Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
TTSP resolves the Grounding Paradox by treating perception as a scalable test-time process that generates, filters, and iteratively refines multiple visual exploration traces, outperforming baselines on high-resolution and multimodal reasoning tasks.
citing papers explorer
-
Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.