{"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/adam/papers/207","list_of":"/method/adam","method":"Adam","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":207,"pages_in_order":244,"rows_per_page":100,"rows":[20601,20700],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/206","next":"/method/adam/papers/208","papers":[{"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":null,"slug":"understanding-decoupled-and-early-weight","title":"Understanding Decoupled and Early Weight Decay","date":"2020-12-27","arxiv_id":"2012.13841","n_code_links":0,"syntology":null},{"paper":null,"slug":"asymptoticng-a-regularized-natural-gradient","title":"AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy","date":"2020-12-24","arxiv_id":"2012.13077","n_code_links":0,"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":"/paper/sentence-based-model-agnostic-nlp","slug":"sentence-based-model-agnostic-nlp","title":"On the Granularity of Explanations in Model Agnostic NLP Interpretability","date":"2020-12-24","arxiv_id":"2012.13189","n_code_links":1,"syntology":null},{"paper":null,"slug":"to-what-extent-do-human-explanations-of-model","title":"To what extent do human explanations of model behavior align with actual model behavior?","date":"2020-12-24","arxiv_id":"2012.13354","n_code_links":0,"syntology":null},{"paper":"/paper/union-net-a-deep-neural-network-model-adapted","slug":"union-net-a-deep-neural-network-model-adapted","title":"Union-net: A deep neural network model adapted to small data sets","date":"2020-12-24","arxiv_id":"2012.13044","n_code_links":1,"syntology":null},{"paper":"/paper/bridging-textual-and-tabular-data-for-cross","slug":"bridging-textual-and-tabular-data-for-cross","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","date":"2020-12-23","arxiv_id":"2012.12627","n_code_links":2,"syntology":null},{"paper":"/paper/detecting-hate-speech-in-memes-using","slug":"detecting-hate-speech-in-memes-using","title":"Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge","date":"2020-12-23","arxiv_id":"2012.12975","n_code_links":1,"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":null,"slug":"applying-wav2vec2-0-to-speech-recognition-in","title":"Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages","date":"2020-12-22","arxiv_id":"2012.12121","n_code_links":0,"syntology":null},{"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":"/paper/improved-biomedical-word-embeddings-in-the","slug":"improved-biomedical-word-embeddings-in-the","title":"Improved Biomedical Word Embeddings in the Transformer Era","date":"2020-12-22","arxiv_id":"2012.11808","n_code_links":1,"syntology":null},{"paper":"/paper/intrinsic-dimensionality-explains-the","slug":"intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","arxiv_id":"2012.13255","n_code_links":2,"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":["rabeehk/compacter"],"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/learning-to-retrieve-entity-aware-knowledge","slug":"learning-to-retrieve-entity-aware-knowledge","title":"Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems","date":"2020-12-22","arxiv_id":"2012.11937","n_code_links":1,"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/recognizing-emotion-cause-in-conversations-1","slug":"recognizing-emotion-cause-in-conversations-1","title":"Recognizing Emotion Cause in Conversations","date":"2020-12-22","arxiv_id":"2012.11820","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-and-surprisal-jointly-deliver-the","title":"Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition","date":"2020-12-22","arxiv_id":"2012.12007","n_code_links":0,"syntology":null},{"paper":null,"slug":"2012-11643","title":"myGym: Modular Toolkit for Visuomotor Robotic Tasks","date":"2020-12-21","arxiv_id":"2012.11643","n_code_links":0,"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":"a-graph-reasoning-network-for-multi-turn","title":"A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-training","date":"2020-12-21","arxiv_id":"2012.11099","n_code_links":0,"syntology":null},{"paper":"/paper/cross-domain-retrieval-in-the-legal-and","slug":"cross-domain-retrieval-in-the-legal-and","title":"Cross-domain Retrieval in the Legal and Patent Domains: a Reproducibility Study","date":"2020-12-21","arxiv_id":"2012.11405","n_code_links":1,"syntology":null},{"paper":"/paper/domain-specific-bert-representation-for-named","slug":"domain-specific-bert-representation-for-named","title":"Domain specific BERT representation for Named Entity Recognition of lab protocol","date":"2020-12-21","arxiv_id":"2012.11145","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/leveraging-parsbert-and-pretrained-mt5-for","slug":"leveraging-parsbert-and-pretrained-mt5-for","title":"Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization","date":"2020-12-21","arxiv_id":"2012.11204","n_code_links":1,"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":"towards-incorporating-entity-specific","title":"Towards Incorporating Entity-specific Knowledge Graph Information in Predicting Drug-Drug Interactions","date":"2020-12-21","arxiv_id":"2012.11142","n_code_links":0,"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":null,"slug":"controllable-and-contextualised-writing-tool","title":"Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models","date":"2020-12-19","arxiv_id":"2101.03216","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-mga-msgd-ann-training-approach-for","title":"A hybrid MGA-MSGD ANN training approach for approximate solution of linear elliptic PDEs","date":"2020-12-18","arxiv_id":"2012.11517","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-using-pre-trained-bert","slug":"an-empirical-study-of-using-pre-trained-bert","title":"An Empirical Study of Using Pre-trained BERT Models for Vietnamese Relation Extraction Task at VLSP 2020","date":"2020-12-18","arxiv_id":"2012.10275","n_code_links":1,"syntology":null},{"paper":"/paper/hatexplain-a-benchmark-dataset-for","slug":"hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","date":"2020-12-18","arxiv_id":"2012.10289","n_code_links":6,"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":"/paper/on-modality-bias-in-the-tvqa-dataset","slug":"on-modality-bias-in-the-tvqa-dataset","title":"On Modality Bias in the TVQA Dataset","date":"2020-12-18","arxiv_id":"2012.10210","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":"a-white-box-analysis-of-colbert","title":"A White Box Analysis of ColBERT","date":"2020-12-17","arxiv_id":"2012.09650","n_code_links":0,"syntology":null},{"paper":"/paper/bert-goes-shopping-comparing-distributional","slug":"bert-goes-shopping-comparing-distributional","title":"BERT Goes Shopping: Comparing Distributional Models for Product Representations","date":"2020-12-17","arxiv_id":"2012.09807","n_code_links":1,"syntology":null},{"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/infinite-nature-perpetual-view-generation-of","slug":"infinite-nature-perpetual-view-generation-of","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","date":"2020-12-17","arxiv_id":"2012.09855","n_code_links":1,"syntology":null},{"paper":"/paper/literature-retrieval-for-precision-medicine","slug":"literature-retrieval-for-precision-medicine","title":"Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization","date":"2020-12-17","arxiv_id":"2012.09355","n_code_links":1,"syntology":null},{"paper":"/paper/masker-masked-keyword-regularization-for","slug":"masker-masked-keyword-regularization-for","title":"MASKER: Masked Keyword Regularization for Reliable Text Classification","date":"2020-12-17","arxiv_id":"2012.09392","n_code_links":1,"syntology":null},{"paper":null,"slug":"mix-a-multi-task-learning-approach-to-solve","title":"MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering","date":"2020-12-17","arxiv_id":"2012.09766","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/sceneformer-indoor-scene-generation-with","slug":"sceneformer-indoor-scene-generation-with","title":"SceneFormer: Indoor Scene Generation with Transformers","date":"2020-12-17","arxiv_id":"2012.09793","n_code_links":2,"syntology":null},{"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":"/paper/a-lightweight-neural-model-for-biomedical","slug":"a-lightweight-neural-model-for-biomedical","title":"A Lightweight Neural Model for Biomedical Entity Linking","date":"2020-12-16","arxiv_id":"2012.08844","n_code_links":1,"syntology":null},{"paper":"/paper/dialogxl-all-in-one-xlnet-for-multi-party","slug":"dialogxl-all-in-one-xlnet-for-multi-party","title":"DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition","date":"2020-12-16","arxiv_id":"2012.08695","n_code_links":4,"syntology":null},{"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":"query-expansion-with-artificially-generated","title":"Query expansion with artificially generated texts","date":"2020-12-16","arxiv_id":"2012.08787","n_code_links":0,"syntology":null},{"paper":null,"slug":"r-2-net-relation-of-relation-learning-network","title":"R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching","date":"2020-12-16","arxiv_id":"2012.08920","n_code_links":0,"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/pre-training-transformers-as-energy-based-1","slug":"pre-training-transformers-as-energy-based-1","title":"Pre-Training Transformers as Energy-Based Cloze Models","date":"2020-12-15","arxiv_id":"2012.08561","n_code_links":1,"syntology":null},{"paper":"/paper/recipenlg-a-cooking-recipes-dataset-for-semi","slug":"recipenlg-a-cooking-recipes-dataset-for-semi","title":"RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation","date":"2020-12-15","arxiv_id":null,"n_code_links":1,"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/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/extracting-training-data-from-large-language","slug":"extracting-training-data-from-large-language","title":"Extracting Training Data from Large Language Models","date":"2020-12-14","arxiv_id":"2012.07805","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["ftramer/LM_Memorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":null,"slug":"lrc-bert-latent-representation-contrastive","title":"LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding","date":"2020-12-14","arxiv_id":"2012.07335","n_code_links":0,"syntology":null},{"paper":null,"slug":"policy-gradient-for-items-recommendation-on","title":"Policy Gradient for items Recommendation on Virtual Taobao","date":"2020-12-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/policy-gradient-rl-algorithms-as-directed","slug":"policy-gradient-rl-algorithms-as-directed","title":"Policy Gradient RL Algorithms as Directed Acyclic Graphs","date":"2020-12-14","arxiv_id":"2012.07763","n_code_links":1,"syntology":null},{"paper":null,"slug":"ranking-items-in-large-scale-item-search","title":"Ranking Items in Large-Scale Item Search Engines with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"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":null,"slug":"vartani-spellcheck-automatic-context","title":"Vartani Spellcheck -- Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance","date":"2020-12-14","arxiv_id":"2012.07652","n_code_links":0,"syntology":null},{"paper":null,"slug":"virtual-autonomous-driving-with-reinforcement","title":"Virtual Autonomous Driving with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"discriminative-pre-training-for-low-resource","title":"Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery","date":"2020-12-13","arxiv_id":"2012.06943","n_code_links":0,"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":null,"slug":"minivlm-a-smaller-and-faster-vision-language","title":"MiniVLM: A Smaller and Faster Vision-Language Model","date":"2020-12-13","arxiv_id":"2012.06946","n_code_links":0,"syntology":null},{"paper":"/paper/cogalex-vi-shared-task-transrelation-a-robust","slug":"cogalex-vi-shared-task-transrelation-a-robust","title":"CogALex-VI Shared Task: Transrelation - A Robust Multilingual Language Model for Multilingual Relation Identification","date":"2020-12-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/computer-vision-and-normalizing-flow-based","slug":"computer-vision-and-normalizing-flow-based","title":"Computer Vision and Normalizing Flow-Based Defect Detection","date":"2020-12-12","arxiv_id":"2012.06737","n_code_links":1,"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/yelp-review-rating-prediction-machine","slug":"yelp-review-rating-prediction-machine","title":"Yelp Review Rating Prediction: Machine Learning and Deep Learning Models","date":"2020-12-12","arxiv_id":"2012.06690","n_code_links":1,"syntology":null},{"paper":null,"slug":"hardware-beyond-backpropagation-a-photonic-co","title":"Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment","date":"2020-12-11","arxiv_id":"2012.06373","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-task-agnostic-bert-distillation","title":"Improving Task-Agnostic BERT Distillation with Layer Mapping Search","date":"2020-12-11","arxiv_id":"2012.06153","n_code_links":0,"syntology":null},{"paper":null,"slug":"opac-opportunistic-actor-critic","title":"OPAC: Opportunistic Actor-Critic","date":"2020-12-11","arxiv_id":"2012.06555","n_code_links":0,"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/the-implicit-bias-for-adaptive-optimization","slug":"the-implicit-bias-for-adaptive-optimization","title":"The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks","date":"2020-12-11","arxiv_id":"2012.06244","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-practical-approach-towards-causality-mining","title":"A Practical Approach towards Causality Mining in Clinical Text using Active Transfer Learning","date":"2020-12-10","arxiv_id":"2012.07563","n_code_links":0,"syntology":null},{"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/towards-neural-programming-interfaces-1","slug":"towards-neural-programming-interfaces-1","title":"Towards Neural Programming Interfaces","date":"2020-12-10","arxiv_id":"2012.05983","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-lingual-word-sense-disambiguation-using","title":"Cross-lingual Word Sense Disambiguation using mBERT Embeddings with Syntactic Dependencies","date":"2020-12-09","arxiv_id":"2012.05300","n_code_links":0,"syntology":null},{"paper":"/paper/mapping-the-space-of-chemical-reactions-using","slug":"mapping-the-space-of-chemical-reactions-using","title":"Mapping the Space of Chemical Reactions Using Attention-Based Neural Networks","date":"2020-12-09","arxiv_id":"2012.06051","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":null,"slug":"discourse-parsing-of-contentious-non","title":"Discourse Parsing of Contentious, Non-Convergent Online Discussions","date":"2020-12-08","arxiv_id":"2012.04585","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-mass-media-shape-public-opinion-toward","title":"Large-scale Quantitative Evidence of Media Impact on Public Opinion toward China","date":"2020-12-08","arxiv_id":"2012.07575","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-estimation-of-influence-of-a","title":"Efficient Estimation of Influence of a Training Instance","date":"2020-12-08","arxiv_id":"2012.04207","n_code_links":0,"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":"/paper/from-bag-of-sentences-to-document-distantly","slug":"from-bag-of-sentences-to-document-distantly","title":"From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension","date":"2020-12-08","arxiv_id":"2012.04334","n_code_links":1,"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":"/paper/tado-time-varying-attention-with-dual","slug":"tado-time-varying-attention-with-dual","title":"TADO: Time-varying Attention with Dual-Optimizer Model","date":"2020-12-08","arxiv_id":"2012.04558","n_code_links":1,"syntology":null}],"record_sha256":"47d9baab532bf9fe90b3793b107775de176f083491e1b778711228e82c6280b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}