{"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/dropout/papers/200","list_of":"/method/dropout","method":"Dropout","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":200,"pages_in_order":275,"rows_per_page":100,"rows":[19901,20000],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/199","next":"/method/dropout/papers/201","papers":[{"paper":null,"slug":"compressing-transformer-based-sequence-to","title":"Compressing Transformer-Based Sequence to Sequence Models With Pre-trained Autoencoders for Text Summarization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-pre-training-for-zero-shot","title":"Contrastive Pre-training for Zero-Shot Information Retrieval","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-networks-on-enhanced-message","title":"Convolutional Networks on Enhanced Message-Passing Graph Improve Semi-Supervised Classification with Few Labels","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-architecture-distillation-using","title":"Cross-Architecture Distillation Using Bidirectional CMOW Embeddings","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"crossformer-transformer-with-alternated-cross","title":"Crossformer: Transformer with Alternated Cross-Layer Guidance","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"d-2-etr-decoder-only-detr-with","title":"D$^2$ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-generalization-in-reinforcement","title":"Disentangling Generalization in Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"distributional-decision-transformer-for","title":"Distributional Decision Transformer for Hindsight Information Matching","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-packing-towards-2x-nlp-speed-up","title":"Efficient Packing: Towards 2x NLP Speed-Up without Loss of Accuracy for BERT","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-point-transformer-for-large-scale","title":"Efficient Point Transformer for Large-scale 3D Scene Understanding","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"embedding-models-through-the-lens-of-stable","title":"Embedding models through the lens of Stable Coloring","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"equivariant-transformers-for-neural-network","title":"Equivariant Transformers for Neural Network based Molecular Potentials","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ernie-sparse-robust-efficient-transformer","title":"ERNIE-SPARSE: Robust Efficient Transformer Through Hierarchically Unifying Isolated Information","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fairness-in-representation-for-multilingual","title":"Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"feddrop-trajectory-weighted-dropout-for","title":"FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-contrastive-learning-for-privacy","title":"Federated Contrastive Learning for Privacy-Preserving Unpaired Image-to-Image Translation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gental-generative-denoising-skip-gram","title":"GenTAL: Generative Denoising Skip-gram Transformer for Unsupervised Binary Code Similarity Detection","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"geometry-entangled-visual-semantic","title":"Geometry-Entangled Visual Semantic Transformer for Image Captioning","date":"2021-09-29","arxiv_id":"2109.14137","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-broadcast-adaptation-defending","title":"Gradient Broadcast Adaptation: Defending against the backdoor attack in pre-trained models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"graphix-a-pre-trained-graph-edit-model-for","title":"GRAPHIX: A Pre-trained Graph Edit Model for Automated Program Repair","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-language-representation-with-visual","title":"Grounding Language Representation with Visual Object Information via Cross Modal Pretraining","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/group-based-interleaved-pipeline-parallelism","slug":"group-based-interleaved-pipeline-parallelism","title":"Group-based Interleaved Pipeline Parallelism for Large-scale DNN Training","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"guiding-transformers-to-process-in-steps","title":"Guiding Transformers to Process in Steps","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hfsp-a-hardware-friendly-soft-pruning","title":"HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-character-tagger-for-short-text","title":"Hierarchical Character Tagger for Short Text Spelling Error Correction","date":"2021-09-29","arxiv_id":"2109.14259","n_code_links":0,"syntology":null},{"paper":null,"slug":"holoformer-deep-compression-of-pre-trained","title":"HoloFormer: Deep Compression of Pre-Trained Transforms via Unified Optimization of N:M Sparsity and Integer Quantization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-bert-address-polysemy-of-korean","title":"How does BERT address polysemy of Korean adverbial postpositions -ey, -eyse, and -(u)lo?","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-cloud-edge-networks-for-efficient","slug":"hybrid-cloud-edge-networks-for-efficient","title":"Hybrid Cloud-Edge Networks for Efficient Inference","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hydrasum-disentangling-stylistic-features-in","title":"HydraSum - Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"illiterate-dall-cdot-e-learns-to-compose","title":"Illiterate DALL$\\cdot$E Learns to Compose","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-sentiment-classification-using-0","title":"Improving Sentiment Classification Using 0-Shot Generated Labels for Custom Transformer Embeddings","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"in-defense-of-dual-encoders-for-neural","title":"In defense of dual-encoders for neural ranking","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"isotropic-contextual-representations-through","title":"Isotropic Contextual Representations through Variational Regularization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-bilinear-temporal-spectral-fusion","title":"Iterative Bilinear Temporal-Spectral Fusion for Unsupervised Representation Learning in Time Series","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-model-pre-training-improves","title":"Language Model Pre-training Improves Generalization in Policy Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-lightweight-neural-networks-via","title":"Learning Lightweight Neural Networks via Channel-Split Recurrent Convolution","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-rate-grafting-transferability-of","title":"Learning Rate Grafting: Transferability of Optimizer Tuning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-schedule-learning-rate-with-graph","title":"Learning to Schedule Learning rate with Graph Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-visual-linguistic-adequacy-fidelity","title":"Learning Visual-Linguistic Adequacy, Fidelity, and Fluency for Novel Object Captioning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lmsa-low-relation-mutil-head-self-attention","title":"LMSA: Low-relation Mutil-head Self-Attention Mechanism in Visual Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/mait-integrating-spatial-locality-into-image","slug":"mait-integrating-spatial-locality-into-image","title":"MaiT: integrating spatial locality into image transformers with attention masks","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mapping-language-models-to-grounded","title":"Mapping Language Models to Grounded Conceptual Spaces","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"minimizing-memorization-in-meta-learning-a","title":"Minimizing Memorization in Meta-learning: A Causal Perspective","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mlp-based-architecture-with-variable-length","title":"MLP-based architecture with variable length input for automatic speech recognition","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-label-correlations-implicitly","title":"Modeling label correlations implicitly through latent label encodings for multi-label text classification","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-variational-dropout-processes","title":"Neural Variational Dropout Processes","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"non-autoregressive-models-are-better","title":"Non-Autoregressive Models are Better Multilingual Translators","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-pre-trained-multi-agent-decision","title":"Offline Pre-trained Multi-Agent Decision Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-reinforcement-learning-for-large","title":"Offline Reinforcement Learning for Large Scale Language Action Spaces","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"physical-system-design-using-hamiltonian","title":"Physical System Design Using Hamiltonian Monte Carlo over Learned Manifolds","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pretraining-for-language-conditioned","title":"Pretraining for Language Conditioned Imitation with Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/privacy-preserving-task-agnostic-vision","slug":"privacy-preserving-task-agnostic-vision","title":"Privacy-preserving Task-Agnostic Vision Transformer for Image Processing","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"rank4class-examining-multiclass","title":"Rank4Class: Examining Multiclass Classification through the Lens of Learning to Rank","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robot-intent-recognition-method-based-on","title":"Robot Intent Recognition Method Based on State Grid Business Office","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scala-speeding-up-fine-tuning-of-pre-trained","title":"ScaLA: Speeding-Up Fine-tuning of Pre-trained Transformer Networks via Efficient and Scalable Adversarial Perturbation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scale-efficiently-insights-from-pretraining","title":"Scale Efficiently: Insights from Pretraining and Finetuning Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-the-depth-of-vision-transformers-via","title":"Scaling the Depth of Vision Transformers via the Fourier Domain Analysis","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-offline-reinforcement","title":"Semi-supervised Offline Reinforcement Learning with Pre-trained Decision Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"seqpate-differentially-private-text","title":"SeqPATE: Differentially Private Text Generation via Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sit-simulation-transformer-for-particle-based","title":"SiT: Simulation Transformer for Particle-based Physics Simulation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spanning-tree-based-graph-generation-for","title":"Spanning Tree-based Graph Generation for Molecules","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-attention-with-learning-to-hash","title":"Sparse Attention with Learning to Hash","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"specialized-transformers-faster-smaller-and","title":"Specialized Transformers: Faster, Smaller and more Accurate NLP Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/subdimensional-expansion-using-attention","slug":"subdimensional-expansion-using-attention","title":"Subdimensional Expansion Using Attention-Based Learning For Multi-Agent Path Finding","date":"2021-09-29","arxiv_id":"2109.14695","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-action-localization-with-global","title":"Temporal Action Localization with Global Segmentation Mask Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"topic-aware-neural-language-model-domain","title":"Topic Aware Neural Language Model: Domain Adaptation of Unconditional Text Generation Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"training-sequence-labeling-models-using-prior","title":"Training sequence labeling models using prior knowledge","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transslowdown-efficiency-attacks-on-neural","title":"TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transtcn-an-attention-based-tcn-framework-for","title":"TransTCN: An Attention-based TCN Framework for Sequential Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"triangular-dropout-variable-network-width","title":"Triangular Dropout: Variable Network Width without Retraining","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tuformer-data-driven-design-of-expressive","title":"Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ufo-vit-high-performance-linear-vision","slug":"ufo-vit-high-performance-linear-vision","title":"UFO-ViT: High Performance Linear Vision Transformer without Softmax","date":"2021-09-29","arxiv_id":"2109.14382","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-role-of-self-attention-for","title":"Understanding the Role of Self Attention for Efficient Speech Recognition","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"video-forgery-detection-using-multiple-cues","title":"Video Forgery Detection Using Multiple Cues on Fusion of EfficientNet and Swin Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vut-versatile-ui-transformer-for-multimodal","title":"VUT: Versatile UI Transformer for Multimodal Multi-Task User Interface Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"zeroliers-diminishing-large-outliers-in-relu","title":"ZeroLiers: Diminishing Large Outliers in ReLU-like Activations","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-vision-transformers-for-the","title":"Fine-tuning Vision Transformers for the Prediction of State Variables in Ising Models","date":"2021-09-28","arxiv_id":"2109.13925","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-different-text-preprocessing-techniques","title":"How Different Text-preprocessing Techniques Using The BERT Model Affect The Gender Profiling of Authors","date":"2021-09-28","arxiv_id":"2109.13890","n_code_links":0,"syntology":null},{"paper":null,"slug":"msr-nv-neural-vocoder-using-multiple-sampling","title":"MSR-NV: Neural Vocoder Using Multiple Sampling Rates","date":"2021-09-28","arxiv_id":"2109.13714","n_code_links":0,"syntology":null},{"paper":null,"slug":"nana-hdr-a-non-attentive-non-autoregressive","title":"Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS","date":"2021-09-28","arxiv_id":"2109.13673","n_code_links":0,"syntology":null},{"paper":"/paper/raft-a-real-world-few-shot-text","slug":"raft-a-real-world-few-shot-text","title":"RAFT: A Real-World Few-Shot Text Classification Benchmark","date":"2021-09-28","arxiv_id":"2109.14076","n_code_links":1,"syntology":null},{"paper":"/paper/single-dataset-experts-for-multi-dataset","slug":"single-dataset-experts-for-multi-dataset","title":"Single-dataset Experts for Multi-dataset Question Answering","date":"2021-09-28","arxiv_id":"2109.13880","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":10,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/made"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"to-which-out-of-distribution-object","title":"Emergent Neural Network Mechanisms for Generalization to Objects in Novel Orientations","date":"2021-09-28","arxiv_id":"2109.13445","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-to-prioritize-natural-language","title":"What to Prioritize? Natural Language Processing for the Development of a Modern Bug Tracking Solution in Hardware Development","date":"2021-09-28","arxiv_id":"2109.13825","n_code_links":0,"syntology":null},{"paper":"/paper/who-explains-the-explanation-quantitatively","slug":"who-explains-the-explanation-quantitatively","title":"Focus! Rating XAI Methods and Finding Biases","date":"2021-09-28","arxiv_id":"2109.15035","n_code_links":1,"syntology":null},{"paper":null,"slug":"bayesian-deep-learning-of-affordances-from","title":"Bayesian deep learning of affordances from RGB images","date":"2021-09-27","arxiv_id":"2109.12845","n_code_links":0,"syntology":null},{"paper":"/paper/effective-use-of-graph-convolution-network","slug":"effective-use-of-graph-convolution-network","title":"Effective Use of Graph Convolution Network and Contextual Sub-Tree forCommodity News Event Extraction","date":"2021-09-27","arxiv_id":"2109.12781","n_code_links":1,"syntology":null},{"paper":"/paper/fast-md-fast-multi-decoder-end-to-end-speech","slug":"fast-md-fast-multi-decoder-end-to-end-speech","title":"Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates","date":"2021-09-27","arxiv_id":"2109.12804","n_code_links":1,"syntology":null},{"paper":"/paper/improving-stack-overflow-question-title","slug":"improving-stack-overflow-question-title","title":"Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information","date":"2021-09-27","arxiv_id":"2109.13073","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrated-training-for-sequence-to-sequence","title":"Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer","date":"2021-09-27","arxiv_id":"2109.12950","n_code_links":0,"syntology":null},{"paper":null,"slug":"introspective-robot-perception-using-smoothed","title":"Introspective Robot Perception using Smoothed Predictions from Bayesian Neural Networks","date":"2021-09-27","arxiv_id":"2109.12869","n_code_links":0,"syntology":null},{"paper":"/paper/optimising-for-interpretability-convolutional","slug":"optimising-for-interpretability-convolutional","title":"Optimising for Interpretability: Convolutional Dynamic Alignment Networks","date":"2021-09-27","arxiv_id":"2109.13004","n_code_links":1,"syntology":null},{"paper":"/paper/patterns-of-lexical-ambiguity-in","slug":"patterns-of-lexical-ambiguity-in","title":"Patterns of Lexical Ambiguity in Contextualised Language Models","date":"2021-09-27","arxiv_id":"2109.13032","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-spatial-transformers-for-few-shot","slug":"sparse-spatial-transformers-for-few-shot","title":"Sparse Spatial Transformers for Few-Shot Learning","date":"2021-09-27","arxiv_id":"2109.12932","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["chenhaoxing/ssformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/turingbench-a-benchmark-environment-for","slug":"turingbench-a-benchmark-environment-for","title":"TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation","date":"2021-09-27","arxiv_id":"2109.13296","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/understanding-and-overcoming-the-challenges","slug":"understanding-and-overcoming-the-challenges","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","date":"2021-09-27","arxiv_id":"2109.12948","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":["qualcomm-ai-research/transformer-quantization"],"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/improving-question-answering-performance","slug":"improving-question-answering-performance","title":"Improving Question Answering Performance Using Knowledge Distillation and Active Learning","date":"2021-09-26","arxiv_id":"2109.12662","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mirbostani/QA-KD-AL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-transformer-a-new-neural-network-based","slug":"multi-transformer-a-new-neural-network-based","title":"Multi-Transformer: A New Neural Network-Based Architecture for Forecasting S&P Volatility","date":"2021-09-26","arxiv_id":"2109.12621","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-prunability-of-attention-heads-in","title":"On the Prunability of Attention Heads in Multilingual BERT","date":"2021-09-26","arxiv_id":"2109.12683","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-refinements-for-lexically","slug":"parallel-refinements-for-lexically","title":"Parallel Refinements for Lexically Constrained Text Generation with BART","date":"2021-09-26","arxiv_id":"2109.12487","n_code_links":1,"syntology":null}],"record_sha256":"37e2b18c581c1dd94bd92dfa300a73ee7f3ca31e9a4a4df23b9f70b284555093","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}