{"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/308","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":308,"pages_in_order":375,"rows_per_page":100,"rows":[30701,30800],"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/307","next":"/method/softmax/papers/309","papers":[{"paper":"/paper/sg-net-spatial-granularity-network-for-one","slug":"sg-net-spatial-granularity-network-for-one","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","date":"2021-03-18","arxiv_id":"2103.10284","n_code_links":1,"syntology":null},{"paper":"/paper/smoothing-and-shrinking-the-sparse-seq2seq","slug":"smoothing-and-shrinking-the-sparse-seq2seq","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","date":"2021-03-18","arxiv_id":"2103.10291","n_code_links":1,"syntology":null},{"paper":null,"slug":"spices-survey-papers-as-interactive","title":"SPICES: SURVEY PAPERS AS INTERACTIVE CHEATSHEET EMBEDDINGS","date":"2021-03-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/unetr-transformers-for-3d-medical-image","slug":"unetr-transformers-for-3d-medical-image","title":"UNETR: Transformers for 3D Medical Image Segmentation","date":"2021-03-18","arxiv_id":"2103.10504","n_code_links":10,"syntology":null},{"paper":"/paper/cnn-model-tuning-for-global-road-damage","slug":"cnn-model-tuning-for-global-road-damage","title":"CNN Model & Tuning for Global Road Damage Detection","date":"2021-03-17","arxiv_id":"2103.09512","n_code_links":1,"syntology":null},{"paper":null,"slug":"code-word-detection-in-fraud-investigations","title":"Code Word Detection in Fraud Investigations using a Deep-Learning Approach","date":"2021-03-17","arxiv_id":"2103.09606","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-role-of-images-for-analyzing-claims-in","slug":"on-the-role-of-images-for-analyzing-claims-in","title":"On the Role of Images for Analyzing Claims in Social Media","date":"2021-03-17","arxiv_id":"2103.09602","n_code_links":1,"syntology":null},{"paper":null,"slug":"sml-a-new-semantic-embedding-alignment","title":"SILT: Efficient transformer training for inter-lingual inference","date":"2021-03-17","arxiv_id":"2103.09635","n_code_links":0,"syntology":null},{"paper":"/paper/trans-svnet-accurate-phase-recognition-from","slug":"trans-svnet-accurate-phase-recognition-from","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","date":"2021-03-17","arxiv_id":"2103.09712","n_code_links":1,"syntology":null},{"paper":"/paper/triplet-watershed-for-hyperspectral-image","slug":"triplet-watershed-for-hyperspectral-image","title":"Triplet-Watershed for Hyperspectral Image Classification","date":"2021-03-17","arxiv_id":"2103.09384","n_code_links":1,"syntology":null},{"paper":"/paper/uniparma-semeval-2021-task-5-toxic-spans","slug":"uniparma-semeval-2021-task-5-toxic-spans","title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model","date":"2021-03-17","arxiv_id":"2103.09645","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-look-one-level-feature","slug":"you-only-look-one-level-feature","title":"You Only Look One-level Feature","date":"2021-03-17","arxiv_id":"2103.09460","n_code_links":6,"syntology":null},{"paper":null,"slug":"adversarial-yolo-defense-human-detection","title":"Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches","date":"2021-03-16","arxiv_id":"2103.08860","n_code_links":0,"syntology":null},{"paper":"/paper/dense-interaction-learning-for-video-based","slug":"dense-interaction-learning-for-video-based","title":"Dense Interaction Learning for Video-based Person Re-identification","date":"2021-03-16","arxiv_id":"2103.09013","n_code_links":0,"syntology":null},{"paper":null,"slug":"frequency-aware-discriminative-feature","title":"Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection","date":"2021-03-16","arxiv_id":"2103.09096","n_code_links":0,"syntology":null},{"paper":null,"slug":"kgsynnet-a-novel-entity-synonyms-discovery","title":"KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph","date":"2021-03-16","arxiv_id":"2103.08893","n_code_links":0,"syntology":null},{"paper":"/paper/lightningdot-pre-training-visual-semantic","slug":"lightningdot-pre-training-visual-semantic","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","date":"2021-03-16","arxiv_id":"2103.08784","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["intersun/LightningDOT"],"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":"robustly-optimized-and-distilled-training-for","title":"Robustly Optimized and Distilled Training for Natural Language Understanding","date":"2021-03-16","arxiv_id":"2103.08809","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-driven-description-synthesis-for","title":"Knowledge driven Description Synthesis for Floor Plan Interpretation","date":"2021-03-15","arxiv_id":"2103.08298","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-invariance-via-feedforward","title":"Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers","date":"2021-03-15","arxiv_id":"2103.07470","n_code_links":0,"syntology":null},{"paper":"/paper/improving-code-summarization-with-block-wise","slug":"improving-code-summarization-with-block-wise","title":"Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting","date":"2021-03-14","arxiv_id":"2103.07845","n_code_links":1,"syntology":null},{"paper":null,"slug":"semvlp-vision-language-pre-training-by-1","title":"SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels","date":"2021-03-14","arxiv_id":"2103.07829","n_code_links":0,"syntology":null},{"paper":"/paper/transfg-a-transformer-architecture-for-fine","slug":"transfg-a-transformer-architecture-for-fine","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","date":"2021-03-14","arxiv_id":"2103.07976","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["TACJu/TransFG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/approximating-how-single-head-attention","slug":"approximating-how-single-head-attention","title":"Approximating How Single Head Attention Learns","date":"2021-03-13","arxiv_id":"2103.07601","n_code_links":1,"syntology":null},{"paper":null,"slug":"embedding-calibration-for-music-semantic","title":"Optimal Embedding Calibration for Symbolic Music Similarity","date":"2021-03-13","arxiv_id":"2103.07656","n_code_links":0,"syntology":null},{"paper":null,"slug":"targeted-aspect-based-multimodal-sentiment","title":"Targeted aspect based multimodal sentiment analysis:an attention capsule extraction and multi-head fusion network","date":"2021-03-13","arxiv_id":"2103.07659","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-mining-of-stocktwits-data-for-predicting","title":"Text Mining of Stocktwits Data for Predicting Stock Prices","date":"2021-03-13","arxiv_id":"2103.16388","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-multiple-linear-regression-based","title":"Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze","date":"2021-03-12","arxiv_id":"2103.07065","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-dictionary-based-language-model","title":"Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation","date":"2021-03-12","arxiv_id":"2103.07040","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-the-performance-of-nlp-toolkits-and","title":"Comparing the Performance of NLP Toolkits and Evaluation measures in Legal Tech","date":"2021-03-12","arxiv_id":"2103.11792","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-and-improving-bert-performance-on","title":"Explaining and Improving BERT Performance on Lexical Semantic Change Detection","date":"2021-03-12","arxiv_id":"2103.07259","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-bert-a-cross-disciplinary-knowledge","title":"Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability","date":"2021-03-12","arxiv_id":"2103.07162","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-architecture-search-based-on-cartesian","title":"Neural Architecture Search based on Cartesian Genetic Programming Coding Method","date":"2021-03-12","arxiv_id":"2103.07173","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-the-behavior-of-dealers-in-over","title":"Predicting the Behavior of Dealers in Over-The-Counter Corporate Bond Markets","date":"2021-03-12","arxiv_id":"2103.09098","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-random-network-for-fine-grained","title":"Sequential Random Network for Fine-grained Image Classification","date":"2021-03-12","arxiv_id":"2103.07230","n_code_links":0,"syntology":null},{"paper":null,"slug":"severity-quantification-and-lesion","title":"Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer","date":"2021-03-12","arxiv_id":"2103.07062","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-for-covid-19-cxr-diagnosis","title":"Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus","date":"2021-03-12","arxiv_id":"2103.07055","n_code_links":0,"syntology":null},{"paper":"/paper/canine-pre-training-an-efficient-tokenization","slug":"canine-pre-training-an-efficient-tokenization","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","date":"2021-03-11","arxiv_id":"2103.06874","n_code_links":6,"syntology":null},{"paper":null,"slug":"composite-re-ranking-for-efficient-document","title":"Composite Re-Ranking for Efficient Document Search with BERT","date":"2021-03-11","arxiv_id":"2103.06499","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-3d-multi-channel-sign-language","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","date":"2021-03-11","arxiv_id":"2103.06982","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-morphological-embeddings-for-1","title":"Evaluation of Morphological Embeddings for the Russian Language","date":"2021-03-11","arxiv_id":"2103.06628","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairfil-contrastive-neural-debiasing-method-1","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","date":"2021-03-11","arxiv_id":"2103.06413","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bi-encoder-document-ranking-models","slug":"improving-bi-encoder-document-ranking-models","title":"Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation","date":"2021-03-11","arxiv_id":"2103.06523","n_code_links":1,"syntology":null},{"paper":null,"slug":"lightmbert-a-simple-yet-effective-method-for","title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","date":"2021-03-11","arxiv_id":"2103.06418","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-improving-deep-learning-trace-analysis","title":"On Improving Deep Learning Trace Analysis with System Call Arguments","date":"2021-03-11","arxiv_id":"2103.06915","n_code_links":0,"syntology":null},{"paper":null,"slug":"pavement-distress-detection-and-segmentation","title":"Pavement Distress Detection and Segmentation using YOLOv4 and DeepLabv3 on Pavements in the Philippines","date":"2021-03-11","arxiv_id":"2103.06467","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-text-to-sql-learning-with","title":"Self-supervised Text-to-SQL Learning with Header Alignment Training","date":"2021-03-11","arxiv_id":"2103.06402","n_code_links":0,"syntology":null},{"paper":"/paper/towards-multi-sense-cross-lingual-alignment-1","slug":"towards-multi-sense-cross-lingual-alignment-1","title":"Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings","date":"2021-03-11","arxiv_id":"2103.06459","n_code_links":1,"syntology":null},{"paper":"/paper/unknown-object-segmentation-from-stereo","slug":"unknown-object-segmentation-from-stereo","title":"Unknown Object Segmentation from Stereo Images","date":"2021-03-11","arxiv_id":"2103.06796","n_code_links":2,"syntology":null},{"paper":"/paper/cuad-an-expert-annotated-nlp-dataset-for","slug":"cuad-an-expert-annotated-nlp-dataset-for","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","date":"2021-03-10","arxiv_id":"2103.06268","n_code_links":2,"syntology":null},{"paper":"/paper/hurdles-to-progress-in-long-form-question","slug":"hurdles-to-progress-in-long-form-question","title":"Hurdles to Progress in Long-form Question Answering","date":"2021-03-10","arxiv_id":"2103.06332","n_code_links":2,"syntology":null},{"paper":"/paper/majority-voting-with-bidirectional-pre","slug":"majority-voting-with-bidirectional-pre","title":"Majority Voting with Bidirectional Pre-translation For Bitext Retrieval","date":"2021-03-10","arxiv_id":"2103.06369","n_code_links":1,"syntology":null},{"paper":null,"slug":"piecewise-linear-regression-and","title":"Piecewise linear regression and classification","date":"2021-03-10","arxiv_id":"2103.06189","n_code_links":0,"syntology":null},{"paper":"/paper/quality-aware-network-for-human-parsing","slug":"quality-aware-network-for-human-parsing","title":"Quality-Aware Network for Human Parsing","date":"2021-03-10","arxiv_id":"2103.05997","n_code_links":1,"syntology":null},{"paper":null,"slug":"rl-csdia-representation-learning-of-computer","title":"RL-CSDia: Representation Learning of Computer Science Diagrams","date":"2021-03-10","arxiv_id":"2103.05900","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mask-r-cnn-approach-to-counting-bacterial","title":"A Mask R-CNN approach to counting bacterial colony forming units in pharmaceutical development","date":"2021-03-09","arxiv_id":"2103.05337","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-code-generation-from-sketches-of","slug":"automatic-code-generation-from-sketches-of","title":"Automatic code generation from sketches of mobile applications in end-user development using Deep Learning","date":"2021-03-09","arxiv_id":"2103.05704","n_code_links":1,"syntology":null},{"paper":null,"slug":"ceqe-contextualized-embeddings-for-query","title":"CEQE: Contextualized Embeddings for Query Expansion","date":"2021-03-09","arxiv_id":"2103.05256","n_code_links":0,"syntology":null},{"paper":"/paper/pretrained-transformers-as-universal","slug":"pretrained-transformers-as-universal","title":"Pretrained Transformers as Universal Computation Engines","date":"2021-03-09","arxiv_id":"2103.05247","n_code_links":4,"syntology":null},{"paper":"/paper/language-models-have-a-moral-dimension","slug":"language-models-have-a-moral-dimension","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","date":"2021-03-08","arxiv_id":"2103.11790","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":["ml-research/MoRT_NMI"],"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/opanas-one-shot-path-aggregation-network","slug":"opanas-one-shot-path-aggregation-network","title":"OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection","date":"2021-03-08","arxiv_id":"2103.04507","n_code_links":1,"syntology":null},{"paper":null,"slug":"skillbert-skilling-the-bert-to-classify-1","title":"SKILLBERT: “SKILLING” THE BERT TO CLASSIFY SKILLS!","date":"2021-03-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-batch-all-triplet-loss-for-visible","title":"Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification","date":"2021-03-08","arxiv_id":"2103.04607","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-pretraining-for-object-detection","title":"Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors","date":"2021-03-08","arxiv_id":"2103.04814","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-adversarial-examples-from","slug":"detecting-adversarial-examples-from","title":"Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain","date":"2021-03-07","arxiv_id":"2103.04302","n_code_links":1,"syntology":null},{"paper":null,"slug":"mtlhealth-a-deep-learning-system-for","title":"MTLHealth: A Deep Learning System for Detecting Disturbing Content in Student Essays","date":"2021-03-07","arxiv_id":"2103.04290","n_code_links":0,"syntology":null},{"paper":null,"slug":"orthogonal-attention-a-cloze-style-approach","title":"Orthogonal Attention: A Cloze-Style Approach to Negation Scope Resolution","date":"2021-03-07","arxiv_id":"2103.04294","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-bert-improving-pre-trained","slug":"syntax-bert-improving-pre-trained","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","date":"2021-03-07","arxiv_id":"2103.04350","n_code_links":1,"syntology":null},{"paper":"/paper/transbts-multimodal-brain-tumor-segmentation","slug":"transbts-multimodal-brain-tumor-segmentation","title":"TransBTS: Multimodal Brain Tumor Segmentation Using Transformer","date":"2021-03-07","arxiv_id":"2103.04430","n_code_links":3,"syntology":null},{"paper":"/paper/a-real-time-low-cost-artificial-intelligence","slug":"a-real-time-low-cost-artificial-intelligence","title":"A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations","date":"2021-03-06","arxiv_id":"2103.04132","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolution-neural-network-hyperparameter","title":"Convolution Neural Network Hyperparameter Optimization Using Simplified Swarm Optimization","date":"2021-03-06","arxiv_id":"2103.03995","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-on-incorporating-pretrained-and","slug":"investigating-on-incorporating-pretrained-and","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","date":"2021-03-06","arxiv_id":"2103.04088","n_code_links":1,"syntology":null},{"paper":null,"slug":"multitasking-deep-learning-model-for","title":"Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy","date":"2021-03-06","arxiv_id":"2103.04207","n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-explanation-using-attention-mechanism-1","title":"Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning","date":"2021-03-06","arxiv_id":"2103.04067","n_code_links":0,"syntology":null},{"paper":"/paper/webface260m-a-benchmark-unveiling-the-power","slug":"webface260m-a-benchmark-unveiling-the-power","title":"WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition","date":"2021-03-06","arxiv_id":"2103.04098","n_code_links":0,"syntology":null},{"paper":"/paper/attention-is-not-all-you-need-pure-attention","slug":"attention-is-not-all-you-need-pure-attention","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","date":"2021-03-05","arxiv_id":"2103.03404","n_code_links":1,"syntology":null},{"paper":"/paper/dual-pointer-network-for-fast-extraction-of","slug":"dual-pointer-network-for-fast-extraction-of","title":"Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence","date":"2021-03-05","arxiv_id":"2103.03509","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-pretrained-multilingual-bert","title":"Fine-tuning Pretrained Multilingual BERT Model for Indonesian Aspect-based Sentiment Analysis","date":"2021-03-05","arxiv_id":"2103.03732","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-for-multilingual","title":"Hierarchical Transformer for Multilingual Machine Translation","date":"2021-03-05","arxiv_id":"2103.03589","n_code_links":0,"syntology":null},{"paper":"/paper/iot-instance-wise-layer-reordering-for-1","slug":"iot-instance-wise-layer-reordering-for-1","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","date":"2021-03-05","arxiv_id":"2103.03457","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["instance-wise-ordered-transformer/IOT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"malbert-using-transformers-for-cybersecurity","title":"MalBERT: Using Transformers for Cybersecurity and Malicious Software Detection","date":"2021-03-05","arxiv_id":"2103.03806","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-mathematical-problem-solving-with","slug":"measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"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":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"non-invasive-self-attention-for-side","title":"Non-invasive Self-attention for Side Information Fusion in Sequential Recommendation","date":"2021-03-05","arxiv_id":"2103.03578","n_code_links":0,"syntology":null},{"paper":null,"slug":"npt-loss-a-metric-loss-with-implicit-mining","title":"NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition","date":"2021-03-05","arxiv_id":"2103.03503","n_code_links":0,"syntology":null},{"paper":"/paper/spectr-spectral-transformer-for-hyperspectral","slug":"spectr-spectral-transformer-for-hyperspectral","title":"SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation","date":"2021-03-05","arxiv_id":"2103.03604","n_code_links":1,"syntology":null},{"paper":"/paper/cotr-efficiently-bridging-cnn-and-transformer","slug":"cotr-efficiently-bridging-cnn-and-transformer","title":"CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation","date":"2021-03-04","arxiv_id":"2103.03024","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-acoustic-modelling-for-phone","title":"End-to-end acoustic modelling for phone recognition of young readers","date":"2021-03-04","arxiv_id":"2103.02899","n_code_links":0,"syntology":null},{"paper":null,"slug":"hardware-acceleration-of-fully-quantized-bert","title":"Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing","date":"2021-03-04","arxiv_id":"2103.02800","n_code_links":0,"syntology":null},{"paper":"/paper/the-transformer-network-for-the-traveling","slug":"the-transformer-network-for-the-traveling","title":"The Transformer Network for the Traveling Salesman Problem","date":"2021-03-04","arxiv_id":"2103.03012","n_code_links":1,"syntology":null},{"paper":"/paper/energy-based-learning-for-scene-graph","slug":"energy-based-learning-for-scene-graph","title":"Energy-Based Learning for Scene Graph Generation","date":"2021-03-03","arxiv_id":"2103.02221","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-learning-for-slot-tagging-with","title":"Few-shot Learning for Slot Tagging with Attentive Relational Network","date":"2021-03-03","arxiv_id":"2103.02333","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-understanding-for","title":"Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain","date":"2021-03-03","arxiv_id":"2103.02691","n_code_links":0,"syntology":null},{"paper":"/paper/random-feature-attention-1","slug":"random-feature-attention-1","title":"Random Feature Attention","date":"2021-03-03","arxiv_id":"2103.02143","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensing-population-distribution-from","title":"Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases","date":"2021-03-03","arxiv_id":"2103.02155","n_code_links":0,"syntology":null},{"paper":null,"slug":"university-of-copenhagen-participation-in","title":"University of Copenhagen Participation in TREC Health Misinformation Track 2020","date":"2021-03-03","arxiv_id":"2103.02462","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-sentiment-analysis-with-bimodal","title":"Video Sentiment Analysis with Bimodal Information-augmented Multi-Head Attention","date":"2021-03-03","arxiv_id":"2103.02362","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hint-from-arithmetic-on-systematic","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","date":"2021-03-02","arxiv_id":"2103.01403","n_code_links":0,"syntology":null},{"paper":null,"slug":"categorical-foundations-of-gradient-based","title":"Categorical Foundations of Gradient-Based Learning","date":"2021-03-02","arxiv_id":"2103.01931","n_code_links":0,"syntology":null},{"paper":null,"slug":"decomposing-lexical-and-compositional-syntax","title":"Disentangling Syntax and Semantics in the Brain with Deep Networks","date":"2021-03-02","arxiv_id":"2103.01620","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-reinforcement-based-specification","title":"Dual Reinforcement-Based Specification Generation for Image De-Rendering","date":"2021-03-02","arxiv_id":"2103.01867","n_code_links":0,"syntology":null}],"record_sha256":"6d9ff4f80619c46cedfe32498c91c3601e7c87a61442eb94adbd1e0eb8392064","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}