Representation Learning

Understanding Subword Compositionality of Large Language Models EMNLP 2025 Understanding Synthetic Context Extension via Retrieval Heads ICML 2025 Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models EMNLP 2025 Understanding the Repeat Curse in Large Language Models from a Feature Perspective ACL 2025 UnDIVE: Generalized Underwater Video Enhancement using Generative Priors WACV 2025 Unfolding-Associative Encoder-Decoder Network with Progressive Alignment for Pansharpening ICCV 2025 Unhackable Temporal Reward for Scalable Video MLLMs ICLR 2025 UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block IJCAI 2025 Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data ICML 2025 Unified Molecule-Text Language Model with Discrete Token Representation IJCAI 2025 Unified Multi-Agent Trajectory Modeling with Masked Trajectory Diffusion ICCV 2025 Unified Video Action Model RSS 2025 Uniform Information Density and Syntactic Reduction: Revisiting *that*-Mentioning in English Complement Clauses EMNLP 2025 UniFuse: A Unified All-in-One Framework for Multi-Modal Medical Image Fusion Under Diverse Degradations and Misalignments ICCV 2025 Unifying Specialized Visual Encoders for Video Language Models ICML 2025 UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting ICLR 2025 UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design ICML 2025 UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing CVPR 2025 UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting CVPR 2025 Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion CVPR 2025 UniRestore3D: A Scalable Framework For General Shape Restoration ICLR 2025 UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines CVPR 2025 UniTR: A Unified Framework for Joint Representation Learning of Trajectories and Road Networks AAAI 2025 Universal Actions for Enhanced Embodied Foundation Models CVPR 2025 Universal Graph Self-Contrastive Learning IJCAI 2025