{"total":552,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723,"area":null},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218,"area":"wm"},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081,"area":null},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601,"area":null},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552,"area":null},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497,"area":null},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291,"area":null},{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217,"area":null},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207,"area":null},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150,"area":null},{"id":"2211.12254","title":"SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields","created":"2022-11-22","cited_by_count":144,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2209.09002","title":"MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation","created":"2022-09-19","cited_by_count":125,"area":null},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"area":"lr"},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113,"area":null},{"id":"2105.14686","title":"Fully Hyperbolic Neural Networks","created":"2021-05-31","cited_by_count":108,"area":null},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","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":"2105.10311","title":"Pretrained Language Models for Text Generation: A Survey","created":"2021-05-21","cited_by_count":95,"area":null},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93,"area":null},{"id":"2302.03162","title":"Protecting Language Generation Models via Invisible Watermarking","created":"2023-02-06","cited_by_count":90,"area":"safety"},{"id":"2103.00073","title":"CURE: Code-Aware Neural Machine Translation for Automatic Program Repair","created":"2021-02-26","cited_by_count":86,"area":null},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86,"area":null},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86,"area":null},{"id":"2110.04573","title":"Space-Time-Separable Graph Convolutional Network for Pose Forecasting","created":"2021-10-09","cited_by_count":84,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2204.00559","title":"DFNet: Enhance Absolute Pose Regression with Direct Feature Matching","created":"2022-04-01","cited_by_count":82,"area":null},{"id":"2209.08773","title":"CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks","created":"2022-09-19","cited_by_count":76,"area":"safety"},{"id":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"area":null},{"id":"2104.06954","title":"Aligning Latent and Image Spaces to Connect the Unconnectable","created":"2021-04-14","cited_by_count":70,"area":null},{"id":"2105.13137","title":"Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future","created":"2021-05-27","cited_by_count":67,"area":null},{"id":"2409.19407","title":"Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking","created":"2024-09-28","cited_by_count":65,"area":null},{"id":"2307.11833","title":"PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks","created":"2023-07-21","cited_by_count":64,"area":null},{"id":"2106.09876","title":"Anomaly Detection in Dynamic Graphs via Transformer","created":"2021-06-18","cited_by_count":59,"area":null},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58,"area":"distill"},{"id":"2305.09860","title":"Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation","created":"2023-05-17","cited_by_count":58,"area":null},{"id":"2405.18719","title":"Contextual Position Encoding: Learning to Count What's Important","created":"2024-05-29","cited_by_count":54,"area":null},{"id":"2308.08947","title":"Watch Your Steps: Local Image and Scene Editing by Text Instructions","created":"2023-08-17","cited_by_count":50,"area":"diffusion"},{"id":"2402.04494","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","created":"2024-02-07","cited_by_count":49,"area":null},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2112.11174","title":"AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version","created":"2021-12-21","cited_by_count":48,"area":null},{"id":"2205.10683","title":"Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy","created":"2022-05-21","cited_by_count":48,"area":null},{"id":"2112.06174","title":"Implicit Transformer Network for Screen Content Image Continuous Super-Resolution","created":"2021-12-12","cited_by_count":46,"area":null},{"id":"2205.01138","title":"Transformers in Time-series Analysis: A Tutorial","created":"2022-04-28","cited_by_count":46,"area":null},{"id":"2401.13537","title":"Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models","created":"2024-01-24","cited_by_count":46,"area":null},{"id":"2203.02225","title":"ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification","created":"2022-03-04","cited_by_count":45,"area":null},{"id":"2107.02380","title":"Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification","created":"2021-07-06","cited_by_count":44,"area":null},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44,"area":null},{"id":"2309.06057","title":"RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair","created":"2023-09-12","cited_by_count":44,"area":"rag"},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2107.05214","title":"Split, embed and merge: An accurate table structure recognizer","created":"2021-07-12","cited_by_count":42,"area":null},{"id":"2102.02810","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","created":"2021-02-04","cited_by_count":41,"area":null},{"id":"2105.12485","title":"TreeBERT: A Tree-Based Pre-Trained Model for Programming Language","created":"2021-05-26","cited_by_count":41,"area":null},{"id":"2304.12760","title":"Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies","created":"2023-04-25","cited_by_count":41,"area":null},{"id":"2304.09677","title":"Reference-guided Controllable Inpainting of Neural Radiance Fields","created":"2023-04-19","cited_by_count":40,"area":null},{"id":"2110.03864","title":"Boundary-aware Transformers for Skin Lesion Segmentation","created":"2021-10-08","cited_by_count":39,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2207.01583","title":"LaTeRF: Label and Text Driven Object Radiance Fields","created":"2022-07-04","cited_by_count":38,"area":null},{"id":"2403.14852","title":"KeyPoint Relative Position Encoding for Face Recognition","created":"2024-03-21","cited_by_count":38,"area":null},{"id":"2105.08399","title":"Relative Positional Encoding for Transformers with Linear Complexity","created":"2021-05-18","cited_by_count":37,"area":null},{"id":"2105.14528","title":"Fast Nearest Neighbor Machine Translation","created":"2021-05-30","cited_by_count":37,"area":null},{"id":"2107.02561","title":"Rethinking Positional Encoding","created":"2021-07-06","cited_by_count":37,"area":null},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2102.08220","title":"Non-Autoregressive Text Generation with Pre-trained Language Models","created":"2021-02-16","cited_by_count":36,"area":null},{"id":"2208.00949","title":"VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations","created":"2022-08-01","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2111.11108","title":"Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version","created":"2021-11-22","cited_by_count":35,"area":null},{"id":"2303.08134","title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","created":"2023-03-14","cited_by_count":34,"area":null},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"id":"2107.09846","title":"Guided Generation of Cause and Effect","created":"2021-07-21","cited_by_count":33,"area":null},{"id":"2205.12551","title":"Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers","created":"2022-05-25","cited_by_count":33,"area":null},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2212.01117","title":"Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning","created":"2022-12-02","cited_by_count":32,"area":null},{"id":"2109.01135","title":"Sequence-to-Sequence Learning with Latent Neural Grammars","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2208.04441","title":"Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks","created":"2022-08-08","cited_by_count":30,"area":null},{"id":"2210.03765","title":"Visualize Before You Write: Imagination-Guided Open-Ended Text Generation","created":"2022-10-07","cited_by_count":30,"area":null},{"id":"2102.12152","title":"Dual-Awareness Attention for Few-Shot Object Detection","created":"2021-02-24","cited_by_count":29,"area":null},{"id":"2106.07930","title":"Language Tags Matter for Zero-Shot Neural Machine Translation","created":"2021-06-15","cited_by_count":29,"area":null},{"id":"2203.01824","title":"LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network","created":"2022-03-03","cited_by_count":29,"area":null},{"id":"2208.05908","title":"Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks","created":"2022-08-11","cited_by_count":29,"area":null},{"id":"2106.03993","title":"Lexicon Learning for Few-Shot Neural Sequence Modeling","created":"2021-06-07","cited_by_count":28,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"id":"2110.12661","title":"ZerO Initialization: Initializing Neural Networks with only Zeros and Ones","created":"2021-10-25","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}],"next_cursor":"100"}