{"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/259","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":259,"pages_in_order":375,"rows_per_page":100,"rows":[25801,25900],"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/258","next":"/method/softmax/papers/260","papers":[{"paper":null,"slug":"visualizing-coatnet-predictions-for-aiding","title":"Visualizing CoAtNet Predictions for Aiding Melanoma Detection","date":"2022-05-21","arxiv_id":"2205.10515","n_code_links":0,"syntology":null},{"paper":"/paper/a-correlation-information-based","slug":"a-correlation-information-based","title":"A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting","date":"2022-05-20","arxiv_id":"2205.10365","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-demographic-attribute-guided-approach-to","title":"A Demographic Attribute Guided Approach to Age Estimation","date":"2022-05-20","arxiv_id":"2205.10254","n_code_links":0,"syntology":null},{"paper":"/paper/cross-reconstruction-transformer-for-self","slug":"cross-reconstruction-transformer-for-self","title":"Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer","date":"2022-05-20","arxiv_id":"2205.09928","n_code_links":1,"syntology":null},{"paper":null,"slug":"current-trends-and-approaches-in-synonyms","title":"Current Trends and Approaches in Synonyms Extraction: Potential Adaptation to Arabic","date":"2022-05-20","arxiv_id":"2205.10412","n_code_links":0,"syntology":null},{"paper":"/paper/degradation-aware-unfolding-half-shuffle","slug":"degradation-aware-unfolding-half-shuffle","title":"Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging","date":"2022-05-20","arxiv_id":"2205.10102","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":1,"n_instrument":3,"unverified":4,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["caiyuanhao1998/MST"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-extreme-parameter-compression-for-1","slug":"exploring-extreme-parameter-compression-for-1","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","date":"2022-05-20","arxiv_id":"2205.10036","n_code_links":1,"syntology":null},{"paper":"/paper/kernel-normalized-convolutional-networks","slug":"kernel-normalized-convolutional-networks","title":"Kernel Normalized Convolutional Networks","date":"2022-05-20","arxiv_id":"2205.10089","n_code_links":1,"syntology":null},{"paper":"/paper/kerple-kernelized-relative-positional","slug":"kerple-kernelized-relative-positional","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","date":"2022-05-20","arxiv_id":"2205.09921","n_code_links":2,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 0 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) · 3 unverified","official":{"repos":["chijames/kerple","eleutherai/gpt-neox"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-count-anything-reference-less","slug":"learning-to-count-anything-reference-less","title":"Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision","date":"2022-05-20","arxiv_id":"2205.10203","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":2,"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) · 2 unverified","official":{"repos":["activevisionlab/learningtocountanything"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/lossless-acceleration-for-seq2seq-generation","slug":"lossless-acceleration-for-seq2seq-generation","title":"Lossless Acceleration for Seq2seq Generation with Aggressive Decoding","date":"2022-05-20","arxiv_id":"2205.10350","n_code_links":2,"syntology":null},{"paper":null,"slug":"mask-guided-vision-transformer-mg-vit-for-few","title":"Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning","date":"2022-05-20","arxiv_id":"2205.09995","n_code_links":0,"syntology":null},{"paper":null,"slug":"mstriq-no-reference-image-quality-assessment","title":"MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion","date":"2022-05-20","arxiv_id":"2205.10101","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","n_code_links":0,"syntology":null},{"paper":"/paper/progressive-class-semantic-matching-for-semi-1","slug":"progressive-class-semantic-matching-for-semi-1","title":"Progressive Class Semantic Matching for Semi-supervised Text Classification","date":"2022-05-20","arxiv_id":"2205.10189","n_code_links":1,"syntology":null},{"paper":"/paper/prototypical-calibration-for-few-shot","slug":"prototypical-calibration-for-few-shot","title":"Prototypical Calibration for Few-shot Learning of Language Models","date":"2022-05-20","arxiv_id":"2205.10183","n_code_links":1,"syntology":null},{"paper":"/paper/temporally-precise-action-spotting-in-soccer","slug":"temporally-precise-action-spotting-in-soccer","title":"Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors","date":"2022-05-20","arxiv_id":"2205.10450","n_code_links":1,"syntology":null},{"paper":null,"slug":"translating-hanja-historical-documents-to","title":"Translating Hanja Historical Documents to Contemporary Korean and English","date":"2022-05-20","arxiv_id":"2205.10019","n_code_links":0,"syntology":null},{"paper":"/paper/uniform-masking-enabling-mae-pre-training-for","slug":"uniform-masking-enabling-mae-pre-training-for","title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality","date":"2022-05-20","arxiv_id":"2205.10063","n_code_links":1,"syntology":null},{"paper":"/paper/a-graph-transformer-for-whole-slide-image","slug":"a-graph-transformer-for-whole-slide-image","title":"A graph-transformer for whole slide image classification","date":"2022-05-19","arxiv_id":"2205.09671","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vkola-lab/tmi2022"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/acceptability-judgements-via-examining-the","slug":"acceptability-judgements-via-examining-the","title":"Acceptability Judgements via Examining the Topology of Attention Maps","date":"2022-05-19","arxiv_id":"2205.09630","n_code_links":1,"syntology":null},{"paper":null,"slug":"arabglossbert-fine-tuning-bert-on-context-1","title":"ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD","date":"2022-05-19","arxiv_id":"2205.09685","n_code_links":0,"syntology":null},{"paper":"/paper/automated-scoring-for-reading-comprehension","slug":"automated-scoring-for-reading-comprehension","title":"Automated Scoring for Reading Comprehension via In-context BERT Tuning","date":"2022-05-19","arxiv_id":"2205.09864","n_code_links":1,"syntology":null},{"paper":"/paper/babynet-residual-transformer-module-for-birth","slug":"babynet-residual-transformer-module-for-birth","title":"BabyNet: Residual Transformer Module for Birth Weight Prediction on Fetal Ultrasound Video","date":"2022-05-19","arxiv_id":"2205.09382","n_code_links":1,"syntology":null},{"paper":null,"slug":"bypassing-logits-bias-in-online-class-1","title":"Bypassing Logits Bias in Online Class-Incremental Learning with a Generative Framework","date":"2022-05-19","arxiv_id":"2205.09347","n_code_links":0,"syntology":null},{"paper":"/paper/cross-enhancement-transformer-for-action","slug":"cross-enhancement-transformer-for-action","title":"Cross-Enhancement Transformer for Action Segmentation","date":"2022-05-19","arxiv_id":"2205.09445","n_code_links":1,"syntology":null},{"paper":null,"slug":"insights-on-neural-representations-for-end-to","title":"Insights on Neural Representations for End-to-End Speech Recognition","date":"2022-05-19","arxiv_id":"2205.09456","n_code_links":0,"syntology":null},{"paper":"/paper/overcoming-language-disparity-in-online","slug":"overcoming-language-disparity-in-online","title":"Overcoming Language Disparity in Online Content Classification with Multimodal Learning","date":"2022-05-19","arxiv_id":"2205.09744","n_code_links":1,"syntology":null},{"paper":"/paper/psychiatric-scale-guided-risky-post-screening","slug":"psychiatric-scale-guided-risky-post-screening","title":"Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression","date":"2022-05-19","arxiv_id":"2205.09497","n_code_links":1,"syntology":null},{"paper":"/paper/towards-understanding-gender-seniority","slug":"towards-understanding-gender-seniority","title":"Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation","date":"2022-05-19","arxiv_id":"2205.09830","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-with-memory-replay","title":"Transformer with Memory Replay","date":"2022-05-19","arxiv_id":"2205.09869","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-as-neural-augmentors-class","slug":"transformers-as-neural-augmentors-class","title":"Transformers as Neural Augmentors: Class Conditional Sentence Generation via Variational Bayes","date":"2022-05-19","arxiv_id":"2205.09391","n_code_links":1,"syntology":null},{"paper":"/paper/transtab-learning-transferable-tabular","slug":"transtab-learning-transferable-tabular","title":"TransTab: Learning Transferable Tabular Transformers Across Tables","date":"2022-05-19","arxiv_id":"2205.09328","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ryanwangzf/transtab"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":7,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"trt-vit-tensorrt-oriented-vision-transformer","title":"TRT-ViT: TensorRT-oriented Vision Transformer","date":"2022-05-19","arxiv_id":"2205.09579","n_code_links":0,"syntology":null},{"paper":null,"slug":"vnt-net-rotational-invariant-vector-neuron","title":"VNT-Net: Rotational Invariant Vector Neuron Transformers","date":"2022-05-19","arxiv_id":"2205.09690","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-gans-are-overkill-for-nlp","title":"Why GANs are overkill for NLP","date":"2022-05-19","arxiv_id":"2205.09838","n_code_links":0,"syntology":null},{"paper":"/paper/adamct-adaptive-mixture-of-cnn-transformer","slug":"adamct-adaptive-mixture-of-cnn-transformer","title":"AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation","date":"2022-05-18","arxiv_id":"2205.08776","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":["juyongjiang/adamct"],"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":"entity-alignment-with-reliable-path-reasoning","title":"Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer","date":"2022-05-18","arxiv_id":"2205.08806","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish-1","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","date":"2022-05-18","arxiv_id":"2205.08808","n_code_links":0,"syntology":null},{"paper":"/paper/lerac-learning-rate-curriculum","slug":"lerac-learning-rate-curriculum","title":"Learning Rate Curriculum","date":"2022-05-18","arxiv_id":"2205.09180","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-pseudo-labeled-data-to-improve","slug":"leveraging-pseudo-labeled-data-to-improve","title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","date":"2022-05-18","arxiv_id":"2205.08993","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fengpeng-yue/speech-to-speech-translation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pash-at-trec-2021-deep-learning-track","title":"PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking","date":"2022-05-18","arxiv_id":"2205.11245","n_code_links":0,"syntology":null},{"paper":"/paper/persian-natural-language-inference-a-meta-1","slug":"persian-natural-language-inference-a-meta-1","title":"Persian Natural Language Inference: A Meta-learning approach","date":"2022-05-18","arxiv_id":"2205.08755","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-multiple-instance-learning","slug":"transformer-based-multiple-instance-learning","title":"Transformer based multiple instance learning for weakly supervised histopathology image segmentation","date":"2022-05-18","arxiv_id":"2205.08878","n_code_links":1,"syntology":null},{"paper":"/paper/u-former-improving-monaural-speech","slug":"u-former-improving-monaural-speech","title":"U-Former: Improving Monaural Speech Enhancement with Multi-head Self and Cross Attention","date":"2022-05-18","arxiv_id":"2205.08681","n_code_links":1,"syntology":null},{"paper":null,"slug":"application-of-graph-based-features-in","title":"Application of Graph Based Features in Computer Aided Diagnosis for Histopathological Image Classification of Gastric Cancer","date":"2022-05-17","arxiv_id":"2205.08467","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-aware-contrastive-learning-for","title":"Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity","date":"2022-05-17","arxiv_id":"2206.11255","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-aggregation-in-zero-shot-cross","title":"Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT","date":"2022-05-17","arxiv_id":"2205.08497","n_code_links":0,"syntology":null},{"paper":null,"slug":"hover-trans-anatomy-aware-hover-transformer","title":"HoVer-Trans: Anatomy-aware HoVer-Transformer for ROI-free Breast Cancer Diagnosis in Ultrasound Images","date":"2022-05-17","arxiv_id":"2205.08390","n_code_links":0,"syntology":null},{"paper":null,"slug":"m6-rec-generative-pretrained-language-models","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","date":"2022-05-17","arxiv_id":"2205.08084","n_code_links":0,"syntology":null},{"paper":null,"slug":"matrix-modality-aware-transformer-for","title":"MATrIX -- Modality-Aware Transformer for Information eXtraction","date":"2022-05-17","arxiv_id":"2205.08094","n_code_links":0,"syntology":null},{"paper":"/paper/mult-an-end-to-end-multitask-learning","slug":"mult-an-end-to-end-multitask-learning","title":"MulT: An End-to-End Multitask Learning Transformer","date":"2022-05-17","arxiv_id":"2205.08303","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"multi-head-attention-neural-network-for","title":"Multi-Head Attention Neural Network for Smartphone Invariant Indoor Localization","date":"2022-05-17","arxiv_id":"2205.08069","n_code_links":0,"syntology":null},{"paper":null,"slug":"povit-vision-transformer-for-multi-objective","title":"POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices","date":"2022-05-17","arxiv_id":"2205.09045","n_code_links":0,"syntology":null},{"paper":null,"slug":"samu-xlsr-semantically-aligned-multimodal","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","date":"2022-05-17","arxiv_id":"2205.08180","n_code_links":0,"syntology":null},{"paper":"/paper/semi-fnd-stacked-ensemble-based-multimodal","slug":"semi-fnd-stacked-ensemble-based-multimodal","title":"SEMI-FND: Stacked Ensemble Based Multimodal Inference For Faster Fake News Detection","date":"2022-05-17","arxiv_id":"2205.08159","n_code_links":0,"syntology":null},{"paper":null,"slug":"skill-structured-knowledge-infusion-for-large","title":"SKILL: Structured Knowledge Infusion for Large Language Models","date":"2022-05-17","arxiv_id":"2205.08184","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-reuse-a-multi-scale-transformer","title":"The Power of Fragmentation: A Hierarchical Transformer Model for Structural Segmentation in Symbolic Music Generation","date":"2022-05-17","arxiv_id":"2205.08579","n_code_links":0,"syntology":null},{"paper":"/paper/viralbert-a-user-focused-bert-based-approach","slug":"viralbert-a-user-focused-bert-based-approach","title":"ViralBERT: A User Focused BERT-Based Approach to Virality Prediction","date":"2022-05-17","arxiv_id":"2206.10298","n_code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-adapter-for-dense","slug":"vision-transformer-adapter-for-dense","title":"Vision Transformer Adapter for Dense Predictions","date":"2022-05-17","arxiv_id":"2205.08534","n_code_links":2,"syntology":null},{"paper":"/paper/chemical-transformer-compression-for","slug":"chemical-transformer-compression-for","title":"Chemical transformer compression for accelerating both training and inference of molecular modeling","date":"2022-05-16","arxiv_id":"2205.07582","n_code_links":1,"syntology":null},{"paper":null,"slug":"consent-context-sensitive-transformer-for","title":"CONSENT: Context Sensitive Transformer for Bold Words Classification","date":"2022-05-16","arxiv_id":"2205.07683","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-multilingual-resources-to-question","title":"Harnessing Multilingual Resources to Question Answering in Arabic","date":"2022-05-16","arxiv_id":"2205.08024","n_code_links":0,"syntology":null},{"paper":null,"slug":"heroes-villains-and-victims-and-gpt-3","title":"Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data","date":"2022-05-16","arxiv_id":"2205.07557","n_code_links":0,"syntology":null},{"paper":null,"slug":"q-munchausen-reinforcement-learning","title":"$q$-Munchausen Reinforcement Learning","date":"2022-05-16","arxiv_id":"2205.07467","n_code_links":0,"syntology":null},{"paper":"/paper/the-ai-teacher-test-measuring-the-pedagogical","slug":"the-ai-teacher-test-measuring-the-pedagogical","title":"The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues","date":"2022-05-16","arxiv_id":"2205.07540","n_code_links":1,"syntology":null},{"paper":"/paper/towards-lossless-ann-snn-conversion-under","slug":"towards-lossless-ann-snn-conversion-under","title":"Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization","date":"2022-05-16","arxiv_id":"2205.07473","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Windere/snn-cvt-dual-phase"],"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","unlocated"]}}},{"paper":null,"slug":"transformers-in-3d-point-clouds-a-survey","title":"Transformers in 3D Point Clouds: A Survey","date":"2022-05-16","arxiv_id":"2205.07417","n_code_links":0,"syntology":null},{"paper":"/paper/what-gpt-knows-about-who-is-who-1","slug":"what-gpt-knows-about-who-is-who-1","title":"What GPT Knows About Who is Who","date":"2022-05-16","arxiv_id":"2205.07407","n_code_links":1,"syntology":null},{"paper":null,"slug":"discovering-latent-concepts-learned-in-bert-1","title":"Discovering Latent Concepts Learned in BERT","date":"2022-05-15","arxiv_id":"2205.07237","n_code_links":0,"syntology":null},{"paper":"/paper/downstream-transformer-generation-of-question","slug":"downstream-transformer-generation-of-question","title":"Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelines","date":"2022-05-15","arxiv_id":"2205.07387","n_code_links":1,"syntology":null},{"paper":null,"slug":"glama-joint-spatial-and-frequency-loss-for","title":"GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting","date":"2022-05-15","arxiv_id":"2205.07162","n_code_links":0,"syntology":null},{"paper":"/paper/hero-gang-neural-model-for-named-entity","slug":"hero-gang-neural-model-for-named-entity","title":"Hero-Gang Neural Model For Named Entity Recognition","date":"2022-05-15","arxiv_id":"2205.07177","n_code_links":1,"syntology":null},{"paper":"/paper/learning-lip-based-audio-visual-speaker","slug":"learning-lip-based-audio-visual-speaker","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","date":"2022-05-15","arxiv_id":"2205.07180","n_code_links":1,"syntology":null},{"paper":null,"slug":"proxyless-neural-architecture-adaptation-for","title":"Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning","date":"2022-05-15","arxiv_id":"2205.07168","n_code_links":0,"syntology":null},{"paper":"/paper/transkimmer-transformer-learns-to-layer-wise-1","slug":"transkimmer-transformer-learns-to-layer-wise-1","title":"Transkimmer: Transformer Learns to Layer-wise Skim","date":"2022-05-15","arxiv_id":"2205.07324","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["chandlerguan/transkimmer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/video-frame-interpolation-with-transformer","slug":"video-frame-interpolation-with-transformer","title":"Video Frame Interpolation with Transformer","date":"2022-05-15","arxiv_id":"2205.07230","n_code_links":1,"syntology":null},{"paper":"/paper/classification-of-astronomical-bodies-by","slug":"classification-of-astronomical-bodies-by","title":"Classification of Astronomical Bodies by Efficient Layer Fine-Tuning of Deep Neural Networks","date":"2022-05-14","arxiv_id":"2205.07124","n_code_links":1,"syntology":null},{"paper":null,"slug":"dense-residual-transformer-for-image","title":"Dense residual Transformer for image denoising","date":"2022-05-14","arxiv_id":"2205.06944","n_code_links":0,"syntology":null},{"paper":null,"slug":"fake-news-quick-detection-on-dynamic","title":"Fake News Quick Detection on Dynamic Heterogeneous Information Networks","date":"2022-05-14","arxiv_id":"2205.07039","n_code_links":0,"syntology":null},{"paper":"/paper/naturalistic-causal-probing-for-morpho-syntax","slug":"naturalistic-causal-probing-for-morpho-syntax","title":"Naturalistic Causal Probing for Morpho-Syntax","date":"2022-05-14","arxiv_id":"2205.07043","n_code_links":1,"syntology":null},{"paper":"/paper/rasat-integrating-relational-structures-into","slug":"rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","date":"2022-05-14","arxiv_id":"2205.06983","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":1,"phrase":"5 ran (of which 0 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) · 4 unverified","official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-scale-gate-for-semantic","title":"Transformer Scale Gate for Semantic Segmentation","date":"2022-05-14","arxiv_id":"2205.07056","n_code_links":0,"syntology":null},{"paper":"/paper/a-microstructure-estimation-transformer","slug":"a-microstructure-estimation-transformer","title":"A microstructure estimation Transformer inspired by sparse representation for diffusion MRI","date":"2022-05-13","arxiv_id":"2205.06450","n_code_links":1,"syntology":null},{"paper":"/paper/a-study-of-the-attention-abnormality-in-1","slug":"a-study-of-the-attention-abnormality-in-1","title":"A Study of the Attention Abnormality in Trojaned BERTs","date":"2022-05-13","arxiv_id":"2205.08305","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["weimin17/attention_abnormality_in_trojaned_berts"],"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":"analysis-of-neural-image-compression-networks","title":"Analysis of Neural Image Compression Networks for Machine-to-Machine Communication","date":"2022-05-13","arxiv_id":"2205.06511","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-contextual-representation-with-1","title":"Improving Contextual Representation with Gloss Regularized Pre-training","date":"2022-05-13","arxiv_id":"2205.06603","n_code_links":0,"syntology":null},{"paper":"/paper/local-attention-graph-based-transformer-for","slug":"local-attention-graph-based-transformer-for","title":"Local Attention Graph-based Transformer for Multi-target Genetic Alteration Prediction","date":"2022-05-13","arxiv_id":"2205.06672","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-deep-neural-object-detection-and","title":"Robust Deep Neural Object Detection and Segmentation for Automotive Driving Scenario with Compressed Image Data","date":"2022-05-13","arxiv_id":"2205.06501","n_code_links":0,"syntology":null},{"paper":"/paper/universal-post-training-backdoor-detection","slug":"universal-post-training-backdoor-detection","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","date":"2022-05-13","arxiv_id":"2205.06900","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wanghangpsu/mm-bd"],"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/vit5-pretrained-text-to-text-transformer-for","slug":"vit5-pretrained-text-to-text-transformer-for","title":"ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation","date":"2022-05-13","arxiv_id":"2205.06457","n_code_links":1,"syntology":null},{"paper":"/paper/a-generalist-agent","slug":"a-generalist-agent","title":"A Generalist Agent","date":"2022-05-12","arxiv_id":"2205.06175","n_code_links":3,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":null}},{"paper":null,"slug":"apptek-s-submission-to-the-iwslt-2022","title":"AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task","date":"2022-05-12","arxiv_id":"2205.05807","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-prawn-farming-forecasting","title":"Deep Learning for Prawn Farming: Forecasting and Anomaly Detection","date":"2022-05-12","arxiv_id":"2205.06359","n_code_links":0,"syntology":null},{"paper":"/paper/distinction-maximization-loss-efficiently","slug":"distinction-maximization-loss-efficiently","title":"Distinction Maximization Loss: Efficiently Improving Out-of-Distribution Detection and Uncertainty Estimation by Replacing the Loss and Calibrating","date":"2022-05-12","arxiv_id":"2205.05874","n_code_links":1,"syntology":null},{"paper":"/paper/entity-aware-and-motion-aware-transformers","slug":"entity-aware-and-motion-aware-transformers","title":"Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos","date":"2022-05-12","arxiv_id":"2205.05854","n_code_links":1,"syntology":null},{"paper":"/paper/group-r-cnn-for-weakly-semi-supervised-object","slug":"group-r-cnn-for-weakly-semi-supervised-object","title":"Group R-CNN for Weakly Semi-supervised Object Detection with Points","date":"2022-05-12","arxiv_id":"2205.05920","n_code_links":1,"syntology":null},{"paper":null,"slug":"infrared-invisible-clothing-hiding-from","title":"Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real World","date":"2022-05-12","arxiv_id":"2205.05909","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-the-computation-of-abstract-sameness","title":"Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?","date":"2022-05-12","arxiv_id":"2205.06149","n_code_links":0,"syntology":null},{"paper":"/paper/multi-task-learning-for-zero-shot-performance","slug":"multi-task-learning-for-zero-shot-performance","title":"Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models","date":"2022-05-12","arxiv_id":"2205.06130","n_code_links":0,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 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) · 3 unverified","official":null}}],"record_sha256":"eacd017200b67adf80eb34ce81ae83683dbfa84f63bcb2f789b27003c42d7103","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}