Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation
Tao Liu, Leela Krishna, Gouti Pavan Kumar +2
Video-to-video (V2V) generation is difficult to evaluate because outputs must both follow editing instructions and preserve frame-level correspondence with the source video, which…
cs.CV2025
GAZE:Governance-Aware pre-annotation for Zero-shot World Model Environments
Leela Krishna, Mengyang Zhao, Saicharithreddy Pasula +2
Training robust world models requires large-scale, precisely labeled multimodal datasets, a process historically bottlenecked by slow and expensive manual annotation. We present a…