AnalysisPhysResponse benchmark: ten video models miss physical parameters, authors report
A new arXiv benchmark finds image-to-video models' physics errors far above those of correct videos, and that PSNR can reward static output.
AI video, reported from the sources
Articles about text-to-video and image-to-video models and their releases.
AnalysisA new arXiv benchmark finds image-to-video models' physics errors far above those of correct videos, and that PSNR can reward static output.
AnalysisAn arXiv paper reports that on Mochi a raised guidance scale repairs .649 of failures above a demand threshold and .385 below it.
AnalysisA new benchmark of 222 experiment pairs finds ten text-and-image-to-video models rarely get both outcomes of a science experiment right.
NewsAn arXiv paper presents MemCrafter, an agentic prompt-refinement method for memorable text-to-video, and reports gains over Seedance-2.5 and other baselines.