OVIE Collection One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation (NeurIPS 2026): base, 512x512, and two fine-tuned checkpoints. • 4 items • Updated 10 days ago
view article Article YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research espnet • 15 days ago • 36
Multiplayer Interactive World Models with Representation Autoencoders Paper • 2607.05352 • Published Jul 6 • 27
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation Paper • 2606.20536 • Published Jun 18 • 13
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation Paper • 2603.23488 • Published Mar 24 • 5