Deep Learning

RNCA: Self-Repairing Segmentation Masks MIDL 2026 RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations CVPR 2026 RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models CVPR 2026 RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding WACV 2026 RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction CVPR 2026 Robertha: Eigenspectrum Regularized Attention for Robust Natural Language Understanding ACL 2026 RoboAgent: Chaining Basic Capabilities for Embodied Task Planning CVPR 2026 Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation CVPR 2026 RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning CVPR 2026 RoBSA: RoPE-based Blockwise Sparse Multi-head Latent Attention ACL 2026 Robust Detection of Synthetic Tabular Data Under Schema Variability AAAI 2026 RobustFormer: Noise-Robust Pre-training for Images and Videos WACV 2026 Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions AAAI 2026 Robust Multi-Scale Implicit Neural Representations for Large-Deformation Lung Registration MIDL 2026 Robustness Under Data Scarcity: Few-Shot Continual Adversarial Training for Evolving Threats CVPR 2026 Robust Promptable Video Object Segmentation CVPR 2026 Robust Pseudo-Labeling via Decoupled Class-Aware Filtering and Dynamic Category Correction AAAI 2026 Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion AAAI 2026 Robust Spiking Neural Networks by Temporal Mutual Information CVPR 2026 Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss JMLR 2026 Role Hypergraph Contrastive Learning for Multivariate Time-Series Analysis AAAI 2026 Role Perceptual Augmented Temporal Graph Network for Related-party Transaction Detection AAAI 2026 Role-SynthCLIP: A Role-Play Driven Diverse Synthetic Data Approach CVPR 2026 RollPacker: Taming Long-Tail Rollouts for RL Post-Training with Tail Batching NSDI 2026 RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation CVPR 2026