{"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/178","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":178,"pages_in_order":255,"rows_per_page":100,"rows":[17701,17800],"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/177","next":"/method/linear-layer/papers/179","papers":[{"paper":"/paper/image-captioning-in-the-transformer-age","slug":"image-captioning-in-the-transformer-age","title":"Image Captioning In the Transformer Age","date":"2022-04-15","arxiv_id":"2204.07374","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-pre-trained-language-models-with","title":"Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition","date":"2022-04-15","arxiv_id":"2204.07464","n_code_links":0,"syntology":null},{"paper":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixture-of-experts-for-biomedical-question","title":"Mixture of Experts for Biomedical Question Answering","date":"2022-04-15","arxiv_id":"2204.07469","n_code_links":0,"syntology":null},{"paper":null,"slug":"ml-ltu-at-semeval-2022-task-4-t5-towards","title":"ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language","date":"2022-04-15","arxiv_id":"2204.07432","n_code_links":0,"syntology":null},{"paper":"/paper/mvster-epipolar-transformer-for-efficient","slug":"mvster-epipolar-transformer-for-efficient","title":"MVSTER: Epipolar Transformer for Efficient Multi-View Stereo","date":"2022-04-15","arxiv_id":"2204.07346","n_code_links":1,"syntology":{"ran":10,"of":17,"n_ran_checked":5,"n_instrument":5,"unverified":7,"pointer_only":0,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["jeffwang987/mvster"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-role-of-pre-trained-language-models-in","slug":"on-the-role-of-pre-trained-language-models-in","title":"On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART","date":"2022-04-15","arxiv_id":"2204.07367","n_code_links":1,"syntology":null},{"paper":"/paper/polling-latent-opinions-a-method-for-1","slug":"polling-latent-opinions-a-method-for-1","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-04-15","arxiv_id":"2204.07483","n_code_links":1,"syntology":null},{"paper":"/paper/pushing-the-limits-of-simple-pipelines-for","slug":"pushing-the-limits-of-simple-pipelines-for","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","date":"2022-04-15","arxiv_id":"2204.07305","n_code_links":1,"syntology":{"ran":14,"of":19,"n_ran_checked":8,"n_instrument":6,"unverified":5,"pointer_only":4,"phrase":"14 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; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hushell/pmf_cvpr22"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"resource-aware-distributed-submodular","title":"Resource-Aware Distributed Submodular Maximization: A Paradigm for Multi-Robot Decision-Making","date":"2022-04-15","arxiv_id":"2204.07520","n_code_links":0,"syntology":null},{"paper":"/paper/rest-v2-simpler-faster-and-stronger","slug":"rest-v2-simpler-faster-and-stronger","title":"ResT V2: Simpler, Faster and Stronger","date":"2022-04-15","arxiv_id":"2204.07366","n_code_links":2,"syntology":null},{"paper":"/paper/text-revision-by-on-the-fly-representation","slug":"text-revision-by-on-the-fly-representation","title":"Text Revision by On-the-Fly Representation Optimization","date":"2022-04-15","arxiv_id":"2204.07359","n_code_links":1,"syntology":null},{"paper":"/paper/unconditional-image-text-pair-generation-with","slug":"unconditional-image-text-pair-generation-with","title":"Unconditional Image-Text Pair Generation with Multimodal Cross Quantizer","date":"2022-04-15","arxiv_id":"2204.07537","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-shuffle-mixer-an-efficient-context-aware","title":"3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume","date":"2022-04-14","arxiv_id":"2204.06779","n_code_links":0,"syntology":null},{"paper":"/paper/activation-regression-for-continuous-domain","slug":"activation-regression-for-continuous-domain","title":"Activation Regression for Continuous Domain Generalization with Applications to Crop Classification","date":"2022-04-14","arxiv_id":"2204.07030","n_code_links":1,"syntology":null},{"paper":null,"slug":"brazilian-court-documents-clustered-by","title":"Analysing similarities between legal court documents using natural language processing approaches based on Transformers","date":"2022-04-14","arxiv_id":"2204.07182","n_code_links":0,"syntology":null},{"paper":"/paper/calbert-code-mixed-adaptive-language-1","slug":"calbert-code-mixed-adaptive-language-1","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2022-04-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/causal-transformer-for-estimating","slug":"causal-transformer-for-estimating","title":"Causal Transformer for Estimating Counterfactual Outcomes","date":"2022-04-14","arxiv_id":"2204.07258","n_code_links":1,"syntology":null},{"paper":null,"slug":"challenges-for-open-domain-targeted-sentiment-1","title":"Challenges for Open-domain Targeted Sentiment Analysis","date":"2022-04-14","arxiv_id":"2204.06893","n_code_links":0,"syntology":null},{"paper":"/paper/deit-iii-revenge-of-the-vit","slug":"deit-iii-revenge-of-the-vit","title":"DeiT III: Revenge of the ViT","date":"2022-04-14","arxiv_id":"2204.07118","n_code_links":12,"syntology":null},{"paper":null,"slug":"does-bert-really-agree-fine-grained-analysis-1","title":"Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task","date":"2022-04-14","arxiv_id":"2204.06889","n_code_links":0,"syntology":null},{"paper":"/paper/generative-power-of-a-protein-language-model","slug":"generative-power-of-a-protein-language-model","title":"Generative power of a protein language model trained on multiple sequence alignments","date":"2022-04-14","arxiv_id":"2204.07110","n_code_links":1,"syntology":null},{"paper":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","slug":"gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","date":"2022-04-14","arxiv_id":"2204.06745","n_code_links":11,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["eleutherai/gpt-neox"],"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":"hierarchical-embedded-bayesian-additive","title":"Hierarchical Embedded Bayesian Additive Regression Trees","date":"2022-04-14","arxiv_id":"2204.07207","n_code_links":0,"syntology":null},{"paper":"/paper/latent-aspect-detection-from-online","slug":"latent-aspect-detection-from-online","title":"Latent Aspect Detection from Online Unsolicited Customer Reviews","date":"2022-04-14","arxiv_id":"2204.06964","n_code_links":1,"syntology":null},{"paper":"/paper/minivit-compressing-vision-transformers-with","slug":"minivit-compressing-vision-transformers-with","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","date":"2022-04-14","arxiv_id":"2204.07154","n_code_links":2,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["microsoft/cream"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"multi-label-topic-classification-for-covid-19","title":"Multi-label topic classification for COVID-19 literature with Bioformer","date":"2022-04-14","arxiv_id":"2204.06758","n_code_links":0,"syntology":null},{"paper":null,"slug":"residual-swin-transformer-channel-attention","title":"Residual Swin Transformer Channel Attention Network for Image Demosaicing","date":"2022-04-14","arxiv_id":"2204.07098","n_code_links":0,"syntology":null},{"paper":null,"slug":"rows-from-many-sources-enriching-row","title":"Rows from Many Sources: Enriching row completions from Wikidata with a pre-trained Language Model","date":"2022-04-14","arxiv_id":"2204.07014","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-relation-learning-for-regression-and-its","title":"Deep Relation Learning for Regression and Its Application to Brain Age Estimation","date":"2022-04-13","arxiv_id":"2204.06598","n_code_links":0,"syntology":null},{"paper":"/paper/fix-bugs-with-transformer-through-a-neural-1","slug":"fix-bugs-with-transformer-through-a-neural-1","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2022-04-13","arxiv_id":"2204.06643","n_code_links":0,"syntology":null},{"paper":null,"slug":"formal-language-recognition-by-hard-attention","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity","date":"2022-04-13","arxiv_id":"2204.06618","n_code_links":0,"syntology":null},{"paper":"/paper/hubert-ee-early-exiting-hubert-for-efficient","slug":"hubert-ee-early-exiting-hubert-for-efficient","title":"HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition","date":"2022-04-13","arxiv_id":"2204.06328","n_code_links":1,"syntology":null},{"paper":null,"slug":"iiitdwd-shankarb-dravidian-codemixi-hasoc2021","title":"IIITDWD-ShankarB@ Dravidian-CodeMixi-HASOC2021: mBERT based model for identification of offensive content in south Indian languages","date":"2022-04-13","arxiv_id":"2204.10195","n_code_links":0,"syntology":null},{"paper":null,"slug":"metro-efficient-denoising-pretraining-of","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","date":"2022-04-13","arxiv_id":"2204.06644","n_code_links":0,"syntology":null},{"paper":"/paper/probing-for-constituency-structure-in-neural","slug":"probing-for-constituency-structure-in-neural","title":"Probing for Constituency Structure in Neural Language Models","date":"2022-04-13","arxiv_id":"2204.06201","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["davidarps/constptbprobing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"recognition-of-freely-selected-keypoints-on","title":"Recognition of Freely Selected Keypoints on Human Limbs","date":"2022-04-13","arxiv_id":"2204.06326","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-markovian-generative-architectures","slug":"revisiting-markovian-generative-architectures","title":"Building Markovian Generative Architectures over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems","date":"2022-04-13","arxiv_id":"2204.06452","n_code_links":2,"syntology":null},{"paper":null,"slug":"tangobert-reducing-inference-cost-by-using","title":"TangoBERT: Reducing Inference Cost by using Cascaded Architecture","date":"2022-04-13","arxiv_id":"2204.06271","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-multimodal-transformers-robust-to-missing","title":"Are Multimodal Transformers Robust to Missing Modality?","date":"2022-04-12","arxiv_id":"2204.05454","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancement-of-pitch-controllability-using","title":"Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch","date":"2022-04-12","arxiv_id":"2204.05753","n_code_links":0,"syntology":null},{"paper":"/paper/explore-more-guidance-a-task-aware","slug":"explore-more-guidance-a-task-aware","title":"Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation","date":"2022-04-12","arxiv_id":"2204.05953","n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-learning-with-noisy-labels","slug":"few-shot-learning-with-noisy-labels","title":"Few-shot Learning with Noisy Labels","date":"2022-04-12","arxiv_id":"2204.05494","n_code_links":1,"syntology":null},{"paper":null,"slug":"hitpr-hierarchical-transformer-for-place","title":"HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud","date":"2022-04-12","arxiv_id":"2204.05481","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-mahaner-a-marathi-named-entity","slug":"l3cube-mahaner-a-marathi-named-entity","title":"L3Cube-MahaNER: A Marathi Named Entity Recognition Dataset and BERT models","date":"2022-04-12","arxiv_id":"2204.06029","n_code_links":1,"syntology":null},{"paper":"/paper/swinnet-swin-transformer-drives-edge-aware","slug":"swinnet-swin-transformer-drives-edge-aware","title":"SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection","date":"2022-04-12","arxiv_id":"2204.05585","n_code_links":1,"syntology":null},{"paper":"/paper/what-language-model-architecture-and","slug":"what-language-model-architecture-and","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","date":"2022-04-12","arxiv_id":"2204.05832","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["bigscience-workshop/architecture-objective"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"category-aware-transformer-network-for-better","title":"Category-Aware Transformer Network for Better Human-Object Interaction Detection","date":"2022-04-11","arxiv_id":"2204.04911","n_code_links":0,"syntology":null},{"paper":"/paper/conslt-a-token-level-contrastive-framework","slug":"conslt-a-token-level-contrastive-framework","title":"A Token-level Contrastive Framework for Sign Language Translation","date":"2022-04-11","arxiv_id":"2204.04916","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["biaofuxmu/conslt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/event-transformer","slug":"event-transformer","title":"Event Transformer","date":"2022-04-11","arxiv_id":"2204.05172","n_code_links":1,"syntology":null},{"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":null,"slug":"deep-non-rigid-structure-from-motion-a","title":"Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspective","date":"2022-04-10","arxiv_id":"2204.04730","n_code_links":0,"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":"mbi-net-a-non-intrusive-multi-branched-speech","title":"MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids","date":"2022-04-07","arxiv_id":"2204.03305","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}],"record_sha256":"51bb6de4c8c8f54e75b273eff01173a38ddecb6bf740d25b0bb91508c400a82f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}