Transformers

T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data ICLR 2025 TLPIQ at BioLaySumm: Hide and Seq, a FLAN-T5 Model for Biomedical Summarization ACL 2025 Token-based Decision Criteria Are Suboptimal in In-context Learning NAACL 2025 TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm WACV 2025 Token Coordinated Prompt Attention is Needed for Visual Prompting ICML 2025 Token Cropr: Faster ViTs for Quite a Few Tasks CVPR 2025 TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation CVPR 2025 TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters ICLR 2025 TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization CVPR 2025 Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation AAAI 2025 Tokenization is Sensitive to Language Variation ACL 2025 Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images CVPR 2025 TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation CVPR 2025 Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification AAAI 2025 Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction ICLR 2025 Token Turing Machines are Efficient Vision Models WACV 2025 TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation ICCV 2025 ToMA: Token Merge with Attention for Diffusion Models ICML 2025 Too Helpful, Too Harmless, Too Honest or Just Right? EMNLP 2025 Tooka-SBERT: Lightweight Sentence Embedding models for Persian IJCNLP 2025 TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning ICLR 2025 TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression CVPR 2025 TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model CVPR 2025 Tora: Trajectory-oriented Diffusion Transformer for Video Generation CVPR 2025 TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration WACV 2025