Transformers

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features ICML 2025 Concept-pedia: a Wide-coverage Semantically-annotated Multimodal Dataset EMNLP 2025 Conditional Dichotomy Quantification via Geometric Embedding ACL 2025 Conditional Information Bottleneck-Based Multivariate Time Series Forecasting IJCAI 2025 Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers AAAI 2025 ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning AAAI 2025 Conformer-based Ultrasound-to-Speech Conversion Interspeech 2025 Confounder-Free Continual Learning via Recursive Feature Normalization ICML 2025 ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking AAAI 2025 Consensus Is All You Get: The Role of Attention in Transformers ICML 2025 Constrained Belief Updates Explain Geometric Structures in Transformer Representations ICML 2025 Construction of NER Model in Ancient Chinese: Solution of EvaHan 2025 Challenge NAACL 2025 Content-aware Balanced Spectrum Encoding in Masked Modeling for Time Series Classification AAAI 2025 Context-aware Biases for Length Extrapolation EMNLP 2025 Context Guided Transformer Entropy Modeling for Video Compression ICCV 2025 ContextHOI: Spatial Context Learning for Human-Object Interaction Detection AAAI 2025 Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images ICML 2025 Contextual Selection of Pseudo-terminology Constraints for Terminology-aware Neural Machine Translation in the IT Domain EMNLP 2025 Continual SFT Matches Multimodal RLHF with Negative Supervision CVPR 2025 Continuous 3D Perception Model with Persistent State CVPR 2025 Continuous-Time Attention: PDE-Guided Mechanisms for Long-Sequence Transformers EMNLP 2025 Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers UAI 2025 Contrastive Multi-view Subspace Clustering via Tensor Transformers Autoencoder AAAI 2025 ControlAR: Controllable Image Generation with Autoregressive Models ICLR 2025 Controllable Generation via Locally Constrained Resampling ICLR 2025