{"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/184","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":184,"pages_in_order":244,"rows_per_page":100,"rows":[18301,18400],"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/183","next":"/method/adam/papers/185","papers":[{"paper":"/paper/scientific-evidence-extraction","slug":"scientific-evidence-extraction","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","date":"2021-09-30","arxiv_id":"2110.00061","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/table-transformer"],"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":["listed","official"]}}},{"paper":"/paper/syntactic-persistence-in-language-models","slug":"syntactic-persistence-in-language-models","title":"Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations","date":"2021-09-30","arxiv_id":"2109.14989","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-collaborative-attention-adaptive-network","title":"A Collaborative Attention Adaptive Network for Financial Market Forecasting","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-dot-product-attention-free-transformer","slug":"a-dot-product-attention-free-transformer","title":"A Dot Product Attention Free Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adam-is-no-better-than-normalized-sgd","title":"Adam is no better than normalized SGD: Dissecting how adaptivity improves GAN performance","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-control-flow-in-transformers","title":"Adaptive Control Flow in Transformers Improves Systematic Generalization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-inertia-disentangling-the-effects-of","title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-wavelet-transformer-network-for-3d","title":"Adaptive Wavelet Transformer Network for 3D Shape Representation Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-investigation-on-hardware-aware-vision","title":"An Investigation on Hardware-Aware Vision Transformer Scaling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-object-centric-sensitivity-analysis-of","title":"An object-centric sensitivity analysis of deep learning based instance segmentation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-implicit-position-encoding","title":"Analyzing the Implicit Position Encoding Ability of Transformer Decoder","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-bert-families-zero-shot-learners-a-study","title":"Are BERT Families Zero-Shot Learners? A Study on Their Potential and Limitations","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-vision-transformers-robust-to-patch-wise","title":"Are Vision Transformers Robust to Patch-wise Perturbations?","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"associated-learning-an-alternative-to-end-to","title":"Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-based-interpretability-with-concept","title":"Attention-based Interpretability with Concept Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-lottery-speech-recognition-made-ultra","title":"Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bootstrapped-hindsight-experience-replay-with","title":"Bootstrapped Hindsight Experience replay with Counterintuitive Prioritization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"coarformer-transformer-for-large-graph-via","title":"Coarformer: Transformer for large graph via graph coarsening","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"collaborative-storytelling-with-human-actors","title":"Collaborative Storytelling with Human Actors and AI Narrators","date":"2021-09-29","arxiv_id":"2109.14728","n_code_links":0,"syntology":null},{"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":"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":"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":"dynamic-regret-analysis-for-online-meta","title":"Dynamic Regret Analysis for Online Meta-Learning","date":"2021-09-29","arxiv_id":"2109.14375","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":"experience-replay-more-when-it-s-a-key","title":"Experience Replay More When It's a Key Transition in Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/explanation-aware-experience-replay-in-rule","slug":"explanation-aware-experience-replay-in-rule","title":"Explanation-Aware Experience Replay in Rule-Dense Environments","date":"2021-09-29","arxiv_id":"2109.14711","n_code_links":1,"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":"faster-reinforcement-learning-with-value","title":"Faster Reinforcement Learning with Value Target Lower Bounding","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":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":"l-sr1-adaptive-regularization-by-cubics-for","title":"L-SR1 Adaptive Regularization by Cubics for Deep Learning","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-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":"meta-attention-for-off-policy-actor-critic","title":"Meta Attention For Off-Policy Actor-Critic","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":"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":"numerical-solution-of-fredholm-integral","title":"Numerical Solution of Fredholm Integral Equations of the Second Kind using Neural Network Models","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":"on-the-one-sided-convergence-of-adam-type","title":"On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization","date":"2021-09-29","arxiv_id":"2109.14213","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":"robust-and-data-efficient-q-learning-by","title":"Robust and Data-efficient Q-learning by Composite Value-estimation","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":"sparse-unbalanced-gan-training-with-in-time","title":"Sparse Unbalanced GAN Training with In-Time Over-Parameterization","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":null,"slug":"spp-rl-state-planning-policy-reinforcement","title":"SPP-RL: State Planning Policy Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spsc-a-fast-and-provable-algorithm-for","title":"SpSC: A Fast and Provable Algorithm for Sampling-Based GNN Training","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":"transliteration-a-simple-technique-for","title":"Transliteration: A Simple Technique For Improving Multilingual Language Modeling","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":"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":"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":"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"]}}}],"record_sha256":"c2d4f604d6bbd8c57d9c6ca7a7af1b2d46a1f900658af73ec4d51966d220d6ef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}