Transformers

Singularformer: Learning to Decompose Self-Attention to Linearize the Complexity of Transformer IJCAI 2023 SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token EMNLP 2023 SJTU-MTLAB’s Submission to the WMT23 Word-Level Auto Completion Task EMNLP 2023 Skill Transformer: A Monolithic Policy for Mobile Manipulation ICCV 2023 Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention CVPR 2023 SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models ICLR 2023 Slot-guided Volumetric Object Radiance Fields NeurIPS 2023 SLViT: Scale-Wise Language-Guided Vision Transformer for Referring Image Segmentation IJCAI 2023 Small Transformers Compute Universal Metric Embeddings JMLR 2023 SMMix: Self-Motivated Image Mixing for Vision Transformers ICCV 2023 SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process ICML 2023 Solving Math Word Problems concerning Systems of Equations with GPT-3 AAAI 2023 Span-level Aspect-based Sentiment Analysis via Table Filling ACL 2023 Span-Selective Linear Attention Transformers for Effective and Robust Schema-Guided Dialogue State Tracking ACL 2023 Sparse Frame Grouping Network with Action Centered for Untrimmed Video Paragraph Captioning EMNLP 2023 SparseMAE: Sparse Training Meets Masked Autoencoders ICCV 2023 Sparse Mixture-of-Experts are Domain Generalizable Learners ICLR 2023 Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers ICLR 2023 Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images CVPR 2023 SparsePose: Sparse-View Camera Pose Regression and Refinement CVPR 2023 Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks ICCV 2023 Sparse Token Transformer with Attention Back Tracking ICLR 2023 Sparse Universal Transformer EMNLP 2023 Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers CVPR 2023 Spatial-Aware Token for Weakly Supervised Object Localization ICCV 2023