MIRO — Multi-Reward Conditioned T2I (ICML 2026) Collection Paper, models, ablations + single-reward specialists, and the live ZeroGPU demo. • 4 items • Updated 1 day ago
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation Paper • 2603.23488 • Published Mar 24 • 5
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation Paper • 2603.23488 • Published Mar 24 • 5
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation Paper • 2603.23488 • Published Mar 24 • 5
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency Paper • 2510.25897 • Published Oct 29, 2025 • 17 • 3
T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning Paper • 2510.23484 • Published Oct 27, 2025 • 3
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency Paper • 2510.25897 • Published Oct 29, 2025 • 17