VGGSounder: Audio-Visual Evaluations for Foundation Models Paper • 2508.08237 • Published Oct 18, 2025 • 5
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training Paper • 2608.24845 • Published Aug 25 • 19
It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models Paper • 2601.00090 • Published Dec 31, 2025 • 5
Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale Paper • 2604.18572 • Published Apr 20 • 4
LAION-Audio-XL: A Web-Scale Corpus and Scaling Studies for Contrastive Language-Audio Pretraining Paper • 2611.11592 • Published 13 days ago • 8