attention Heads in Multilingual BERT","date":"2021-09-26","arxiv_id":"2109.12683","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-refinements-for-lexically","slug":"parallel-refinements-for-lexically","title":"Parallel Refinements for Lexically Constrained Text Generation with BART","date":"2021-09-26","arxiv_id":"2109.12487","n_code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-hashing-for-image","slug":"vision-transformer-hashing-for-image","title":"Vision Transformer Hashing for Image Retrieval","date":"2021-09-26","arxiv_id":"2109.12564","n_code_links":1,"syntology":null},{"paper":null,"slug":"vit-cane-visual-assistant-for-the-visually","title":"ViT Cane: Visual Assistant for the Visually Impaired","date":"2021-09-26","arxiv_id":"2109.13857","n_code_links":0,"syntology":null},{"paper":"/paper/bitr-unet-a-cnn-transformer-combined-network","slug":"bitr-unet-a-cnn-transformer-combined-network","title":"BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor Segmentation","date":"2021-09-25","arxiv_id":"2109.12271","n_code_links":1,"syntology":null},{"paper":null,"slug":"finetuning-transformer-models-to-build-asag","title":"Finetuning Transformer Models to Build ASAG System","date":"2021-09-25","arxiv_id":"2109.12300","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-selectively-learn-for-weakly","title":"Learning to Selectively Learn for Weakly-supervised Paraphrase Generation","date":"2021-09-25","arxiv_id":"2109.12457","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-multi-instance-learning-for","title":"Multi-Modal Multi-Instance Learning for Retinal Disease Recognition","date":"2021-09-25","arxiv_id":"2109.12307","n_code_links":0,"syntology":null},{"paper":null,"slug":"temgnet-deep-transformer-based-decoding-of","title":"TEMGNet: Deep Transformer-based Decoding of Upperlimb sEMG for Hand Gestures Recognition","date":"2021-09-25","arxiv_id":"2109.12379","n_code_links":0,"syntology":null},{"paper":null,"slug":"aes-are-both-overstable-and-oversensitive","title":"AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses","date":"2021-09-24","arxiv_id":"2109.11728","n_code_links":0,"syntology":null},{"paper":null,"slug":"dact-bert-differentiable-adaptive-computation","title":"DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference","date":"2021-09-24","arxiv_id":"2109.11745","n_code_links":0,"syntology":null},{"paper":null,"slug":"dense-contrastive-visual-linguistic","title":"Dense Contrastive Visual-Linguistic Pretraining","date":"2021-09-24","arxiv_id":"2109.11778","n_code_links":0,"syntology":null},{"paper":null,"slug":"identification-of-enzymatic-active-sites-with","title":"Identification of Enzymatic Active Sites with Unsupervised Language Modeling","date":"2021-09-24","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lacking-the-embedding-of-a-word-look-it-up","title":"Lacking the embedding of a word? Look it up into a traditional dictionary","date":"2021-09-24","arxiv_id":"2109.11763","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-pretrained-models-for-automatic","slug":"leveraging-pretrained-models-for-automatic","title":"Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations","date":"2021-09-24","arxiv_id":"2109.12174","n_code_links":1,"syntology":null},{"paper":null,"slug":"localizing-infinity-shaped-fishes-sketch","title":"Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild","date":"2021-09-24","arxiv_id":"2109.11874","n_code_links":0,"syntology":null},{"paper":"/paper/long-range-transformers-for-dynamic","slug":"long-range-transformers-for-dynamic","title":"Long-Range Transformers for Dynamic Spatiotemporal Forecasting","date":"2021-09-24","arxiv_id":"2109.12218","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["qdata/spacetimeformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"robustness-and-sensitivity-of-bert-models","title":"Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text","date":"2021-09-24","arxiv_id":"2109.11888","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-generalize-linearly","slug":"transformers-generalize-linearly","title":"Transformers Generalize Linearly","date":"2021-09-24","arxiv_id":"2109.12036","n_code_links":1,"syntology":null},{"paper":"/paper/breaking-bert-understanding-its","slug":"breaking-bert-understanding-its","title":"Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack","date":"2021-09-23","arxiv_id":"2109.11308","n_code_links":1,"syntology":null},{"paper":null,"slug":"incorporating-linguistic-knowledge-for","title":"Dependency Structure for News Document Summarization","date":"2021-09-23","arxiv_id":"2109.11199","n_code_links":0,"syntology":null},{"paper":null,"slug":"oh-former-omni-relational-high-order","title":"OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification","date":"2021-09-23","arxiv_id":"2109.11159","n_code_links":0,"syntology":null},{"paper":"/paper/putting-words-in-bert-s-mouth-navigating","slug":"putting-words-in-bert-s-mouth-navigating","title":"Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords","date":"2021-09-23","arxiv_id":"2109.11491","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-volctrans-glat-system-non-autoregressive","title":"The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21","date":"2021-09-23","arxiv_id":"2109.11247","n_code_links":0,"syntology":null},{"paper":null,"slug":"alzheimers-dementia-detection-using-acoustic","title":"Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT","date":"2021-09-22","arxiv_id":"2109.11010","n_code_links":0,"syntology":null},{"paper":"/paper/controlled-evaluation-of-grammatical","slug":"controlled-evaluation-of-grammatical","title":"Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models","date":"2021-09-22","arxiv_id":"2109.11058","n_code_links":1,"syntology":null},{"paper":null,"slug":"dialoguebert-a-self-supervised-learning-based","title":"DialogueBERT: A Self-Supervised Learning based Dialogue Pre-training Encoder","date":"2021-09-22","arxiv_id":"2109.10480","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-multimodal-transformer-to","slug":"hierarchical-multimodal-transformer-to","title":"Hierarchical Multimodal Transformer to Summarize Videos","date":"2021-09-22","arxiv_id":"2109.10559","n_code_links":0,"syntology":null},{"paper":"/paper/improving-360-monocular-depth-estimation-via","slug":"improving-360-monocular-depth-estimation-via","title":"Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning","date":"2021-09-22","arxiv_id":"2109.10563","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":"/paper/kd-vlp-improving-end-to-end-vision-and","slug":"kd-vlp-improving-end-to-end-vision-and","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","date":"2021-09-22","arxiv_id":"2109.10504","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-models-as-recommender-systems","title":"Language Models as Recommender Systems: Evaluations and Limitations","date":"2021-09-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-efficiency-effectiveness-trade","title":"Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection","date":"2021-09-22","arxiv_id":"2109.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"recursively-summarizing-books-with-human","title":"Recursively Summarizing Books with Human Feedback","date":"2021-09-22","arxiv_id":"2109.10862","n_code_links":0,"syntology":null},{"paper":"/paper/scale-efficiently-insights-from-pre-training","slug":"scale-efficiently-insights-from-pre-training","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","date":"2021-09-22","arxiv_id":"2109.10686","n_code_links":3,"syntology":{"ran":12,"of":12,"n_ran_checked":12,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"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":"t6d-direct-transformers-for-multi-object-6d","title":"T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression","date":"2021-09-22","arxiv_id":"2109.10948","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-niutrans-machine-translation-systems-for-1","title":"The NiuTrans Machine Translation Systems for WMT21","date":"2021-09-22","arxiv_id":"2109.10485","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-contextualized-document","slug":"unsupervised-contextualized-document","title":"Unsupervised Contextualized Document Representation","date":"2021-09-22","arxiv_id":"2109.10509","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-review-on-summarizing","title":"A Comprehensive Review on Summarizing Financial News Using Deep Learning","date":"2021-09-21","arxiv_id":"2109.10118","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertweetfr-domain-adaptation-of-pre-trained","title":"BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets","date":"2021-09-21","arxiv_id":"2109.10234","n_code_links":0,"syntology":null},{"paper":"/paper/ds-net-dynamic-weight-slicing-for-efficient","slug":"ds-net-dynamic-weight-slicing-for-efficient","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","date":"2021-09-21","arxiv_id":"2109.10060","n_code_links":1,"syntology":null},{"paper":null,"slug":"invbert-text-reconstruction-from","title":"InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline","date":"2021-09-21","arxiv_id":"2109.10104","n_code_links":0,"syntology":null},{"paper":"/paper/lotr-face-landmark-localization-using","slug":"lotr-face-landmark-localization-using","title":"LOTR: Face Landmark Localization Using Localization Transformer","date":"2021-09-21","arxiv_id":"2109.10057","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-learning-with-sentiment-emotion","title":"Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Language","date":"2021-09-21","arxiv_id":"2109.10255","n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-for-short-text","title":"Representation Learning for Short Text Clustering","date":"2021-09-21","arxiv_id":"2109.09894","n_code_links":0,"syntology":null},{"paper":"/paper/trocr-transformer-based-optical-character","slug":"trocr-transformer-based-optical-character","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","date":"2021-09-21","arxiv_id":"2109.10282","n_code_links":8,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/unilm"],"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/a-plug-and-play-method-for-controlled-text","slug":"a-plug-and-play-method-for-controlled-text","title":"A Plug-and-Play Method for Controlled Text Generation","date":"2021-09-20","arxiv_id":"2109.09707","n_code_links":1,"syntology":null},{"paper":"/paper/bartpho-pre-trained-sequence-to-sequence","slug":"bartpho-pre-trained-sequence-to-sequence","title":"BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese","date":"2021-09-20","arxiv_id":"2109.09701","n_code_links":3,"syntology":null}],"record_sha256":"7bf7c6c7098d22358e5661b864bb362b2200add5de5cbb46890f9e04c04bbf2a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}