Transformers

Transformers Learn Transition Dynamics when Trained to Predict Markov Decision Processes EMNLP 2024 Transformers@LT-EDI-EACL2024: Caste and Migration Hate Speech Detection in Tamil Using Ensembling on Transformers EACL 2024 Transformers need glasses! Information over-squashing in language tasks NeurIPS 2024 Transformers on Markov data: Constant depth suffices NeurIPS 2024 Transformers, parallel computation, and logarithmic depth ICML 2024 Transformer-specific Interpretability EACL 2024 Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot ICML 2024 Transformers Represent Belief State Geometry in their Residual Stream NeurIPS 2024 Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models NeurIPS 2024 Transformer-VQ: Linear-Time Transformers via Vector Quantization ICLR 2024 Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner NeurIPS 2024 TransGOP: Transformer-Based Gaze Object Prediction AAAI 2024 Translation Equivariant Transformer Neural Processes ICML 2024 TransLoc4D: Transformer-based 4D Radar Place Recognition CVPR 2024 Transmitted and Aggregated Self-Attention for Automatic Speech Recognition Interspeech 2024 Transolver: A Fast Transformer Solver for PDEs on General Geometries ICML 2024 TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic Segmentation WACV 2024 Tree Cross Attention ICLR 2024 Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision ACL 2024 Tree Transformer’s Disambiguation Ability of Prepositional Phrase Attachment and Garden Path Effects ACL 2024 Trends, Applications, and Challenges in Human Attention Modelling IJCAI 2024 T-Rep: Representation Learning for Time Series using Time-Embeddings ICLR 2024 Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers CVPR 2024 Triplet Attention Transformer for Spatiotemporal Predictive Learning WACV 2024 TSLANet: Rethinking Transformers for Time Series Representation Learning ICML 2024