Deep Learning

Denoising with a Joint-Embedding Predictive Architecture ICLR 2025 De Novo Molecular and Crystal Design with Latent Space Bayesian Optimization AAAI 2025 Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation ICCV 2025 Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration AAAI 2025 Dense Depth from Event Focal Stack WACV 2025 DenseLoRA: Dense Low-Rank Adaptation of Large Language Models ACL 2025 Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation AAAI 2025 DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo ICLR 2025 Dense Policy: Bidirectional Autoregressive Learning of Actions ICCV 2025 Dense Retrieval with Quantity Comparison Intent ACL 2025 Density Estimation Using the Perceptron JMLR 2025 Density Ratio Estimation with Conditional Probability Paths ICML 2025 DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation CVPR 2025 DEPfold: RNA Secondary Structure Prediction as Dependency Parsing. ICLR 2025 Deploying Multi-task Online Server with Large Language Model COLING 2025 Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices EMNLP 2025 DepMGNN: Matrixial Graph Neural Network for Video-based Automatic Depression Assessment AAAI 2025 DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion ICCV 2025 DepressGEN: Synthetic Data Generation Framework for Depression Detection Interspeech 2025 Depression Detection on Social Media with Large Language Models EMNLP 2025 Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation ICCV 2025 Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation ICCV 2025 Depth Any Video with Scalable Synthetic Data ICLR 2025 DepthART: Monocular Depth Estimation as Autoregressive Refinement Task IJCAI 2025 DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos CVPR 2025