Transformers

Weight decay induces low-rank attention layers NeurIPS 2024 Weighted Layer Averaging RoBERTa for Black-Box Machine-Generated Text Detection SemEval 2024 What Are You Token About? Differentiable Perturbed Top-k Token Selection for Scientific Document Summarization ACL 2024 What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks ICML 2024 What Do Transformers Know about Government? COLING 2024 What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages ACL 2024 What Makes Language Models Good-enough? ACL 2024 What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information NeurIPS 2024 What’s Mine becomes Yours: Defining, Annotating and Detecting Context-Dependent Paraphrases in News Interview Dialogs EMNLP 2024 When can transformers reason with abstract symbols? ICLR 2024 When Is a Name Sensitive? Eponyms in Clinical Text and Implications for De-Identification EACL 2024 When should we prefer Decision Transformers for Offline Reinforcement Learning? ICLR 2024 When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation CVPR 2024 When Will Gradient Regularization Be Harmful? ICML 2024 Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing EMNLP 2024 White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? JMLR 2024 Why are Sensitive Functions Hard for Transformers? ACL 2024 Why are Visually-Grounded Language Models Bad at Image Classification? NeurIPS 2024 Why Transformers Need Adam: A Hessian Perspective NeurIPS 2024 WildlifeDatasets: An Open-Source Toolkit for Animal Re-Identification WACV 2024 Window Attention is Bugged: How not to Interpolate Position Embeddings ICLR 2024 Win-Win: Training High-Resolution Vision Transformers from Two Windows ICLR 2024 WMT24 System Description for the MultiIndic22MT Shared Task on Manipuri Language EMNLP 2024 Word-Conditioned 3D American Sign Language Motion Generation EMNLP 2024 Word Sense Disambiguation as a Game of Neurosymbolic Darts COLING 2024