{"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/label-smoothing/papers/128","list_of":"/method/label-smoothing","method":"Label Smoothing","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":128,"pages_in_order":144,"rows_per_page":100,"rows":[12701,12800],"of":14327,"counts":{"archive_papers_tagged":14327,"with_a_code_link":6651,"where_syntology_ran_a_sample":2259,"not_listed_spam_title":0,"listed":14327,"listed_where_code_ran":2259,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1920,"every_run_a_failure_of_syntologys_instrument":339,"listed_with_a_run_with_no_instrument_failure":1920,"listed_every_run_a_failure_of_syntologys_instrument":339,"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/label-smoothing","prev":"/method/label-smoothing/papers/127","next":"/method/label-smoothing/papers/129","papers":[{"paper":null,"slug":"representation-and-bias-in-multilingual-nlp","title":"Representation and Bias in Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representational-correlates-of-hierarchical","title":"Representational correlates of hierarchical phrase structure in deep language models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/scene-context-aware-salient-object-detection","slug":"scene-context-aware-salient-object-detection","title":"Scene Context-Aware Salient Object Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"share-or-not-learning-to-schedule-language","title":"Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"single-layers-of-attention-suffice-to-predict","title":"Single Layers of Attention Suffice to Predict Protein Contacts","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/star-a-structure-aware-lightweight","slug":"star-a-structure-aware-lightweight","title":"STAR: A Structure-Aware Lightweight Transformer for Real-Time Image Enhancement","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/subformer-a-parameter-reduced-transformer","slug":"subformer-a-parameter-reduced-transformer","title":"Subformer: A Parameter Reduced Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/subformer-exploring-weight-sharing-for","slug":"subformer-exploring-weight-sharing-for","title":"Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers","date":"2021-01-01","arxiv_id":"2101.00234","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthesizer-rethinking-self-attention-for","title":"Synthesizer: Rethinking Self-Attention for Transformer Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"trans-caps-transformer-capsule-networks-with","title":"Trans-Caps: Transformer Capsule Networks with Self-attention Routing","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-protein-language-models-are","title":"Transformer protein language models are unsupervised structure learners","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-ql-a-step-towards-making","title":"Transformer-QL: A Step Towards Making Transformer Network Quadratically Large","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-satisfy","title":"Transformers satisfy","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-recurrent-neural-networks-with","title":"Transforming Recurrent Neural Networks with Attention and Fixed-point Equations","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/trar-routing-the-attention-spans-in","slug":"trar-routing-the-attention-spans-in","title":"TRAR: Routing the Attention Spans in Transformer for Visual Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"updet-universal-multi-agent-rl-via-policy","title":"UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-transformers-where-do-transformers","title":"Visual Transformers: Where Do Transformers Really Belong in Vision Models?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/visualsparta-sparse-transformer-fragment","slug":"visualsparta-sparse-transformer-fragment","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","date":"2021-01-01","arxiv_id":"2101.00265","n_code_links":1,"syntology":null},{"paper":null,"slug":"wb-detr-transformer-based-detector-without","title":"WB-DETR: Transformer-Based Detector Without Backbone","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-are-effective-labels-for-augmented-data","title":"What are effective labels for augmented data? Improving robustness with AutoLabel","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-modal-deep-learning-model-for-video","title":"A Multi-modal Deep Learning Model for Video Thumbnail Selection","date":"2020-12-31","arxiv_id":"2101.00073","n_code_links":0,"syntology":null},{"paper":"/paper/fully-non-autoregressive-neural-machine","slug":"fully-non-autoregressive-neural-machine","title":"Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade","date":"2020-12-31","arxiv_id":"2012.15833","n_code_links":1,"syntology":null},{"paper":"/paper/minilmv2-multi-head-self-attention-relation","slug":"minilmv2-multi-head-self-attention-relation","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","date":"2020-12-31","arxiv_id":"2012.15828","n_code_links":2,"syntology":null},{"paper":null,"slug":"revisiting-robust-neural-machine-translation","title":"Revisiting Robust Neural Machine Translation: A Transformer Case Study","date":"2020-12-31","arxiv_id":"2012.15710","n_code_links":0,"syntology":null},{"paper":"/paper/transtrack-multiple-object-tracking-with","slug":"transtrack-multiple-object-tracking-with","title":"TransTrack: Multiple Object Tracking with Transformer","date":"2020-12-31","arxiv_id":"2012.15460","n_code_links":2,"syntology":null},{"paper":null,"slug":"verb-knowledge-injection-for-multilingual","title":"Verb Knowledge Injection for Multilingual Event Processing","date":"2020-12-31","arxiv_id":"2012.15421","n_code_links":0,"syntology":null},{"paper":null,"slug":"xlm-t-scaling-up-multilingual-machine","title":"XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders","date":"2020-12-31","arxiv_id":"2012.15547","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-deeper-transformers-on-small","slug":"optimizing-deeper-transformers-on-small","title":"Optimizing Deeper Transformers on Small Datasets","date":"2020-12-30","arxiv_id":"2012.15355","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-for-image-quality-assessment","title":"Transformer for Image Quality Assessment","date":"2020-12-30","arxiv_id":"2101.01097","n_code_links":0,"syntology":null},{"paper":"/paper/unnatural-language-inference","slug":"unnatural-language-inference","title":"UnNatural Language Inference","date":"2020-12-30","arxiv_id":"2101.00010","n_code_links":1,"syntology":null},{"paper":"/paper/a-hierarchical-transformer-with-speaker","slug":"a-hierarchical-transformer-with-speaker","title":"A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation","date":"2020-12-29","arxiv_id":"2012.14781","n_code_links":1,"syntology":null},{"paper":"/paper/kaleidoscope-an-efficient-learnable-1","slug":"kaleidoscope-an-efficient-learnable-1","title":"Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps","date":"2020-12-29","arxiv_id":"2012.14966","n_code_links":2,"syntology":{"ran":16,"of":23,"n_ran_checked":9,"n_instrument":7,"unverified":7,"pointer_only":0,"phrase":"16 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","official":{"repos":["HazyResearch/butterfly","HazyResearch/learning-circuits"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":9,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","n_code_links":9,"syntology":null},{"paper":"/paper/sit3-code-summarization-with-structure","slug":"sit3-code-summarization-with-structure","title":"Code Summarization with Structure-induced Transformer","date":"2020-12-29","arxiv_id":"2012.14710","n_code_links":1,"syntology":null},{"paper":"/paper/lattice-free-mmi-adaptation-of-self","slug":"lattice-free-mmi-adaptation-of-self","title":"Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic Models","date":"2020-12-28","arxiv_id":"2012.14252","n_code_links":2,"syntology":null},{"paper":"/paper/red-dragon-ai-at-textgraphs-2020-shared-task","slug":"red-dragon-ai-at-textgraphs-2020-shared-task","title":"Red Dragon AI at TextGraphs 2020 Shared Task: LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking","date":"2020-12-28","arxiv_id":"2012.14164","n_code_links":1,"syntology":null},{"paper":"/paper/syntax-enhanced-pre-trained-model","slug":"syntax-enhanced-pre-trained-model","title":"Syntax-Enhanced Pre-trained Model","date":"2020-12-28","arxiv_id":"2012.14116","n_code_links":1,"syntology":null},{"paper":"/paper/transpose-towards-explainable-human-pose","slug":"transpose-towards-explainable-human-pose","title":"TransPose: Keypoint Localization via Transformer","date":"2020-12-28","arxiv_id":"2012.14214","n_code_links":1,"syntology":null},{"paper":"/paper/learning-light-weight-translation-models-from","slug":"learning-light-weight-translation-models-from","title":"Learning Light-Weight Translation Models from Deep Transformer","date":"2020-12-27","arxiv_id":"2012.13866","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["libeineu/GPKD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"portfolio-optimization-with-2d-relative","title":"Portfolio Optimization with 2D Relative-Attentional Gated Transformer","date":"2020-12-27","arxiv_id":"2101.03138","n_code_links":0,"syntology":null},{"paper":null,"slug":"sg-net-syntax-guided-transformer-for-language","title":"SG-Net: Syntax Guided Transformer for Language Representation","date":"2020-12-27","arxiv_id":"2012.13915","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-adversarial-attack-to-object-detection","slug":"sparse-adversarial-attack-to-object-detection","title":"Sparse Adversarial Attack to Object Detection","date":"2020-12-26","arxiv_id":"2012.13692","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-hateful-memes-using-a-multimodal","slug":"detecting-hateful-memes-using-a-multimodal","title":"Detecting Hateful Memes Using a Multimodal Deep Ensemble","date":"2020-12-24","arxiv_id":"2012.13235","n_code_links":1,"syntology":null},{"paper":null,"slug":"i-like-fish-especially-dolphins-addressing","title":"I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling","date":"2020-12-24","arxiv_id":"2012.13391","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-neural-machine-translation-prefers-empty","title":"Why Neural Machine Translation Prefers Empty Outputs","date":"2020-12-24","arxiv_id":"2012.13454","n_code_links":0,"syntology":null},{"paper":null,"slug":"future-guided-incremental-transformer-for","title":"Future-Guided Incremental Transformer for Simultaneous Translation","date":"2020-12-23","arxiv_id":"2012.12465","n_code_links":0,"syntology":null},{"paper":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","n_code_links":40,"syntology":{"ran":12,"of":19,"n_ran_checked":9,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["facebookresearch/deit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"domain-adaptation-of-nmt-models-for-english","title":"Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020","date":"2020-12-22","arxiv_id":"2012.12112","n_code_links":0,"syntology":null},{"paper":null,"slug":"molecular-ct-unifying-geometry-and","title":"Molecular CT: Unifying Geometry and Representation Learning for Molecules at Different Scales","date":"2020-12-22","arxiv_id":"2012.11816","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-self-attention-with-role-guided","slug":"multi-head-self-attention-with-role-guided","title":"Multi-Head Self-Attention with Role-Guided Masks","date":"2020-12-22","arxiv_id":"2012.12366","n_code_links":1,"syntology":null},{"paper":"/paper/self-progressing-robust-training","slug":"self-progressing-robust-training","title":"Self-Progressing Robust Training","date":"2020-12-22","arxiv_id":"2012.11769","n_code_links":1,"syntology":null},{"paper":"/paper/3d-object-detection-with-pointformer","slug":"3d-object-detection-with-pointformer","title":"3D Object Detection with Pointformer","date":"2020-12-21","arxiv_id":"2012.11409","n_code_links":1,"syntology":null},{"paper":null,"slug":"encoding-syntactic-knowledge-in-transformer","title":"Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling","date":"2020-12-21","arxiv_id":"2012.11689","n_code_links":0,"syntology":null},{"paper":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","n_code_links":5,"syntology":null},{"paper":"/paper/sub-linear-memory-how-to-make-performers-slim","slug":"sub-linear-memory-how-to-make-performers-slim","title":"Sub-Linear Memory: How to Make Performers SLiM","date":"2020-12-21","arxiv_id":"2012.11346","n_code_links":2,"syntology":null},{"paper":null,"slug":"adaptive-bi-directional-attention-exploring","title":"Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension","date":"2020-12-20","arxiv_id":"2012.10877","n_code_links":0,"syntology":null},{"paper":"/paper/neurst-neural-speech-translation-toolkit","slug":"neurst-neural-speech-translation-toolkit","title":"NeurST: Neural Speech Translation Toolkit","date":"2020-12-18","arxiv_id":"2012.10018","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-streaming-asr-with-non-autoregressive","title":"Toward Streaming ASR with Non-Autoregressive Insertion-based Model","date":"2020-12-18","arxiv_id":"2012.10128","n_code_links":0,"syntology":null},{"paper":"/paper/a-generalization-of-transformer-networks-to","slug":"a-generalization-of-transformer-networks-to","title":"A Generalization of Transformer Networks to Graphs","date":"2020-12-17","arxiv_id":"2012.09699","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":{"repos":["graphdeeplearning/graphtransformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"end-to-end-deep-object-tracking-with-circular","title":"End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box","date":"2020-12-17","arxiv_id":"2012.09771","n_code_links":0,"syntology":null},{"paper":"/paper/pct-point-cloud-transformer","slug":"pct-point-cloud-transformer","title":"PCT: Point cloud transformer","date":"2020-12-17","arxiv_id":"2012.09688","n_code_links":11,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":{"repos":["MenghaoGuo/PCT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/taming-transformers-for-high-resolution-image","slug":"taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","arxiv_id":"2012.09841","n_code_links":13,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["CompVis/taming-transformers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"toward-transformer-based-object-detection","title":"Toward Transformer-Based Object Detection","date":"2020-12-17","arxiv_id":"2012.09958","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-interpretability-beyond-attention","slug":"transformer-interpretability-beyond-attention","title":"Transformer Interpretability Beyond Attention Visualization","date":"2020-12-17","arxiv_id":"2012.09838","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["hila-chefer/Transformer-Explainability"],"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":"focusing-more-on-conflicts-with-mis","title":"Learning from Mistakes: Using Mis-predictions as Harm Alerts in Language Pre-Training","date":"2020-12-16","arxiv_id":"2012.08789","n_code_links":0,"syntology":null},{"paper":"/paper/point-transformer-1","slug":"point-transformer-1","title":"Point Transformer","date":"2020-12-16","arxiv_id":"2012.09164","n_code_links":24,"syntology":null},{"paper":null,"slug":"revisiting-linformer-with-a-modified-self","title":"Revisiting Linformer with a modified self-attention with linear complexity","date":"2020-12-16","arxiv_id":"2101.10277","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-throughput-screening-with-machine","title":"High throughput screening with machine learning","date":"2020-12-15","arxiv_id":"2012.08275","n_code_links":0,"syntology":null},{"paper":"/paper/traditional-ir-rivals-neural-models-on-the-ms","slug":"traditional-ir-rivals-neural-models-on-the-ms","title":"Traditional IR rivals neural models on the MS MARCO Document Ranking Leaderboard","date":"2020-12-15","arxiv_id":"2012.08020","n_code_links":2,"syntology":null},{"paper":"/paper/weakly-supervised-label-smoothing","slug":"weakly-supervised-label-smoothing","title":"Weakly Supervised Label Smoothing","date":"2020-12-15","arxiv_id":"2012.08575","n_code_links":1,"syntology":null},{"paper":"/paper/contrastive-learning-with-adversarial-2","slug":"contrastive-learning-with-adversarial-2","title":"Contrastive Learning with Adversarial Perturbations for Conditional Text Generation","date":"2020-12-14","arxiv_id":"2012.07280","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":["seanie12/CLAPS"],"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/informer-beyond-efficient-transformer-for","slug":"informer-beyond-efficient-transformer-for","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","date":"2020-12-14","arxiv_id":"2012.07436","n_code_links":14,"syntology":{"ran":62,"of":76,"n_ran_checked":62,"n_instrument":0,"unverified":14,"pointer_only":13,"phrase":"62 ran (of which 53 constructed an object rather than computing a result; 62 with no instrument failure: 0 honoured, 1 violated, 61 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","official":{"repos":["WenjieDu/PyPOTS"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","named_in_paper"]}}},{"paper":"/paper/reasoning-in-dialog-improving-response","slug":"reasoning-in-dialog-improving-response","title":"Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension","date":"2020-12-14","arxiv_id":"2012.07410","n_code_links":1,"syntology":null},{"paper":"/paper/improving-image-captioning-by-leveraging-1","slug":"improving-image-captioning-by-leveraging-1","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","date":"2020-12-13","arxiv_id":"2012.07061","n_code_links":1,"syntology":null},{"paper":"/paper/kvl-bert-knowledge-enhanced-visual-and","slug":"kvl-bert-knowledge-enhanced-visual-and","title":"KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning","date":"2020-12-13","arxiv_id":"2012.07000","n_code_links":0,"syntology":null},{"paper":"/paper/detr-for-pedestrian-detection","slug":"detr-for-pedestrian-detection","title":"DETR for Crowd Pedestrian Detection","date":"2020-12-12","arxiv_id":"2012.06785","n_code_links":1,"syntology":null},{"paper":"/paper/spatial-temporal-transformer-network-for-1","slug":"spatial-temporal-transformer-network-for-1","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","date":"2020-12-11","arxiv_id":"2012.06399","n_code_links":1,"syntology":null},{"paper":"/paper/tabtransformer-tabular-data-modeling-using","slug":"tabtransformer-tabular-data-modeling-using","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","date":"2020-12-11","arxiv_id":"2012.06678","n_code_links":12,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["lucidrains/tab-transformer-pytorch"],"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/as-good-as-new-how-to-successfully-recycle","slug":"as-good-as-new-how-to-successfully-recycle","title":"As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages","date":"2020-12-10","arxiv_id":"2012.05628","n_code_links":1,"syntology":null},{"paper":null,"slug":"da-hgt-domain-adaptive-heterogeneous-graph","title":"GDA-HIN: A Generalized Domain Adaptive Model across Heterogeneous Information Networks","date":"2020-12-10","arxiv_id":"2012.05688","n_code_links":0,"syntology":null},{"paper":"/paper/label-confusion-learning-to-enhance-text","slug":"label-confusion-learning-to-enhance-text","title":"Label Confusion Learning to Enhance Text Classification Models","date":"2020-12-09","arxiv_id":"2012.04987","n_code_links":1,"syntology":null},{"paper":"/paper/simple-is-not-easy-a-simple-strong-baseline","slug":"simple-is-not-easy-a-simple-strong-baseline","title":"Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps","date":"2020-12-09","arxiv_id":"2012.05153","n_code_links":1,"syntology":null},{"paper":"/paper/extractive-opinion-summarization-in-quantized","slug":"extractive-opinion-summarization-in-quantized","title":"Extractive Opinion Summarization in Quantized Transformer Spaces","date":"2020-12-08","arxiv_id":"2012.04443","n_code_links":2,"syntology":null},{"paper":null,"slug":"parameter-efficient-multimodal-transformers-1","title":"Parameter Efficient Multimodal Transformers for Video Representation Learning","date":"2020-12-08","arxiv_id":"2012.04124","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-policy-networks-for-npc-behaviors-that","title":"Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games","date":"2020-12-07","arxiv_id":"2012.03532","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-graph-for-neural-machine-translation","title":"Document Graph for Neural Machine Translation","date":"2020-12-07","arxiv_id":"2012.03477","n_code_links":0,"syntology":null},{"paper":"/paper/re-satellite-image-time-series-classification","slug":"re-satellite-image-time-series-classification","title":"[Re] Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention","date":"2020-12-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"data-efficient-methods-for-dialogue-systems","title":"Data-Efficient Methods for Dialogue Systems","date":"2020-12-05","arxiv_id":"2012.02929","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-protein-language-models-with","slug":"pre-training-protein-language-models-with","title":"Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks","date":"2020-12-05","arxiv_id":"2012.03084","n_code_links":1,"syntology":null},{"paper":"/paper/echobert-a-transformer-based-approach-for","slug":"echobert-a-transformer-based-approach-for","title":"EchoBERT: A Transformer-Based Approach for Behavior Detection in Echograms","date":"2020-12-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-for-low-resource-natural","title":"Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning","date":"2020-12-04","arxiv_id":"2012.02462","n_code_links":0,"syntology":null},{"paper":"/paper/dialogbert-discourse-aware-response","slug":"dialogbert-discourse-aware-response","title":"DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances","date":"2020-12-03","arxiv_id":"2012.01775","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":"trace-early-detection-of-chronic-kidney","title":"TRACE: Early Detection of Chronic Kidney Disease Onset with Transformer-Enhanced Feature Embedding","date":"2020-12-03","arxiv_id":"2012.03729","n_code_links":0,"syntology":null},{"paper":null,"slug":"traffic-surveillance-using-vehicle-license","title":"Traffic Surveillance using Vehicle License Plate Detection and Recognition in Bangladesh","date":"2020-12-03","arxiv_id":"2012.02218","n_code_links":0,"syntology":null},{"paper":"/paper/contour-transformer-network-for-one-shot","slug":"contour-transformer-network-for-one-shot","title":"Contour Transformer Network for One-shot Segmentation of Anatomical Structures","date":"2020-12-02","arxiv_id":"2012.01480","n_code_links":1,"syntology":null},{"paper":"/paper/learning-universal-shape-dictionary-for","slug":"learning-universal-shape-dictionary-for","title":"Learning Universal Shape Dictionary for Realtime Instance Segmentation","date":"2020-12-02","arxiv_id":"2012.01050","n_code_links":1,"syntology":null},{"paper":null,"slug":"regularization-via-adaptive-pairwise-label","title":"Regularization via Adaptive Pairwise Label Smoothing","date":"2020-12-02","arxiv_id":"2012.01559","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-sparse-transformer-for-time","slug":"adversarial-sparse-transformer-for-time","title":"Adversarial Sparse Transformer for Time Series Forecasting","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/analogy-models-for-neural-word-inflection","slug":"analogy-models-for-neural-word-inflection","title":"Analogy Models for Neural Word Inflection","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-at-semeval-2020-task-8-using-bert-to","title":"BERT at SemEval-2020 Task 8: Using BERT to Analyse Meme Emotions","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"6bd8d7e771d0c7a88debd46e301e0977c0512f67f33e2697956ea9502972bc99","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}