| ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer | Mar 8, 2022 | Image Classificationobject-detection | CodeCode Available | 2 |
| Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation | Aug 27, 2021 | Inductive BiasPlaying the Game of 2048 | CodeCode Available | 2 |
| FLAT: Chinese NER Using Flat-Lattice Transformer | Apr 24, 2020 | Chinese Named Entity Recognitionnamed-entity-recognition | CodeCode Available | 2 |
| MPNet: Masked and Permuted Pre-training for Language Understanding | Apr 20, 2020 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation | Mar 17, 2020 | image-classificationImage Classification | CodeCode Available | 2 |
| Machine Learning in Asset Management—Part 1: Portfolio Construction—Trading Strategies | Feb 10, 2020 | Algorithmic TradingAsset Management | CodeCode Available | 2 |
| R-FCN-3000 at 30fps: Decoupling Detection and Classification | Dec 5, 2017 | ClassificationGeneral Classification | CodeCode Available | 2 |
| SeqPE: Transformer with Sequential Position Encoding | Jun 16, 2025 | image-classificationImage Classification | CodeCode Available | 1 |
| ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices | Jun 4, 2025 | Position | CodeCode Available | 1 |
| POSS: Position Specialist Generates Better Draft for Speculative Decoding | Jun 4, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
