{"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/softmax/papers/239","list_of":"/method/softmax","method":"Softmax","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":239,"pages_in_order":375,"rows_per_page":100,"rows":[23801,23900],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/238","next":"/method/softmax/papers/240","papers":[{"paper":null,"slug":"tsmind-alibaba-and-soochow-university-s","title":"TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task","date":"2022-11-16","arxiv_id":"2211.08987","n_code_links":0,"syntology":null},{"paper":"/paper/unified-question-answering-in-slovene","slug":"unified-question-answering-in-slovene","title":"Unified Question Answering in Slovene","date":"2022-11-16","arxiv_id":"2211.09159","n_code_links":1,"syntology":null},{"paper":"/paper/unirel-unified-representation-and-interaction","slug":"unirel-unified-representation-and-interaction","title":"UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction","date":"2022-11-16","arxiv_id":"2211.09039","n_code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-fingerspelling-recognition","slug":"weakly-supervised-fingerspelling-recognition","title":"Weakly-supervised Fingerspelling Recognition in British Sign Language Videos","date":"2022-11-16","arxiv_id":"2211.08954","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-multi-neighborhood-attention-based","title":"Adaptive Multi-Neighborhood Attention based Transformer for Graph Representation Learning","date":"2022-11-15","arxiv_id":"2211.07970","n_code_links":0,"syntology":null},{"paper":"/paper/align-mlm-word-embedding-alignment-is-crucial","slug":"align-mlm-word-embedding-alignment-is-crucial","title":"ALIGN-MLM: Word Embedding Alignment is Crucial for Multilingual Pre-training","date":"2022-11-15","arxiv_id":"2211.08547","n_code_links":1,"syntology":null},{"paper":"/paper/an-fnet-based-auto-encoder-for-long-sequence","slug":"an-fnet-based-auto-encoder-for-long-sequence","title":"An FNet based Auto Encoder for Long Sequence News Story Generation","date":"2022-11-15","arxiv_id":"2211.08295","n_code_links":1,"syntology":null},{"paper":"/paper/auto-outlier-fusion-technique-for-chest-x-ray","slug":"auto-outlier-fusion-technique-for-chest-x-ray","title":"Auto-outlier Fusion Technique for Chest X-ray classification with Multi-head Attention Mechanism","date":"2022-11-15","arxiv_id":"2211.08006","n_code_links":1,"syntology":null},{"paper":"/paper/breakpoint-transformers-for-modeling-and","slug":"breakpoint-transformers-for-modeling-and","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","date":"2022-11-15","arxiv_id":"2211.07950","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["allenai/situation_modeling"],"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":null,"slug":"contextual-transformer-for-offline-meta","title":"Contextual Transformer for Offline Meta Reinforcement Learning","date":"2022-11-15","arxiv_id":"2211.08016","n_code_links":0,"syntology":null},{"paper":null,"slug":"convformer-combining-cnn-and-transformer-for","title":"ConvFormer: Combining CNN and Transformer for Medical Image Segmentation","date":"2022-11-15","arxiv_id":"2211.08564","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-modality-transformer-for-visible","title":"Cross-Modality Transformer for Visible-Infrared Person Re-Identification","date":"2022-11-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-temporal-filtering-in-video-models","slug":"dynamic-temporal-filtering-in-video-models","title":"Dynamic Temporal Filtering in Video Models","date":"2022-11-15","arxiv_id":"2211.08252","n_code_links":1,"syntology":null},{"paper":null,"slug":"empowering-language-models-with-knowledge","title":"Empowering Language Models with Knowledge Graph Reasoning for Question Answering","date":"2022-11-15","arxiv_id":"2211.08380","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedtune-a-deep-dive-into-efficient-federated","title":"FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers","date":"2022-11-15","arxiv_id":"2211.08025","n_code_links":0,"syntology":null},{"paper":"/paper/glue-x-evaluating-natural-language","slug":"glue-x-evaluating-natural-language","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","date":"2022-11-15","arxiv_id":"2211.08073","n_code_links":1,"syntology":null},{"paper":"/paper/hybrid-transformers-for-music-source","slug":"hybrid-transformers-for-music-source","title":"Hybrid Transformers for Music Source Separation","date":"2022-11-15","arxiv_id":"2211.08553","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":10,"phrase":"9 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/demucs"],"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/influencer-detection-with-dynamic-graph","slug":"influencer-detection-with-dynamic-graph","title":"Influencer Detection with Dynamic Graph Neural Networks","date":"2022-11-15","arxiv_id":"2211.09664","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-for-detection","slug":"knowledge-distillation-for-detection","title":"Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2022-11-15","arxiv_id":"2211.08071","n_code_links":2,"syntology":null},{"paper":"/paper/latent-bottlenecked-attentive-neural","slug":"latent-bottlenecked-attentive-neural","title":"Latent Bottlenecked Attentive Neural Processes","date":"2022-11-15","arxiv_id":"2211.08458","n_code_links":1,"syntology":null},{"paper":"/paper/promptcap-prompt-guided-task-aware-image","slug":"promptcap-prompt-guided-task-aware-image","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","date":"2022-11-15","arxiv_id":"2211.09699","n_code_links":1,"syntology":null},{"paper":null,"slug":"robbert-2022-updating-a-dutch-language-model","title":"RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use","date":"2022-11-15","arxiv_id":"2211.08192","n_code_links":0,"syntology":null},{"paper":"/paper/shadowdiffusion-diffusion-based-shadow","slug":"shadowdiffusion-diffusion-based-shadow","title":"DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity","date":"2022-11-15","arxiv_id":"2211.08089","n_code_links":1,"syntology":null},{"paper":"/paper/are-hard-examples-also-harder-to-explain-a","slug":"are-hard-examples-also-harder-to-explain-a","title":"Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations","date":"2022-11-14","arxiv_id":"2211.07517","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["swarnahub/explanationhardness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bivit-extremely-compressed-binary-vision","title":"BiViT: Extremely Compressed Binary Vision Transformer","date":"2022-11-14","arxiv_id":"2211.07091","n_code_links":0,"syntology":null},{"paper":"/paper/cabvit-cross-attention-among-blocks-for","slug":"cabvit-cross-attention-among-blocks-for","title":"Fcaformer: Forward Cross Attention in Hybrid Vision Transformer","date":"2022-11-14","arxiv_id":"2211.07198","n_code_links":2,"syntology":null},{"paper":"/paper/cst5-data-augmentation-for-code-switched-1","slug":"cst5-data-augmentation-for-code-switched-1","title":"CST5: Data Augmentation for Code-Switched Semantic Parsing","date":"2022-11-14","arxiv_id":"2211.07514","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-methods-for-automatic-1","title":"Artificial Intelligence for Automatic Detection and Classification Disease on the X-Ray Images","date":"2022-11-14","arxiv_id":"2211.08244","n_code_links":0,"syntology":null},{"paper":"/paper/evade-the-trap-of-mediocrity-promoting","slug":"evade-the-trap-of-mediocrity-promoting","title":"Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention","date":"2022-11-14","arxiv_id":"2211.07164","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpreting-bias-in-the-neural-networks-a","title":"Interpreting Bias in the Neural Networks: A Peek Into Representational Similarity","date":"2022-11-14","arxiv_id":"2211.07774","n_code_links":0,"syntology":null},{"paper":"/paper/on-analyzing-the-role-of-image-for-visual","slug":"on-analyzing-the-role-of-image-for-visual","title":"On Analyzing the Role of Image for Visual-enhanced Relation Extraction","date":"2022-11-14","arxiv_id":"2211.07504","n_code_links":2,"syntology":null},{"paper":null,"slug":"pruning-very-deep-neural-network-channels-for","title":"Pruning Very Deep Neural Network Channels for Efficient Inference","date":"2022-11-14","arxiv_id":"2211.08339","n_code_links":0,"syntology":null},{"paper":null,"slug":"queryform-a-simple-zero-shot-form-entity","title":"QueryForm: A Simple Zero-shot Form Entity Query Framework","date":"2022-11-14","arxiv_id":"2211.07730","n_code_links":0,"syntology":null},{"paper":null,"slug":"spe-symmetrical-prompt-enhancement-for-fact","title":"SPE: Symmetrical Prompt Enhancement for Fact Probing","date":"2022-11-14","arxiv_id":"2211.07078","n_code_links":0,"syntology":null},{"paper":"/paper/technological-taxonomies-for-hypernym-and","slug":"technological-taxonomies-for-hypernym-and","title":"Technological taxonomies for hypernym and hyponym retrieval in patent texts","date":"2022-11-14","arxiv_id":"2212.06039","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-robust-numerical-question-answering","title":"Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems","date":"2022-11-14","arxiv_id":"2211.07455","n_code_links":0,"syntology":null},{"paper":"/paper/ugif-ui-grounded-instruction-following","slug":"ugif-ui-grounded-instruction-following","title":"UGIF: UI Grounded Instruction Following","date":"2022-11-14","arxiv_id":"2211.07615","n_code_links":0,"syntology":null},{"paper":null,"slug":"wsc-trans-a-3d-network-model-for-automatic","title":"WSC-Trans: A 3D network model for automatic multi-structural segmentation of temporal bone CT","date":"2022-11-14","arxiv_id":"2211.07143","n_code_links":0,"syntology":null},{"paper":null,"slug":"demystify-self-attention-in-vision","title":"Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application","date":"2022-11-13","arxiv_id":"2211.08543","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-few-shot-image-classification-with","slug":"enhancing-few-shot-image-classification-with","title":"Enhancing Few-shot Image Classification with Cosine Transformer","date":"2022-11-13","arxiv_id":"2211.06828","n_code_links":1,"syntology":null},{"paper":"/paper/greenplm-cross-lingual-pre-trained-language","slug":"greenplm-cross-lingual-pre-trained-language","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","date":"2022-11-13","arxiv_id":"2211.06993","n_code_links":1,"syntology":null},{"paper":"/paper/learning-from-partially-labeled-data-for","slug":"learning-from-partially-labeled-data-for","title":"Learning from partially labeled data for multi-organ and tumor segmentation","date":"2022-11-13","arxiv_id":"2211.06894","n_code_links":1,"syntology":null},{"paper":"/paper/residual-degradation-learning-unfolding","slug":"residual-degradation-learning-unfolding","title":"Residual Degradation Learning Unfolding Framework with Mixing Priors across Spectral and Spatial for Compressive Spectral Imaging","date":"2022-11-13","arxiv_id":"2211.06891","n_code_links":1,"syntology":null},{"paper":"/paper/ssl4eo-s12-a-large-scale-multi-modal-multi","slug":"ssl4eo-s12-a-large-scale-multi-modal-multi","title":"SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation","date":"2022-11-13","arxiv_id":"2211.07044","n_code_links":4,"syntology":null},{"paper":null,"slug":"textual-data-augmentation-for-patient","title":"Textual Data Augmentation for Patient Outcomes Prediction","date":"2022-11-13","arxiv_id":"2211.06778","n_code_links":0,"syntology":null},{"paper":"/paper/what-would-harry-say-building-dialogue-agents","slug":"what-would-harry-say-building-dialogue-agents","title":"Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters","date":"2022-11-13","arxiv_id":"2211.06869","n_code_links":1,"syntology":null},{"paper":"/paper/xu-at-semeval-2022-task-4-pre-bert-neural-1","slug":"xu-at-semeval-2022-task-4-pre-bert-neural-1","title":"Xu at SemEval-2022 Task 4: Pre-BERT Neural Network Methods vs Post-BERT RoBERTa Approach for Patronizing and Condescending Language Detection","date":"2022-11-13","arxiv_id":"2211.06874","n_code_links":1,"syntology":null},{"paper":null,"slug":"au-aware-vision-transformers-for-biased","title":"AU-Aware Vision Transformers for Biased Facial Expression Recognition","date":"2022-11-12","arxiv_id":"2211.06609","n_code_links":0,"syntology":null},{"paper":"/paper/dark-patterns-in-e-commerce-a-dataset-and-its","slug":"dark-patterns-in-e-commerce-a-dataset-and-its","title":"Dark patterns in e-commerce: a dataset and its baseline evaluations","date":"2022-11-12","arxiv_id":"2211.06543","n_code_links":1,"syntology":null},{"paper":null,"slug":"deyo-detr-with-yolo-for-step-by-step-object","title":"DEYO: DETR with YOLO for Step-by-Step Object Detection","date":"2022-11-12","arxiv_id":"2211.06588","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-machine-learning-framework-for","title":"End-to-End Machine Learning Framework for Facial AU Detection in Intensive Care Units","date":"2022-11-12","arxiv_id":"2211.06570","n_code_links":0,"syntology":null},{"paper":null,"slug":"kinematics-transformer-solving-the-inverse","title":"Kinematics Transformer: Solving The Inverse Modeling Problem of Soft Robots using Transformers","date":"2022-11-12","arxiv_id":"2211.06643","n_code_links":0,"syntology":null},{"paper":null,"slug":"multicrossvit-multimodal-vision-transformer","title":"MultiCrossViT: Multimodal Vision Transformer for Schizophrenia Prediction using Structural MRI and Functional Network Connectivity Data","date":"2022-11-12","arxiv_id":"2211.06726","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-benchmark-for-out-of-distribution-detection","title":"A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation","date":"2022-11-11","arxiv_id":"2211.06241","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-adapter-based-multi-label-pre-training-for","title":"An Adapter based Multi-label Pre-training for Speech Separation and Enhancement","date":"2022-11-11","arxiv_id":"2211.06041","n_code_links":0,"syntology":null},{"paper":null,"slug":"control-transformer-robot-navigation-in","title":"Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling","date":"2022-11-11","arxiv_id":"2211.06407","n_code_links":0,"syntology":null},{"paper":null,"slug":"docut5-seq2seq-sql-generation-with-table","title":"DocuT5: Seq2seq SQL Generation with Table Documentation","date":"2022-11-11","arxiv_id":"2211.06193","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-hla-imputation-from-sequential-snps","slug":"efficient-hla-imputation-from-sequential-snps","title":"Efficient HLA imputation from sequential SNPs data by Transformer","date":"2022-11-11","arxiv_id":"2211.06430","n_code_links":1,"syntology":null},{"paper":null,"slug":"gambling-on-momentum","title":"Gambling on Momentum","date":"2022-11-11","arxiv_id":"2211.06052","n_code_links":0,"syntology":null},{"paper":"/paper/misinformation-detection-using-persuasive","slug":"misinformation-detection-using-persuasive","title":"Using Persuasive Writing Strategies to Explain and Detect Health Misinformation","date":"2022-11-11","arxiv_id":"2211.05985","n_code_links":1,"syntology":null},{"paper":null,"slug":"patchblender-a-motion-prior-for-video","title":"PatchBlender: A Motion Prior for Video Transformers","date":"2022-11-11","arxiv_id":"2211.14449","n_code_links":0,"syntology":null},{"paper":"/paper/repghost-a-hardware-efficient-ghost-module","slug":"repghost-a-hardware-efficient-ghost-module","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","date":"2022-11-11","arxiv_id":"2211.06088","n_code_links":3,"syntology":{"ran":10,"of":17,"n_ran_checked":10,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"10 ran (of which 0 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) · 7 unverified","official":{"repos":["chengpengchen/repghost","rwightman/pytorch-image-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ssgvs-semantic-scene-graph-to-video-synthesis","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","date":"2022-11-11","arxiv_id":"2211.06119","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-architectural-bottleneck-principle","title":"The Architectural Bottleneck Principle","date":"2022-11-11","arxiv_id":"2211.06420","n_code_links":0,"syntology":null},{"paper":null,"slug":"token-transformer-can-class-token-help-window","title":"Token Transformer: Can class token help window-based transformer build better long-range interactions?","date":"2022-11-11","arxiv_id":"2211.06083","n_code_links":0,"syntology":null},{"paper":null,"slug":"assistive-completion-of-agrammatic-aphasic","title":"Assistive Completion of Agrammatic Aphasic Sentences: A Transfer Learning Approach using Neurolinguistics-based Synthetic Dataset","date":"2022-11-10","arxiv_id":"2211.05557","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-combination-of-convolutional-and","title":"BERT-Based Combination of Convolutional and Recurrent Neural Network for Indonesian Sentiment Analysis","date":"2022-11-10","arxiv_id":"2211.05273","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-in-plutarch-s-shadows","title":"BERT in Plutarch's Shadows","date":"2022-11-10","arxiv_id":"2211.05673","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedical-multi-hop-question-answering-using","title":"Biomedical Multi-hop Question Answering Using Knowledge Graph Embeddings and Language Models","date":"2022-11-10","arxiv_id":"2211.05351","n_code_links":0,"syntology":null},{"paper":"/paper/cherry-hypothesis-identifying-the-cherry-on","slug":"cherry-hypothesis-identifying-the-cherry-on","title":"PAD-Net: An Efficient Framework for Dynamic Networks","date":"2022-11-10","arxiv_id":"2211.05528","n_code_links":1,"syntology":null},{"paper":null,"slug":"coordinating-cav-swarms-at-intersections-with","title":"Coordinating CAV Swarms at Intersections with a Deep Learning Model","date":"2022-11-10","arxiv_id":"2211.05297","n_code_links":0,"syntology":null},{"paper":"/paper/demystify-transformers-convolutions-in-modern","slug":"demystify-transformers-convolutions-in-modern","title":"Demystify Transformers & Convolutions in Modern Image Deep Networks","date":"2022-11-10","arxiv_id":"2211.05781","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opengvlab/stm-evaluation"],"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/fine-grained-entity-segmentation","slug":"fine-grained-entity-segmentation","title":"High-Quality Entity Segmentation","date":"2022-11-10","arxiv_id":"2211.05776","n_code_links":1,"syntology":null},{"paper":null,"slug":"hyperbolic-cosine-transformer-for-lidar-3d","title":"Hyperbolic Cosine Transformer for LiDAR 3D Object Detection","date":"2022-11-10","arxiv_id":"2211.05580","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-forgetting-in-online-continual-3","title":"Mitigating Forgetting in Online Continual Learning via Contrasting Semantically Distinct Augmentations","date":"2022-11-10","arxiv_id":"2211.05347","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-optimizing-the-communication-of-model","title":"On Optimizing the Communication of Model Parallelism","date":"2022-11-10","arxiv_id":"2211.05322","n_code_links":0,"syntology":null},{"paper":"/paper/oneformer-one-transformer-to-rule-universal","slug":"oneformer-one-transformer-to-rule-universal","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","date":"2022-11-10","arxiv_id":"2211.06220","n_code_links":4,"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":["SHI-Labs/OneFormer"],"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":"syntax-guided-domain-adaptation-for-aspect","title":"Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis","date":"2022-11-10","arxiv_id":"2211.05457","n_code_links":0,"syntology":null},{"paper":null,"slug":"test-time-adversarial-detection-and","title":"Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses","date":"2022-11-10","arxiv_id":"2211.05854","n_code_links":0,"syntology":null},{"paper":"/paper/unifying-flow-stereo-and-depth-estimation","slug":"unifying-flow-stereo-and-depth-estimation","title":"Unifying Flow, Stereo and Depth Estimation","date":"2022-11-10","arxiv_id":"2211.05783","n_code_links":1,"syntology":null},{"paper":null,"slug":"viecap4h-vlsp-2021-objectaoa-enhancing","title":"VieCap4H-VLSP 2021: ObjectAoA-Enhancing performance of Object Relation Transformer with Attention on Attention for Vietnamese image captioning","date":"2022-11-10","arxiv_id":"2211.05405","n_code_links":0,"syntology":null},{"paper":"/paper/bloom-a-176b-parameter-open-access","slug":"bloom-a-176b-parameter-open-access","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","date":"2022-11-09","arxiv_id":"2211.05100","n_code_links":7,"syntology":{"ran":2,"of":11,"n_ran_checked":1,"n_instrument":1,"unverified":9,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":null}},{"paper":"/paper/collateral-facilitation-in-humans-and","slug":"collateral-facilitation-in-humans-and","title":"Collateral facilitation in humans and language models","date":"2022-11-09","arxiv_id":"2211.05198","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jmichaelov/collateral-facilitation"],"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":"cross-lingual-transfer-learning-for-check","title":"Cross-lingual Transfer Learning for Check-worthy Claim Identification over Twitter","date":"2022-11-09","arxiv_id":"2211.05087","n_code_links":0,"syntology":null},{"paper":null,"slug":"distribution-aligned-fine-tuning-for","title":"Distribution-Aligned Fine-Tuning for Efficient Neural Retrieval","date":"2022-11-09","arxiv_id":"2211.04942","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-large-scale-audio-tagging-via","slug":"efficient-large-scale-audio-tagging-via","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","date":"2022-11-09","arxiv_id":"2211.04772","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fschmid56/efficientat"],"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":"efficiently-scaling-transformer-inference","title":"Efficiently Scaling Transformer Inference","date":"2022-11-09","arxiv_id":"2211.05102","n_code_links":0,"syntology":null},{"paper":null,"slug":"ff2-a-feature-fusion-two-stream-framework-for","title":"FF2: A Feature Fusion Two-Stream Framework for Punctuation Restoration","date":"2022-11-09","arxiv_id":"2211.04699","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-with-controllable","title":"Large Language Models with Controllable Working Memory","date":"2022-11-09","arxiv_id":"2211.05110","n_code_links":0,"syntology":null},{"paper":"/paper/mask-more-and-mask-later-efficient-pre","slug":"mask-more-and-mask-later-efficient-pre","title":"Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token","date":"2022-11-09","arxiv_id":"2211.04898","n_code_links":1,"syntology":null},{"paper":"/paper/masked-vision-language-transformers-for-scene","slug":"masked-vision-language-transformers-for-scene","title":"Masked Vision-Language Transformers for Scene Text Recognition","date":"2022-11-09","arxiv_id":"2211.04785","n_code_links":1,"syntology":null},{"paper":null,"slug":"pure-transformer-with-integrated-experts-for","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","date":"2022-11-09","arxiv_id":"2211.04963","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-persian-language-review","title":"Sentiment Analysis of Persian Language: Review of Algorithms, Approaches and Datasets","date":"2022-11-09","arxiv_id":"2212.06041","n_code_links":0,"syntology":null},{"paper":null,"slug":"sg-shuffle-multi-aspect-shuffle-transformer","title":"SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation","date":"2022-11-09","arxiv_id":"2211.04773","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-reasoning-aware-explainable-vqa","title":"Towards Reasoning-Aware Explainable VQA","date":"2022-11-09","arxiv_id":"2211.05190","n_code_links":0,"syntology":null},{"paper":"/paper/training-a-vision-transformer-from-scratch-in","slug":"training-a-vision-transformer-from-scratch-in","title":"Training a Vision Transformer from scratch in less than 24 hours with 1 GPU","date":"2022-11-09","arxiv_id":"2211.05187","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 4 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) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"transformers-meet-small-datasets","title":"Transformers Meet Small Datasets","date":"2022-11-09","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/vitality-unifying-low-rank-and-sparse","slug":"vitality-unifying-low-rank-and-sparse","title":"ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention","date":"2022-11-09","arxiv_id":"2211.05109","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":11,"n_instrument":2,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["GATECH-EIC/ViTaLiTy"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-multimodal-approach-for-dementia-detection","title":"A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer","date":"2022-11-08","arxiv_id":"2211.04368","n_code_links":0,"syntology":null},{"paper":"/paper/a-new-bart-prior-for-flexible-modeling-with","slug":"a-new-bart-prior-for-flexible-modeling-with","title":"flexBART: Flexible Bayesian regression trees with categorical predictors","date":"2022-11-08","arxiv_id":"2211.04459","n_code_links":1,"syntology":null}],"record_sha256":"c6c8fa6bf83af85727f8b4c6c4d1e95bf09a476be01d7d0650b58b3b797a9aa7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}