SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning.- Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents.- Rethinking Fast Adversarial Training: A Splitting Technique To Overcome Catastrophic Overfitting.- Quality Assured: Rethinking Annotation Strategies in Imaging AI.- BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues.- Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder.- Weakly-Supervised 3D Hand Reconstruction with Knowledge Prior and Uncertainty Guidance.- 3D Reconstruction of Objects in Hands without Real World 3D Supervision.- To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning.- Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer.- 3D Hand Pose Estimation in Everyday Egocentric Images.- Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops.- Towards Neuro-Symbolic Video Understanding.- Optimization-based Uncertainty Attribution Via Learning Informative Perturbations.- Context-Aware Action Recognition: Introducing a Comprehensive Dataset for Behavior Contrast.- Semi-supervised Segmentation of Histopathology Images with Noise-Aware Topological Consistency.- Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling.- Instant Uncertainty Calibration of NeRFs Using a Meta-Calibrator.- MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks.- Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training.- Data Augmentation via Latent Diffusion for Saliency Prediction.- Explorative Inbetweening of Time and Space.- A Diffusion Model for Simulation Ready Coronary Anatomy with Morpho-skeletal Control.- Learning to Make Keypoints Sub-Pixel Accurate.- Imaging with Confidence: Uncertainty Quantification for High-dimensional Undersampled MR Images.- Generalizable Human Gaussians for Sparse View Synthesis.- DrivingDiffusion: Layout-Guided Multi-View Driving Scenarios Video Generation with Latent Diffusion Model.