{"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/284","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":284,"pages_in_order":375,"rows_per_page":100,"rows":[28301,28400],"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/283","next":"/method/softmax/papers/285","papers":[{"paper":null,"slug":"extracting-feelings-of-people-regarding-covid","title":"Extracting Feelings of People Regarding COVID-19 by Social Network Mining","date":"2021-10-12","arxiv_id":"2110.06151","n_code_links":0,"syntology":null},{"paper":"/paper/hetformer-heterogeneous-transformer-with","slug":"hetformer-heterogeneous-transformer-with","title":"HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization","date":"2021-10-12","arxiv_id":"2110.06388","n_code_links":1,"syntology":null},{"paper":"/paper/lightseq-accelerated-training-for-transformer","slug":"lightseq-accelerated-training-for-transformer","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","date":"2021-10-12","arxiv_id":"2110.05722","n_code_links":1,"syntology":null},{"paper":"/paper/list-lite-self-training-makes-efficient-few-1","slug":"list-lite-self-training-makes-efficient-few-1","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","date":"2021-10-12","arxiv_id":"2110.06274","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":7,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["microsoft/list"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mention-memory-incorporating-textual-1","slug":"mention-memory-incorporating-textual-1","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","date":"2021-10-12","arxiv_id":"2110.06176","n_code_links":1,"syntology":null},{"paper":"/paper/relative-molecule-self-attention-transformer-1","slug":"relative-molecule-self-attention-transformer-1","title":"Relative Molecule Self-Attention Transformer","date":"2021-10-12","arxiv_id":"2110.05841","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":"/paper/rescoring-sequence-to-sequence-models-for","slug":"rescoring-sequence-to-sequence-models-for","title":"Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes","date":"2021-10-12","arxiv_id":"2110.05909","n_code_links":1,"syntology":null},{"paper":"/paper/satellite-image-semantic-segmentation","slug":"satellite-image-semantic-segmentation","title":"Satellite Image Semantic Segmentation","date":"2021-10-12","arxiv_id":"2110.05812","n_code_links":1,"syntology":null},{"paper":"/paper/starformer-transformer-with-state-action-1","slug":"starformer-transformer-with-state-action-1","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","date":"2021-10-12","arxiv_id":"2110.06206","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["elicassion/StARformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/swish-driven-googlenet-for-intelligent-analog","slug":"swish-driven-googlenet-for-intelligent-analog","title":"Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMO","date":"2021-10-12","arxiv_id":"2110.05830","n_code_links":2,"syntology":null},{"paper":"/paper/a-comprehensive-comparison-of-word-embeddings","slug":"a-comprehensive-comparison-of-word-embeddings","title":"A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution","date":"2021-10-11","arxiv_id":"2110.05115","n_code_links":1,"syntology":null},{"paper":"/paper/adaptively-multi-view-and-temporal-fusing","slug":"adaptively-multi-view-and-temporal-fusing","title":"Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation","date":"2021-10-11","arxiv_id":"2110.05092","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-softmax-bottleneck-for","title":"Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling","date":"2021-10-11","arxiv_id":"2110.05409","n_code_links":0,"syntology":null},{"paper":"/paper/certified-patch-robustness-via-smoothed-1","slug":"certified-patch-robustness-via-smoothed-1","title":"Certified Patch Robustness via Smoothed Vision Transformers","date":"2021-10-11","arxiv_id":"2110.07719","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":3,"phrase":"6 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["madrylab/smoothed-vit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"emds-7-environmental-microorganism-image","title":"EMDS-7: Environmental Microorganism Image Dataset Seventh Version for Multiple Object Detection Evaluation","date":"2021-10-11","arxiv_id":"2110.07723","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-gender-fairness-of-pre-trained-1","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","date":"2021-10-11","arxiv_id":"2110.05367","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-transfer-learning-capabilities","slug":"investigating-transfer-learning-capabilities","title":"Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block","date":"2021-10-11","arxiv_id":"2110.05270","n_code_links":1,"syntology":null},{"paper":"/paper/learnable-adaptive-cosine-estimator-lace-for","slug":"learnable-adaptive-cosine-estimator-lace-for","title":"Learnable Adaptive Cosine Estimator (LACE) for Image Classification","date":"2021-10-11","arxiv_id":"2110.05324","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-learning-for-situated-multi-domain","title":"Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems","date":"2021-10-11","arxiv_id":"2110.05221","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-self-attention-based-transformer","title":"Multi-View Self-Attention Based Transformer for Speaker Recognition","date":"2021-10-11","arxiv_id":"2110.05036","n_code_links":0,"syntology":null},{"paper":null,"slug":"offensive-language-detection-with-bert-based","title":"Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities","date":"2021-10-11","arxiv_id":"2110.05133","n_code_links":0,"syntology":null},{"paper":null,"slug":"partial-variable-training-for-efficient-on","title":"Partial Variable Training for Efficient On-Device Federated Learning","date":"2021-10-11","arxiv_id":"2110.05607","n_code_links":0,"syntology":null},{"paper":"/paper/sim2air-synthetic-aerial-dataset-for-uav","slug":"sim2air-synthetic-aerial-dataset-for-uav","title":"Sim2Air - Synthetic aerial dataset for UAV monitoring","date":"2021-10-11","arxiv_id":"2110.05145","n_code_links":1,"syntology":null},{"paper":null,"slug":"sru-pioneering-fast-recurrence-with-attention","title":"SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition","date":"2021-10-11","arxiv_id":"2110.05571","n_code_links":0,"syntology":null},{"paper":"/paper/the-center-of-attention-center-keypoint-1","slug":"the-center-of-attention-center-keypoint-1","title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","date":"2021-10-11","arxiv_id":"2110.05132","n_code_links":1,"syntology":null},{"paper":"/paper/topic-modeling-clade-assisted-sentiment","slug":"topic-modeling-clade-assisted-sentiment","title":"Topic Modeling, Clade-assisted Sentiment Analysis, and Vaccine Brand Reputation Analysis of COVID-19 Vaccine-related Facebook Comments in the Philippines","date":"2021-10-11","arxiv_id":"2111.04416","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-source-separation-via-bayesian","slug":"unsupervised-source-separation-via-bayesian","title":"Unsupervised Source Separation via Bayesian Inference in the Latent Domain","date":"2021-10-11","arxiv_id":"2110.05313","n_code_links":1,"syntology":null},{"paper":null,"slug":"dct-dynamic-compressive-transformer-for","title":"DCT: Dynamic Compressive Transformer for Modeling Unbounded Sequence","date":"2021-10-10","arxiv_id":"2110.04821","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-channel-end-to-end-neural-diarization","title":"Multi-Channel End-to-End Neural Diarization with Distributed Microphones","date":"2021-10-10","arxiv_id":"2110.04694","n_code_links":0,"syntology":null},{"paper":"/paper/nvit-vision-transformer-compression-and-1","slug":"nvit-vision-transformer-compression-and-1","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","date":"2021-10-10","arxiv_id":"2110.04869","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"on-automatic-text-extractive-summarization","title":"Automatic Text Extractive Summarization Based on Graph and Pre-trained Language Model Attention","date":"2021-10-10","arxiv_id":"2110.04878","n_code_links":0,"syntology":null},{"paper":"/paper/paste-a-tagging-free-decoding-framework-using","slug":"paste-a-tagging-free-decoding-framework-using","title":"PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction","date":"2021-10-10","arxiv_id":"2110.04794","n_code_links":1,"syntology":null},{"paper":"/paper/sp-gpt2-semantics-improvement-in-vietnamese","slug":"sp-gpt2-semantics-improvement-in-vietnamese","title":"SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation","date":"2021-10-10","arxiv_id":"2110.15723","n_code_links":2,"syntology":null},{"paper":null,"slug":"supershaper-task-agnostic-super-pre-training","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","date":"2021-10-10","arxiv_id":"2110.04711","n_code_links":0,"syntology":null},{"paper":"/paper/yuan-1-0-large-scale-pre-trained-language","slug":"yuan-1-0-large-scale-pre-trained-language","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","date":"2021-10-10","arxiv_id":"2110.04725","n_code_links":1,"syntology":null},{"paper":"/paper/an-isotropy-analysis-in-the-multilingual-bert","slug":"an-isotropy-analysis-in-the-multilingual-bert","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","date":"2021-10-09","arxiv_id":"2110.04504","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-keyword-spotting-using-xception-1d","slug":"end-to-end-keyword-spotting-using-xception-1d","title":"End-to-end Keyword Spotting using Xception-1d","date":"2021-10-09","arxiv_id":"2110.07498","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-recent-advances-in-pre-trained","slug":"leveraging-recent-advances-in-pre-trained","title":"Leveraging recent advances in Pre-Trained Language Models forEye-Tracking Prediction","date":"2021-10-09","arxiv_id":"2110.04475","n_code_links":1,"syntology":null},{"paper":"/paper/vector-quantized-image-modeling-with-improved-1","slug":"vector-quantized-image-modeling-with-improved-1","title":"Vector-quantized Image Modeling with Improved VQGAN","date":"2021-10-09","arxiv_id":"2110.04627","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/vision-transformer-based-covid-19-detection","slug":"vision-transformer-based-covid-19-detection","title":"Vision Transformer based COVID-19 Detection using Chest X-rays","date":"2021-10-09","arxiv_id":"2110.04458","n_code_links":0,"syntology":null},{"paper":null,"slug":"2110-06794","title":"The Layout Generation Algorithm of Graphic Design Based on Transformer-CVAE","date":"2021-10-08","arxiv_id":"2110.06794","n_code_links":0,"syntology":null},{"paper":"/paper/abcp-automatic-block-wise-and-channel-wise","slug":"abcp-automatic-block-wise-and-channel-wise","title":"ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search","date":"2021-10-08","arxiv_id":"2110.03858","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-token-attacks-on-vision","title":"Adversarial Token Attacks on Vision Transformers","date":"2021-10-08","arxiv_id":"2110.04337","n_code_links":0,"syntology":null},{"paper":null,"slug":"all-in-one-multi-task-learning-bert-models","title":"ALL-IN-ONE: Multi-Task Learning BERT models for Evaluating Peer Assessments","date":"2021-10-08","arxiv_id":"2110.03895","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-lgm-leveraging-object-context","title":"Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition","date":"2021-10-08","arxiv_id":"2110.04042","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-learning-for-source-code-with","title":"Towards Learning (Dis)-Similarity of Source Code from Program Contrasts","date":"2021-10-08","arxiv_id":"2110.03868","n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-face-mask-recognition-with-advanced","title":"COVID-19 Face Mask Recognition with Advanced Face Cut Algorithm for Human Safety Measures","date":"2021-10-08","arxiv_id":"2110.04316","n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-monitoring-system-using-social","title":"COVID-19 Monitoring System using Social Distancing and Face Mask Detection on Surveillance video datasets","date":"2021-10-08","arxiv_id":"2110.03905","n_code_links":0,"syntology":null},{"paper":null,"slug":"development-of-an-extractive-title-generation","title":"Development of an Extractive Title Generation System Using Titles of Papers of Top Conferences for Intermediate English Students","date":"2021-10-08","arxiv_id":"2110.04204","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-generative-networks-using-gaussian-1","title":"Evaluating generative networks using Gaussian mixtures of image features","date":"2021-10-08","arxiv_id":"2110.05240","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-random-features-1","slug":"hybrid-random-features-1","title":"Hybrid Random Features","date":"2021-10-08","arxiv_id":"2110.04367","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":["arijitthegame/hybrid-sampling"],"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":"/paper/hydrasum-disentangling-stylistic-features-in-1","slug":"hydrasum-disentangling-stylistic-features-in-1","title":"HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models","date":"2021-10-08","arxiv_id":"2110.04400","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":3,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["salesforce/hydra-sum"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"kg-fid-infusing-knowledge-graph-in-fusion-in-1","title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","date":"2021-10-08","arxiv_id":"2110.04330","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-enhanced-hierarchical-graph","slug":"knowledge-enhanced-hierarchical-graph","title":"Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation","date":"2021-10-08","arxiv_id":"2110.04000","n_code_links":1,"syntology":null},{"paper":"/paper/learning-a-self-expressive-network-for-1","slug":"learning-a-self-expressive-network-for-1","title":"Learning a Self-Expressive Network for Subspace Clustering","date":"2021-10-08","arxiv_id":"2110.04318","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["zhangsz1998/self-expressive-network"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-adaptive-control-flow-in","title":"Learning Adaptive Control Flow in Transformers for Improved Systematic Generalization","date":"2021-10-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/local-and-global-context-based-pairwise","slug":"local-and-global-context-based-pairwise","title":"Local and Global Context-Based Pairwise Models for Sentence Ordering","date":"2021-10-08","arxiv_id":"2110.04291","n_code_links":1,"syntology":null},{"paper":null,"slug":"m6-10t-a-sharing-delinking-paradigm-for","title":"M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining","date":"2021-10-08","arxiv_id":"2110.03888","n_code_links":0,"syntology":null},{"paper":"/paper/multiplex-behavioral-relation-learning-for","slug":"multiplex-behavioral-relation-learning-for","title":"Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network","date":"2021-10-08","arxiv_id":"2110.04002","n_code_links":1,"syntology":null},{"paper":"/paper/rpt-toward-transferable-model-on","slug":"rpt-toward-transferable-model-on","title":"RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training","date":"2021-10-08","arxiv_id":"2110.07336","n_code_links":1,"syntology":null},{"paper":null,"slug":"speeding-up-deep-model-training-by-sharing","title":"Speeding up Deep Model Training by Sharing Weights and Then Unsharing","date":"2021-10-08","arxiv_id":"2110.03848","n_code_links":0,"syntology":null},{"paper":"/paper/taming-sparsely-activated-transformer-with","slug":"taming-sparsely-activated-transformer-with","title":"Taming Sparsely Activated Transformer with Stochastic Experts","date":"2021-10-08","arxiv_id":"2110.04260","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":["microsoft/stochastic-mixture-of-experts"],"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":"text-analysis-and-deep-learning-a-network","title":"Text analysis and deep learning: A network approach","date":"2021-10-08","arxiv_id":"2110.04151","n_code_links":0,"syntology":null},{"paper":null,"slug":"token-pooling-in-visual-transformers","title":"Token Pooling in Vision Transformers","date":"2021-10-08","arxiv_id":"2110.03860","n_code_links":0,"syntology":null},{"paper":"/paper/vidt-an-efficient-and-effective-fully","slug":"vidt-an-efficient-and-effective-fully","title":"ViDT: An Efficient and Effective Fully Transformer-based Object Detector","date":"2021-10-08","arxiv_id":"2110.03921","n_code_links":1,"syntology":null},{"paper":null,"slug":"5g-traffic-prediction-with-time-series","title":"5G Traffic Prediction with Time Series Analysis","date":"2021-10-07","arxiv_id":"2110.03781","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformer-based","title":"A Comparative Study of Transformer-Based Language Models on Extractive Question Answering","date":"2021-10-07","arxiv_id":"2110.03142","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-is-all-you-need-good-embeddings","title":"Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....","date":"2021-10-07","arxiv_id":"2110.03183","n_code_links":0,"syntology":null},{"paper":"/paper/cross-language-learning-for-entity-matching","slug":"cross-language-learning-for-entity-matching","title":"Cross-Language Learning for Entity Matching","date":"2021-10-07","arxiv_id":"2110.03338","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-supermask-pruning-learning-to","slug":"end-to-end-supermask-pruning-learning-to","title":"End-to-End Supermask Pruning: Learning to Prune Image Captioning Models","date":"2021-10-07","arxiv_id":"2110.03298","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jiahuei/sparse-image-captioning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-pre-trained-transformer-for","title":"Generative Pre-Trained Transformer for Cardiac Abnormality Detection","date":"2021-10-07","arxiv_id":"2110.04071","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-confidence-estimation-on-out-of","title":"Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition","date":"2021-10-07","arxiv_id":"2110.03327","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-growth-at-risk-using-a-multi","title":"Investigating Growth at Risk Using a Multi-country Non-parametric Quantile Factor Model","date":"2021-10-07","arxiv_id":"2110.03411","n_code_links":0,"syntology":null},{"paper":"/paper/layer-wise-pruning-of-transformer-attention","slug":"layer-wise-pruning-of-transformer-attention","title":"Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling","date":"2021-10-07","arxiv_id":"2110.03252","n_code_links":1,"syntology":null},{"paper":null,"slug":"minimum-word-error-training-for-non","title":"Minimum word error training for non-autoregressive Transformer-based code-switching ASR","date":"2021-10-07","arxiv_id":"2110.03573","n_code_links":0,"syntology":null},{"paper":null,"slug":"universality-of-deep-neural-network-lottery","title":"Universality of Winning Tickets: A Renormalization Group Perspective","date":"2021-10-07","arxiv_id":"2110.03210","n_code_links":0,"syntology":null},{"paper":"/paper/8-bit-optimizers-via-block-wise-quantization","slug":"8-bit-optimizers-via-block-wise-quantization","title":"8-bit Optimizers via Block-wise Quantization","date":"2021-10-06","arxiv_id":"2110.02861","n_code_links":3,"syntology":null},{"paper":"/paper/adversarial-robustness-comparison-of-vision","slug":"adversarial-robustness-comparison-of-vision","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","date":"2021-10-06","arxiv_id":"2110.02797","n_code_links":1,"syntology":null},{"paper":"/paper/anomaly-transformer-time-series-anomaly","slug":"anomaly-transformer-time-series-anomaly","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","date":"2021-10-06","arxiv_id":"2110.02642","n_code_links":3,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thuml/Anomaly-Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/cbp-backpropagation-with-constraint-on-weight","slug":"cbp-backpropagation-with-constraint-on-weight","title":"CBP: Backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method","date":"2021-10-06","arxiv_id":"2110.02550","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["dooseokjeong/cbp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamically-decoding-source-domain-knowledge","title":"Dynamically Decoding Source Domain Knowledge for Domain Generalization","date":"2021-10-06","arxiv_id":"2110.03027","n_code_links":0,"syntology":null},{"paper":"/paper/geometric-transformers-for-protein-interface","slug":"geometric-transformers-for-protein-interface","title":"Geometric Transformers for Protein Interface Contact Prediction","date":"2021-10-06","arxiv_id":"2110.02423","n_code_links":2,"syntology":null},{"paper":"/paper/hire-snn-harnessing-the-inherent-robustness-1","slug":"hire-snn-harnessing-the-inherent-robustness-1","title":"HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise","date":"2021-10-06","arxiv_id":"2110.11417","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["ksouvik52/hiresnn2021"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"how-bpe-affects-memorization-in-transformers","title":"How BPE Affects Memorization in Transformers","date":"2021-10-06","arxiv_id":"2110.02782","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-pointer-networks-for-traveling","slug":"hybrid-pointer-networks-for-traveling","title":"Hybrid Pointer Networks for Traveling Salesman Problems Optimization","date":"2021-10-06","arxiv_id":"2110.03104","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-iteratively-solve-routing","slug":"learning-to-iteratively-solve-routing","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","date":"2021-10-06","arxiv_id":"2110.02544","n_code_links":2,"syntology":{"ran":9,"of":16,"n_ran_checked":9,"n_instrument":0,"unverified":7,"pointer_only":0,"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) · 7 unverified","official":{"repos":["yining043/VRP-DACT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/lidsnet-a-lightweight-on-device-intent","slug":"lidsnet-a-lightweight-on-device-intent","title":"LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network","date":"2021-10-06","arxiv_id":"2110.15717","n_code_links":0,"syntology":null},{"paper":"/paper/nus-ids-at-fincausal-2021-dependency-tree-in","slug":"nus-ids-at-fincausal-2021-dependency-tree-in","title":"NUS-IDS at FinCausal 2021: Dependency Tree in Graph Neural Network for Better Cause-Effect Span Detection","date":"2021-10-06","arxiv_id":"2110.02991","n_code_links":1,"syntology":null},{"paper":"/paper/on-neurons-invariant-to-sentence-structural","slug":"on-neurons-invariant-to-sentence-structural","title":"On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation","date":"2021-10-06","arxiv_id":"2110.03067","n_code_links":1,"syntology":null},{"paper":"/paper/ponet-pooling-network-for-efficient-token","slug":"ponet-pooling-network-for-efficient-token","title":"PoNet: Pooling Network for Efficient Token Mixing in Long Sequences","date":"2021-10-06","arxiv_id":"2110.02442","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lxchtan/ponet"],"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":"post-hoc-models-for-performance-estimation-of","title":"Post-hoc Models for Performance Estimation of Machine Learning Inference","date":"2021-10-06","arxiv_id":"2110.02459","n_code_links":0,"syntology":null},{"paper":"/paper/psg-hasoc-dravidian-codemixfire2021","slug":"psg-hasoc-dravidian-codemixfire2021","title":"Pretrained Transformers for Offensive Language Identification in Tanglish","date":"2021-10-06","arxiv_id":"2110.02852","n_code_links":1,"syntology":null},{"paper":null,"slug":"seed-classification-using-synthetic-image","title":"Seed Classification using Synthetic Image Datasets Generated from Low-Altitude UAV Imagery","date":"2021-10-06","arxiv_id":"2110.02846","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-prediction-which-one-should-come","slug":"semantic-prediction-which-one-should-come","title":"Semantic Prediction: Which One Should Come First, Recognition or Prediction?","date":"2021-10-06","arxiv_id":"2110.02829","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-the-impact-of-covid-19-on-economy","title":"Analyzing the Impact of COVID-19 on Economy from the Perspective of Users Reviews","date":"2021-10-05","arxiv_id":"2110.02198","n_code_links":0,"syntology":null},{"paper":"/paper/anchor-free-oriented-proposal-generator-for","slug":"anchor-free-oriented-proposal-generator-for","title":"Anchor-free Oriented Proposal Generator for Object Detection","date":"2021-10-05","arxiv_id":"2110.01931","n_code_links":1,"syntology":null},{"paper":null,"slug":"asr-rescoring-and-confidence-estimation-with","title":"ASR Rescoring and Confidence Estimation with ELECTRA","date":"2021-10-05","arxiv_id":"2110.01857","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-subspace-analysing-for-semi-supervised","title":"Deep Subspace analysing for Semi-Supervised multi-label classification of Diabetic Foot Ulcer","date":"2021-10-05","arxiv_id":"2110.01795","n_code_links":0,"syntology":null},{"paper":"/paper/disambiguation-bert-for-n-best-rescoring-in","slug":"disambiguation-bert-for-n-best-rescoring-in","title":"BERT Attends the Conversation: Improving Low-Resource Conversational ASR","date":"2021-10-05","arxiv_id":"2110.02267","n_code_links":1,"syntology":null},{"paper":"/paper/distilhubert-speech-representation-learning","slug":"distilhubert-speech-representation-learning","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","date":"2021-10-05","arxiv_id":"2110.01900","n_code_links":1,"syntology":null}],"record_sha256":"27f373fd253a880ef941e3c15e874a38bfca9573a92f28e360a07f1ff5754672","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}