Grounded reasoning, where a model outputs text coordinates of relevant locations in chain-of-thought reasoning, is a common strategy for solving complex visual reasoning problems. However, the benefits and limitations of grounded reasoning are understudied. We study where and why grounded reasoning is most useful. To d...
Da-Wei Yan, Le Xue, Forrest Huang et al.· 0 citations
This work introduces ScienceVision, a cross-domain benchmark for scientific 3D understanding and reasoning through expert-level visual question answering (VQA), and evaluates 12 models on the same questions in three settings.
Tian-Yi Ma, Jing Gu, Haozhe Zhao et al.· 0 citations
Visual counting benchmarks report whether vision-language models produce the correct number, but not whether errors arise from perception or reasoning. We introduce DecoyCount, a benchmark built from 1,660 real-world images with designed decoys across seven mechanisms, along with paired prompts: a neutral question, a m...
Qiu-Yi Zhang, Zhen Xu, Jing Gu et al.· 0 citations
Training a model to generate visual content can encourage it to learn rich perceptual capabilities related to geometry, spatial relationships, and objectness; yet, its benefits for visual understanding remain unclear. We ask: when and how does visual generation supervision improve visual understanding? We study control...
Jia-Xin Ge, Yi-Ming Qin, Ji Xie et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
