{"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/245","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":245,"pages_in_order":375,"rows_per_page":100,"rows":[24401,24500],"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/244","next":"/method/softmax/papers/246","papers":[{"paper":null,"slug":"murag-multimodal-retrieval-augmented","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","date":"2022-10-06","arxiv_id":"2210.02928","n_code_links":0,"syntology":null},{"paper":"/paper/rainier-reinforced-knowledge-introspector-for","slug":"rainier-reinforced-knowledge-introspector-for","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","date":"2022-10-06","arxiv_id":"2210.03078","n_code_links":1,"syntology":{"ran":7,"of":13,"n_ran_checked":4,"n_instrument":3,"unverified":6,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["liujch1998/rainier"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/real-world-robot-learning-with-masked-visual","slug":"real-world-robot-learning-with-masked-visual","title":"Real-World Robot Learning with Masked Visual Pre-training","date":"2022-10-06","arxiv_id":"2210.03109","n_code_links":1,"syntology":null},{"paper":"/paper/structure-representation-network-and","slug":"structure-representation-network-and","title":"Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal","date":"2022-10-06","arxiv_id":"2210.03061","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["jinyeying/fogremoval"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"synbench-task-agnostic-benchmarking-of","title":"SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data","date":"2022-10-06","arxiv_id":"2210.02989","n_code_links":0,"syntology":null},{"paper":"/paper/to-softmax-or-not-to-softmax-that-is-the","slug":"to-softmax-or-not-to-softmax-that-is-the","title":"To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer Models","date":"2022-10-06","arxiv_id":"2210.03005","n_code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-based-model-for-describing","slug":"vision-transformer-based-model-for-describing","title":"Vision Transformer Based Model for Describing a Set of Images as a Story","date":"2022-10-06","arxiv_id":"2210.02762","n_code_links":0,"syntology":null},{"paper":"/paper/vlsnr-vision-linguistics-coordination-time","slug":"vlsnr-vision-linguistics-coordination-time","title":"VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation","date":"2022-10-06","arxiv_id":"2210.02946","n_code_links":2,"syntology":null},{"paper":null,"slug":"when-not-to-use-machine-learning-a","title":"When not to use machine learning: a perspective on potential and limitations","date":"2022-10-06","arxiv_id":"2210.02666","n_code_links":0,"syntology":null},{"paper":"/paper/xdoc-unified-pre-training-for-cross-format","slug":"xdoc-unified-pre-training-for-cross-format","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","date":"2022-10-06","arxiv_id":"2210.02849","n_code_links":1,"syntology":null},{"paper":"/paper/centralized-feature-pyramid-for-object","slug":"centralized-feature-pyramid-for-object","title":"Centralized Feature Pyramid for Object Detection","date":"2022-10-05","arxiv_id":"2210.02093","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 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) · 1 unverified","official":{"repos":["qy1994-0919/cfpnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-the-role-of-mean-teachers-in-self","slug":"exploring-the-role-of-mean-teachers-in-self","title":"Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders","date":"2022-10-05","arxiv_id":"2210.02077","n_code_links":1,"syntology":null},{"paper":"/paper/fqdet-fast-converging-query-based-detector","slug":"fqdet-fast-converging-query-based-detector","title":"FQDet: Fast-converging Query-based Detector","date":"2022-10-05","arxiv_id":"2210.02318","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"pointer_only":3,"phrase":"3 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cedricpicron/fqdet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","n_code_links":9,"syntology":{"ran":15,"of":21,"n_ran_checked":14,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/interface-adjustable-angular-margin-inter","slug":"interface-adjustable-angular-margin-inter","title":"InterFace:Adjustable Angular Margin Inter-class Loss for Deep Face Recognition","date":"2022-10-05","arxiv_id":"2210.02018","n_code_links":1,"syntology":null},{"paper":"/paper/medical-image-retrieval-via-nearest-neighbor","slug":"medical-image-retrieval-via-nearest-neighbor","title":"Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features","date":"2022-10-05","arxiv_id":"2210.02401","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-preserving-text-classification-on-1","title":"Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption","date":"2022-10-05","arxiv_id":"2210.02574","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-structured-dropout","title":"Revisiting Structured Dropout","date":"2022-10-05","arxiv_id":"2210.02570","n_code_links":0,"syntology":null},{"paper":null,"slug":"tc-sknet-with-gridmask-for-low-complexity","title":"TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene","date":"2022-10-05","arxiv_id":"2210.02287","n_code_links":0,"syntology":null},{"paper":"/paper/temporally-consistent-video-transformer-for","slug":"temporally-consistent-video-transformer-for","title":"Temporally Consistent Transformers for Video Generation","date":"2022-10-05","arxiv_id":"2210.02396","n_code_links":2,"syntology":null},{"paper":null,"slug":"tgdlf2-0-theory-guided-deep-learning-for","title":"TgDLF2.0: Theory-guided deep-learning for electrical load forecasting via Transformer and transfer learning","date":"2022-10-05","arxiv_id":"2210.02448","n_code_links":0,"syntology":null},{"paper":"/paper/waveformer-linear-time-attention-with-forward","slug":"waveformer-linear-time-attention-with-forward","title":"WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability","date":"2022-10-05","arxiv_id":"2210.01989","n_code_links":1,"syntology":null},{"paper":"/paper/a-perceptual-quality-metric-for-video-frame","slug":"a-perceptual-quality-metric-for-video-frame","title":"A Perceptual Quality Metric for Video Frame Interpolation","date":"2022-10-04","arxiv_id":"2210.01879","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":["hqqxyy/vfips"],"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":"/paper/accurate-image-restoration-with-attention","slug":"accurate-image-restoration-with-attention","title":"Accurate Image Restoration with Attention Retractable Transformer","date":"2022-10-04","arxiv_id":"2210.01427","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["gladzhang/art"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/bridged-transformer-for-vision-and-point-1","slug":"bridged-transformer-for-vision-and-point-1","title":"Bridged Transformer for Vision and Point Cloud 3D Object Detection","date":"2022-10-04","arxiv_id":"2210.01391","n_code_links":2,"syntology":null},{"paper":"/paper/data-leakage-in-tabular-federated-learning","slug":"data-leakage-in-tabular-federated-learning","title":"TabLeak: Tabular Data Leakage in Federated Learning","date":"2022-10-04","arxiv_id":"2210.01785","n_code_links":1,"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":["eth-sri/tableak"],"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"]}}},{"paper":"/paper/explaining-patterns-in-data-with-language","slug":"explaining-patterns-in-data-with-language","title":"Explaining Patterns in Data with Language Models via Interpretable Autoprompting","date":"2022-10-04","arxiv_id":"2210.01848","n_code_links":2,"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":["csinva/imodelsX"],"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":"immfusion-robust-mmwave-rgb-fusion-for-3d","title":"ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions","date":"2022-10-04","arxiv_id":"2210.01346","n_code_links":0,"syntology":null},{"paper":"/paper/improving-label-deficient-keyword-spotting","slug":"improving-label-deficient-keyword-spotting","title":"Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining","date":"2022-10-04","arxiv_id":"2210.01703","n_code_links":2,"syntology":null},{"paper":"/paper/k-means-for-unsupervised-instance","slug":"k-means-for-unsupervised-instance","title":"K-means for unsupervised instance segmentation using a self-supervised transformer","date":"2022-10-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-signal-temporal-logic-through-neural","slug":"learning-signal-temporal-logic-through-neural","title":"Learning Signal Temporal Logic through Neural Network for Interpretable Classification","date":"2022-10-04","arxiv_id":"2210.01910","n_code_links":1,"syntology":null},{"paper":null,"slug":"memory-in-humans-and-deep-language-models","title":"Memory in humans and deep language models: Linking hypotheses for model augmentation","date":"2022-10-04","arxiv_id":"2210.01869","n_code_links":0,"syntology":null},{"paper":"/paper/moat-alternating-mobile-convolution-and","slug":"moat-alternating-mobile-convolution-and","title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","date":"2022-10-04","arxiv_id":"2210.01820","n_code_links":2,"syntology":null},{"paper":null,"slug":"mtsmae-masked-autoencoders-for-multivariate","title":"MTSMAE: Masked Autoencoders for Multivariate Time-Series Forecasting","date":"2022-10-04","arxiv_id":"2210.02199","n_code_links":0,"syntology":null},{"paper":"/paper/one-transformer-can-understand-both-2d-3d","slug":"one-transformer-can-understand-both-2d-3d","title":"One Transformer Can Understand Both 2D & 3D Molecular Data","date":"2022-10-04","arxiv_id":"2210.01765","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":{"repos":["lsj2408/Transformer-M"],"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"]}}},{"paper":null,"slug":"a-strong-transfer-baseline-for-rgb-d-fusion","title":"Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition","date":"2022-10-03","arxiv_id":"2210.00843","n_code_links":0,"syntology":null},{"paper":null,"slug":"characterization-of-effects-of-transfer","title":"The (In)Effectiveness of Intermediate Task Training For Domain Adaptation and Cross-Lingual Transfer Learning","date":"2022-10-03","arxiv_id":"2210.01091","n_code_links":0,"syntology":null},{"paper":null,"slug":"complexity-based-prompting-for-multi-step","title":"Complexity-Based Prompting for Multi-Step Reasoning","date":"2022-10-03","arxiv_id":"2210.00720","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-former-hybrid-self-attention-transformer","title":"Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration","date":"2022-10-03","arxiv_id":"2210.01069","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-spiking-transformer-enabled-by","slug":"efficient-spiking-transformer-enabled-by","title":"Masked Spiking Transformer","date":"2022-10-03","arxiv_id":"2210.01208","n_code_links":1,"syntology":null},{"paper":"/paper/fine-grained-object-categorization-for","slug":"fine-grained-object-categorization-for","title":"Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models","date":"2022-10-03","arxiv_id":"2210.04613","n_code_links":1,"syntology":null},{"paper":"/paper/fully-transformer-network-for-change","slug":"fully-transformer-network-for-change","title":"Fully Transformer Network for Change Detection of Remote Sensing Images","date":"2022-10-03","arxiv_id":"2210.00757","n_code_links":1,"syntology":null},{"paper":null,"slug":"introducing-vision-transformer-for-alzheimer","title":"Introducing Vision Transformer for Alzheimer's Disease classification task with 3D input","date":"2022-10-03","arxiv_id":"2210.01177","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-greedy-reasoners-a","slug":"language-models-are-greedy-reasoners-a","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","date":"2022-10-03","arxiv_id":"2210.01240","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["asaparov/prontoqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"probing-of-quantitative-values-in-abstractive","title":"Probing of Quantitative Values in Abstractive Summarization Models","date":"2022-10-03","arxiv_id":"2210.00667","n_code_links":0,"syntology":null},{"paper":"/paper/smooth-image-to-image-translations-with","slug":"smooth-image-to-image-translations-with","title":"Smooth image-to-image translations with latent space interpolations","date":"2022-10-03","arxiv_id":"2210.00841","n_code_links":1,"syntology":null},{"paper":"/paper/the-effectiveness-of-masked-language-modeling","slug":"the-effectiveness-of-masked-language-modeling","title":"The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection","date":"2022-10-03","arxiv_id":"2210.00907","n_code_links":1,"syntology":null},{"paper":null,"slug":"wavefit-an-iterative-and-non-autoregressive","title":"WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration","date":"2022-10-03","arxiv_id":"2210.01029","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-audio-visual-masked-autoencoder","slug":"contrastive-audio-visual-masked-autoencoder","title":"Contrastive Audio-Visual Masked Autoencoder","date":"2022-10-02","arxiv_id":"2210.07839","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["yuangongnd/cav-mae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"dartformer-finding-the-best-type-of-attention","title":"DARTFormer: Finding The Best Type Of Attention","date":"2022-10-02","arxiv_id":"2210.00641","n_code_links":0,"syntology":null},{"paper":"/paper/deep-octa-ensemble-deep-learning-approaches","slug":"deep-octa-ensemble-deep-learning-approaches","title":"Deep-OCTA: Ensemble Deep Learning Approaches for Diabetic Retinopathy Analysis on OCTA Images","date":"2022-10-02","arxiv_id":"2210.00515","n_code_links":1,"syntology":null},{"paper":"/paper/intrinsicnerf-learning-intrinsic-neural","slug":"intrinsicnerf-learning-intrinsic-neural","title":"IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis","date":"2022-10-02","arxiv_id":"2210.00647","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":0,"n_instrument":3,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["zju3dv/intrinsicnerf"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"seeing-through-the-noisy-dark-toward-real","title":"Seeing Through the Noisy Dark: Towards Real-world Low-Light Image Enhancement and Denoising","date":"2022-10-02","arxiv_id":"2210.00545","n_code_links":0,"syntology":null},{"paper":"/paper/siamese-nas-using-trained-samples-efficiently","slug":"siamese-nas-using-trained-samples-efficiently","title":"Siamese-NAS: Using Trained Samples Efficiently to Find Lightweight Neural Architecture by Prior Knowledge","date":"2022-10-02","arxiv_id":"2210.00546","n_code_links":1,"syntology":null},{"paper":null,"slug":"wide-attention-is-the-way-forward-for","title":"Wide Attention Is The Way Forward For Transformers?","date":"2022-10-02","arxiv_id":"2210.00640","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparison-of-transformer-convolutional-and","title":"A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition","date":"2022-10-01","arxiv_id":"2210.00367","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-ensemble-of-convolutional-neural-networks-1","title":"An Ensemble of Convolutional Neural Networks to Detect Foliar Diseases in Apple Plants","date":"2022-10-01","arxiv_id":"2210.00298","n_code_links":0,"syntology":null},{"paper":null,"slug":"cascaded-multi-modal-mixing-transformers-for","title":"Cascaded Multi-Modal Mixing Transformers for Alzheimer's Disease Classification with Incomplete Data","date":"2022-10-01","arxiv_id":"2210.00255","n_code_links":0,"syntology":null},{"paper":null,"slug":"construction-and-evaluation-of-a-self","title":"Construction and Evaluation of a Self-Attention Model for Semantic Understanding of Sentence-Final Particles","date":"2022-10-01","arxiv_id":"2210.00282","n_code_links":0,"syntology":null},{"paper":null,"slug":"eapruning-evolutionary-pruning-for-vision","title":"EAPruning: Evolutionary Pruning for Vision Transformers and CNNs","date":"2022-10-01","arxiv_id":"2210.00181","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-analogical-reasoning-over","slug":"multimodal-analogical-reasoning-over","title":"Multimodal Analogical Reasoning over Knowledge Graphs","date":"2022-10-01","arxiv_id":"2210.00312","n_code_links":2,"syntology":{"ran":17,"of":27,"n_ran_checked":14,"n_instrument":3,"unverified":10,"pointer_only":2,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["zjunlp/MKG_Analogy"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/promptkg-a-prompt-learning-framework-for","slug":"promptkg-a-prompt-learning-framework-for","title":"LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings","date":"2022-10-01","arxiv_id":"2210.00305","n_code_links":2,"syntology":null},{"paper":null,"slug":"adaptive-sparse-and-monotonic-attention-for","title":"Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition","date":"2022-09-30","arxiv_id":"2209.15176","n_code_links":0,"syntology":null},{"paper":"/paper/diffusion-based-image-translation-using","slug":"diffusion-based-image-translation-using","title":"Diffusion-based Image Translation using Disentangled Style and Content Representation","date":"2022-09-30","arxiv_id":"2209.15264","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["anon294384/diffuseit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/dual-progressive-transformations-for-weakly","slug":"dual-progressive-transformations-for-weakly","title":"Dual Progressive Transformations for Weakly Supervised Semantic Segmentation","date":"2022-09-30","arxiv_id":"2209.15211","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-backbone-protein-ligand-structure","slug":"dynamic-backbone-protein-ligand-structure","title":"State-specific protein-ligand complex structure prediction with a multi-scale deep generative model","date":"2022-09-30","arxiv_id":"2209.15171","n_code_links":2,"syntology":null},{"paper":"/paper/exploiting-selection-bias-on-underspecified","slug":"exploiting-selection-bias-on-underspecified","title":"Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution","date":"2022-09-30","arxiv_id":"2210.00131","n_code_links":2,"syntology":null},{"paper":null,"slug":"impact-of-face-image-quality-estimation-on","title":"Impact of Face Image Quality Estimation on Presentation Attack Detection","date":"2022-09-30","arxiv_id":"2209.15489","n_code_links":0,"syntology":null},{"paper":"/paper/improving-local-features-with-relevant","slug":"improving-local-features-with-relevant","title":"Improving Local Features with Relevant Spatial Information by Vision Transformer for Crowd Counting","date":"2022-09-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"linear-convergence-for-natural-policy","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization","date":"2022-09-30","arxiv_id":"2209.15382","n_code_links":0,"syntology":null},{"paper":"/paper/metro-memory-enhanced-transformer-for","slug":"metro-memory-enhanced-transformer-for","title":"FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning","date":"2022-09-30","arxiv_id":"2209.15315","n_code_links":1,"syntology":{"ran":5,"of":16,"n_ran_checked":3,"n_instrument":2,"unverified":11,"pointer_only":16,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","official":{"repos":["songtaoliu0823/fusionretro"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobilevitv3-mobile-friendly-vision","slug":"mobilevitv3-mobile-friendly-vision","title":"MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features","date":"2022-09-30","arxiv_id":"2209.15159","n_code_links":2,"syntology":null},{"paper":"/paper/part-pre-trained-authorship-representation","slug":"part-pre-trained-authorship-representation","title":"PART: Pre-trained Authorship Representation Transformer","date":"2022-09-30","arxiv_id":"2209.15373","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-distillation-for-further-pre-training-of","title":"Self-Distillation for Further Pre-training of Transformers","date":"2022-09-30","arxiv_id":"2210.02871","n_code_links":0,"syntology":null},{"paper":"/paper/smallcap-lightweight-image-captioning","slug":"smallcap-lightweight-image-captioning","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","date":"2022-09-30","arxiv_id":"2209.15323","n_code_links":1,"syntology":null},{"paper":"/paper/speechlm-enhanced-speech-pre-training-with","slug":"speechlm-enhanced-speech-pre-training-with","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","date":"2022-09-30","arxiv_id":"2209.15329","n_code_links":1,"syntology":null},{"paper":"/paper/visuo-tactile-transformers-for-manipulation","slug":"visuo-tactile-transformers-for-manipulation","title":"Visuo-Tactile Transformers for Manipulation","date":"2022-09-30","arxiv_id":"2210.00121","n_code_links":1,"syntology":null},{"paper":null,"slug":"where-should-i-spend-my-flops-efficiency","title":"Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods","date":"2022-09-30","arxiv_id":"2209.15589","n_code_links":0,"syntology":null},{"paper":"/paper/3d-ux-net-a-large-kernel-volumetric-convnet","slug":"3d-ux-net-a-large-kernel-volumetric-convnet","title":"3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation","date":"2022-09-29","arxiv_id":"2209.15076","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["masilab/3dux-net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"bidirectional-language-models-are-also-few","title":"Bidirectional Language Models Are Also Few-shot Learners","date":"2022-09-29","arxiv_id":"2209.14500","n_code_links":0,"syntology":null},{"paper":"/paper/continuous-pde-dynamics-forecasting-with","slug":"continuous-pde-dynamics-forecasting-with","title":"Continuous PDE Dynamics Forecasting with Implicit Neural Representations","date":"2022-09-29","arxiv_id":"2209.14855","n_code_links":1,"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":["mkirchmeyer/DINo"],"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":"convrnn-t-convolutional-augmented-recurrent","title":"ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition","date":"2022-09-29","arxiv_id":"2209.14868","n_code_links":0,"syntology":null},{"paper":"/paper/digress-discrete-denoising-diffusion-for","slug":"digress-discrete-denoising-diffusion-for","title":"DiGress: Discrete Denoising diffusion for graph generation","date":"2022-09-29","arxiv_id":"2209.14734","n_code_links":3,"syntology":{"ran":15,"of":25,"n_ran_checked":10,"n_instrument":5,"unverified":10,"pointer_only":0,"phrase":"15 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":{"repos":["cvignac/digress"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed"]}}},{"paper":"/paper/dynamic-prompt-learning-via-policy-gradient","slug":"dynamic-prompt-learning-via-policy-gradient","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","date":"2022-09-29","arxiv_id":"2209.14610","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":null}},{"paper":"/paper/spikformer-when-spiking-neural-network-meets","slug":"spikformer-when-spiking-neural-network-meets","title":"Spikformer: When Spiking Neural Network Meets Transformer","date":"2022-09-29","arxiv_id":"2209.15425","n_code_links":2,"syntology":null},{"paper":"/paper/360fusionnerf-panoramic-neural-radiance","slug":"360fusionnerf-panoramic-neural-radiance","title":"360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidance","date":"2022-09-28","arxiv_id":"2209.14265","n_code_links":1,"syntology":null},{"paper":"/paper/attacking-compressed-vision-transformers","slug":"attacking-compressed-vision-transformers","title":"Attacking Compressed Vision Transformers","date":"2022-09-28","arxiv_id":"2209.13785","n_code_links":1,"syntology":null},{"paper":null,"slug":"cefer-a-four-facets-framework-based-on","title":"CEFER: A Four Facets Framework based on Context and Emotion embedded features for Implicit and Explicit Emotion Recognition","date":"2022-09-28","arxiv_id":"2209.13999","n_code_links":0,"syntology":null},{"paper":"/paper/downstream-datasets-make-surprisingly-good","slug":"downstream-datasets-make-surprisingly-good","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","date":"2022-09-28","arxiv_id":"2209.14389","n_code_links":1,"syntology":null},{"paper":null,"slug":"effective-general-domain-data-inclusion-for","title":"Effective General-Domain Data Inclusion for the Machine Translation Task by Vanilla Transformers","date":"2022-09-28","arxiv_id":"2209.14073","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-relationship-between-2","title":"Exploring the Relationship between Architecture and Adversarially Robust Generalization","date":"2022-09-28","arxiv_id":"2209.14105","n_code_links":0,"syntology":null},{"paper":null,"slug":"keyword-extraction-from-short-texts-with-a","title":"Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer","date":"2022-09-28","arxiv_id":"2209.14008","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-image-captioning-via-generative","title":"Medical Image Captioning via Generative Pretrained Transformers","date":"2022-09-28","arxiv_id":"2209.13983","n_code_links":0,"syntology":null},{"paper":"/paper/mtu-net-multi-level-transunet-for-space-based","slug":"mtu-net-multi-level-transunet-for-space-based","title":"MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection","date":"2022-09-28","arxiv_id":"2209.13756","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-prediction-of-spontaneous-humour-a","slug":"multimodal-prediction-of-spontaneous-humour-a","title":"Towards Multimodal Prediction of Spontaneous Humour: A Novel Dataset and First Results","date":"2022-09-28","arxiv_id":"2209.14272","n_code_links":2,"syntology":null},{"paper":null,"slug":"supervised-contrastive-learning-as-multi","title":"Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models","date":"2022-09-28","arxiv_id":"2209.14161","n_code_links":0,"syntology":null},{"paper":"/paper/tvlt-textless-vision-language-transformer","slug":"tvlt-textless-vision-language-transformer","title":"TVLT: Textless Vision-Language Transformer","date":"2022-09-28","arxiv_id":"2209.14156","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 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) · 1 unverified","official":{"repos":["zinengtang/tvlt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/unest-local-spatial-representation-learning","slug":"unest-local-spatial-representation-learning","title":"UNesT: Local Spatial Representation Learning with Hierarchical Transformer for Efficient Medical Segmentation","date":"2022-09-28","arxiv_id":"2209.14378","n_code_links":1,"syntology":null},{"paper":"/paper/who-is-gpt-3-an-exploration-of-personality","slug":"who-is-gpt-3-an-exploration-of-personality","title":"Who is GPT-3? An Exploration of Personality, Values and Demographics","date":"2022-09-28","arxiv_id":"2209.14338","n_code_links":1,"syntology":null},{"paper":"/paper/yato-yet-another-deep-learning-based-text","slug":"yato-yet-another-deep-learning-based-text","title":"YATO: Yet Another deep learning based Text analysis Open toolkit","date":"2022-09-28","arxiv_id":"2209.13877","n_code_links":1,"syntology":null}],"record_sha256":"9f0dfee4efd985bddf4d77c8f70ecc2d82c849d86ab5eaff18bc81abea582445","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}