Skip to main content

VinUniversity

2 related articles

Subscribe to updates

arXiv Nov 9, 2026
ScanDreamer gives quadrotors an online map to imagine with: 96.3% success and 3.6% collisions in unseen simulated layouts
For quadrotor navigation through unknown clutter, ScanDreamer builds an online 2D scan-memory map from depth images and vehicle pose, and conditions its world model, actor and critic on that map, so imagined rollouts advance the pose over a frozen map and read geodesic progress and wall-contact signals from mapped geometry. Across 1560 test episodes in NVIDIA Isaac Sim spanning unseen layouts and parameter ranges, three seeds average 96.3% success and 3.6% collisions, against 59.6% success and 28.8% collisions for AirDreamer at the same online-interaction budget.
For quadrotor navigation through unknown clutter, ScanDreamer builds an online 2D scan-memory map from depth images and vehicle pose, and conditions its world model, actor and critic on that map, so imagined rollouts advance the pose over a frozen map and read geodesic progress and wall-contact signals from mapped geometry. Across 1560 test episodes in NVIDIA Isaac Sim spanning unseen layouts and parameter ranges, three seeds average 96.3% success and 3.6% collisions, against 59.6% success and 28.8% collisions for AirDreamer at the same online-interaction budget.
Nanyang Technological University VinUniversity
Yunyi Gao（First author）
ScanDreamer Quadrotor Navigation World Model Occupancy Mapping Model-Based Reinforcement Learning
arXiv Oct 25, 2026
CT-to-MRI synthesis without 3D diffusion: StaX-Net shares interleaved 2D blocks and reaches an abdominal perceptual distance of 642.1, below Pix2Pix
Cross-modality medical image translation has been troubled by anatomically inconsistent synthesis, and standard generative adversarial networks update generator and discriminator together, letting opposing gradients pull on shared representations. StaX-Net interleaves multi-scale computational blocks between the generator and discriminator, lets the discriminator update first while shared blocks are frozen during the generator step, and uses target MRI only during training to guide a feature transform. On the Abdomen/Pelvis, Head and Neck, and Thorax subsets of SynthRAD 2025 it is compared with five baselines, reaching an Abdomen/Pelvis VGG perceptual distance of 642.1, below Pix2Pix at 991.2 and UNet-AE at 1687.9.
Cross-modality medical image translation has been troubled by anatomically inconsistent synthesis, and standard generative adversarial networks update generator and discriminator together, letting opposing gradients pull on shared representations. StaX-Net interleaves multi-scale computational blocks between the generator and discriminator, lets the discriminator update first while shared blocks are frozen during the generator step, and uses target MRI only during training to guide a feature transform. On the Abdomen/Pelvis, Head and Neck, and Thorax subsets of SynthRAD 2025 it is compared with five baselines, reaching an Abdomen/Pelvis VGG perceptual distance of 642.1, below Pix2Pix at 991.2 and UNet-AE at 1687.9.
VinUniversity
Amin Golnari（First author）
StaX-Net Cross-Modality Medical Image Translation Generative Adversarial Networks Stackelberg-Inspired Asymmetric Optimization

You’re all caught up