Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Pretrained video diffusion models can act as universal, plug-and-play restoration layers for legacy codecs, outperforming VTM-23.0 on both perceptual metrics and classical PSNR while slashing bitrates by up to 94%.
Current AI agents struggle with long-horizon professional tasks, achieving only 30% success in complex GUI workflows, revealing critical gaps in their capabilities.