{"total":198,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"area":null},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947,"area":null},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601,"area":null},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"area":null},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129,"area":null},{"id":"2311.05112","title":"A Survey of Large Language Models in Medicine: Progress, Application, and Challenge","created":"2023-11-09","cited_by_count":124,"area":null},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112,"area":null},{"id":"2104.03466","title":"Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT","created":"2021-04-08","cited_by_count":104,"area":null},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2111.04734","title":"Mixed Transformer U-Net For Medical Image Segmentation","created":"2021-11-08","cited_by_count":95,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2207.10315","title":"SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer","created":"2022-07-21","cited_by_count":83,"area":null},{"id":"2104.07705","title":"How to Train BERT with an Academic Budget","created":"2021-04-15","cited_by_count":80,"area":null},{"id":"2204.03409","title":"MAESTRO: Matched Speech Text Representations through Modality Matching","created":"2022-04-07","cited_by_count":79,"area":null},{"id":"2111.04076","title":"Direct Multi-view Multi-person 3D Pose Estimation","created":"2021-11-07","cited_by_count":64,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60,"area":null},{"id":"2108.08035","title":"Adaptive Graph Convolution for Point Cloud Analysis","created":"2021-08-18","cited_by_count":60,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2112.05132","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","created":"2021-12-09","cited_by_count":53,"area":null},{"id":"2107.03175","title":"A Survey on Dialogue Summarization: Recent Advances and New Frontiers","created":"2021-07-07","cited_by_count":51,"area":null},{"id":"2401.06197","title":"Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2105.09259","title":"Learning Language Specific Sub-network for Multilingual Machine Translation","created":"2021-05-19","cited_by_count":48,"area":null},{"id":"2111.03945","title":"Towards Building ASR Systems for the Next Billion Users","created":"2021-11-06","cited_by_count":47,"area":null},{"id":"2105.14462","title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","created":"2021-05-30","cited_by_count":44,"area":null},{"id":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44,"area":null},{"id":"2101.00234","title":"Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers","created":"2021-01-01","cited_by_count":43,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2303.14651","title":"You Only Segment Once: Towards Real-Time Panoptic Segmentation","created":"2023-03-26","cited_by_count":40,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2106.01401","title":"Container: Context Aggregation Network","created":"2021-06-02","cited_by_count":37,"area":null},{"id":"2109.04588","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","created":"2021-09-09","cited_by_count":35,"area":null},{"id":"2106.08556","title":"Coreference-Aware Dialogue Summarization","created":"2021-06-16","cited_by_count":34,"area":null},{"id":"2105.06548","title":"Not All Memories are Created Equal: Learning to Forget by Expiring","created":"2021-05-13","cited_by_count":32,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2304.11523","title":"TransFlow: Transformer as Flow Learner","created":"2023-04-23","cited_by_count":32,"area":null},{"id":"2102.02340","title":"MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records","created":"2021-02-03","cited_by_count":30,"area":null},{"id":"2103.16748","title":"Dual Contrastive Loss and Attention for GANs","created":"2021-03-31","cited_by_count":30,"area":null},{"id":"2208.02879","title":"PointConvFormer: Revenge of the Point-based Convolution","created":"2022-08-04","cited_by_count":30,"area":null},{"id":"2103.13597","title":"Mask Attention Networks: Rethinking and Strengthen Transformer","created":"2021-03-25","cited_by_count":28,"area":null},{"id":"2105.03322","title":"Are Pre-trained Convolutions Better than Pre-trained Transformers?","created":"2021-05-07","cited_by_count":27,"area":null},{"id":"2105.14064","title":"Controllable Abstractive Dialogue Summarization with Sketch Supervision","created":"2021-05-28","cited_by_count":27,"area":null},{"id":"2108.09301","title":"Discriminative Region-based Multi-Label Zero-Shot Learning","created":"2021-08-20","cited_by_count":27,"area":null},{"id":"2110.08743","title":"GNN-LM: Language Modeling based on Global Contexts via GNN","created":"2021-10-17","cited_by_count":27,"area":null},{"id":"2209.00860","title":"Real-time 3D Single Object Tracking with Transformer","created":"2022-09-02","cited_by_count":27,"area":null},{"id":"2109.04994","title":"Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization","created":"2021-09-10","cited_by_count":23,"area":null},{"id":"2112.04863","title":"3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis","created":"2021-12-09","cited_by_count":23,"area":null},{"id":"2301.07851","title":"From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition","created":"2023-01-19","cited_by_count":23,"area":null},{"id":"2108.11333","title":"Lightweight Self-Attentive Sequential Recommendation","created":"2021-08-25","cited_by_count":22,"area":null},{"id":"2301.08880","title":"A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement","created":"2023-01-21","cited_by_count":22,"area":null},{"id":"2107.05790","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","created":"2021-07-13","cited_by_count":21,"area":null},{"id":"2107.07445","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","created":"2021-07-15","cited_by_count":21,"area":null},{"id":"2202.07959","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","created":"2022-02-16","cited_by_count":21,"area":null},{"id":"2305.15099","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2109.04080","title":"Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2305.01638","title":"Sequence Modeling with Multiresolution Convolutional Memory","created":"2023-05-02","cited_by_count":19,"area":null},{"id":"2104.01481","title":"Do We Need Anisotropic Graph Neural Networks?","created":"2021-04-03","cited_by_count":18,"area":null},{"id":"2104.04923","title":"Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog","created":"2021-04-11","cited_by_count":17,"area":null},{"id":"2105.13072","title":"TranSmart: A Practical Interactive Machine Translation System","created":"2021-05-27","cited_by_count":17,"area":null},{"id":"2106.00941","title":"Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation","created":"2021-06-02","cited_by_count":17,"area":null},{"id":"2109.07780","title":"Improving Neural Machine Translation by Bidirectional Training","created":"2021-09-16","cited_by_count":17,"area":null},{"id":"2310.08049","title":"Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability","created":"2023-10-12","cited_by_count":17,"area":null},{"id":"2106.08630","title":"HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2106.13627","title":"Language Models are Good Translators","created":"2021-06-25","cited_by_count":16,"area":null},{"id":"2207.02796","title":"Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution","created":"2022-07-06","cited_by_count":16,"area":null},{"id":"2208.00399","title":"Neural Knowledge Bank for Pretrained Transformers","created":"2022-07-31","cited_by_count":16,"area":null},{"id":"2210.15497","title":"LSG Attention: Extrapolation of pretrained Transformers to long sequences","created":"2022-10-13","cited_by_count":16,"area":null},{"id":"2101.09115","title":"The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT","created":"2021-01-22","cited_by_count":15,"area":null},{"id":"2209.00930","title":"Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization","created":"2022-09-02","cited_by_count":14,"area":null},{"id":"2211.12148","title":"Aligning Source Visual and Target Language Domains for Unpaired Video Captioning","created":"2022-11-22","cited_by_count":14,"area":null},{"id":"2105.14669","title":"Memory-Efficient Differentiable Transformer Architecture Search","created":"2021-05-31","cited_by_count":13,"area":null},{"id":"2201.00625","title":"GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings","created":"2022-01-03","cited_by_count":13,"area":null},{"id":"2206.04665","title":"AGConv: Adaptive Graph Convolution on 3D Point Clouds","created":"2022-06-09","cited_by_count":13,"area":null},{"id":"2208.01182","title":"Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning","created":"2022-08-02","cited_by_count":13,"area":null},{"id":"2210.10027","title":"Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2106.03297","title":"On the Language Coverage Bias for Neural Machine Translation","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2106.15338","title":"Probabilistic Attention for Interactive Segmentation","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2109.07383","title":"RankNAS: Efficient Neural Architecture Search by Pairwise Ranking","created":"2021-09-15","cited_by_count":12,"area":null},{"id":"2209.11750","title":"Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition","created":"2022-09-22","cited_by_count":12,"area":null},{"id":"2104.04946","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","created":"2021-04-11","cited_by_count":11,"area":null},{"id":"2106.05505","title":"Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models","created":"2021-06-10","cited_by_count":11,"area":null},{"id":"2212.13023","title":"Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal","created":"2022-12-26","cited_by_count":11,"area":null},{"id":"2301.09008","title":"Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference","created":"2023-01-21","cited_by_count":11,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2207.14467","title":"GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation","created":"2022-07-29","cited_by_count":10,"area":null}],"next_cursor":"100"}