cross attention

Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling ICML 2025 EmoSpeechAuth: Emotion-Aware Speaker Verification Interspeech 2025 Enabling Long(er) Horizon Imitation for Manipulation Tasks by Modeling Subgoal Transitions CoRL 2025 Griffin: Towards a Graph-Centric Relational Database Foundation Model ICML 2025 Grounding Continuous Representations in Geometry: Equivariant Neural Fields ICLR 2025 Instruct2See: Learning to Remove Any Obstructions Across Distributions ICML 2025 Learned Image Compression with Dictionary-based Entropy Model CVPR 2025 LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models ICML 2025 MediVLM: A Vision Language Model for Radiology Report Generation from Medical Images EMNLP 2025 On Understanding Attention-Based In-Context Learning for Categorical Data ICML 2025 Parrot: Multilingual Visual Instruction Tuning ICML 2025 Personalized Preference Fine-tuning of Diffusion Models CVPR 2025 SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields ICML 2025 The Source Image is the Best Attention for Infrared and Visible Image Fusion ICCV 2025 Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation CVPR 2025 Unifying Specialized Visual Encoders for Video Language Models ICML 2025 XAttnMark: Learning Robust Audio Watermarking with Cross-Attention ICML 2025 Alignment before Awareness: Towards Visual Question Localized-Answering in Robotic Surgery via Optimal Transport and Answer Semantics COLING 2024 C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction CVPR 2024 Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR NAACL 2024 Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement NeurIPS 2024 ECSIC: Epipolar Cross Attention for Stereo Image Compression WACV 2024 GeoMFormer: A General Architecture for Geometric Molecular Representation Learning ICML 2024 Hybrid Mamba for Few-Shot Segmentation NeurIPS 2024 IDC: Boost Text-to-image Retrieval via Indirect and Direct Connections COLING 2024