Jize Jiang

works on

inference-time refinement 1 multimodal reasoning 1 reinforcement learning 1 self-verification 1 vision-language models 1

From the 1 of 8 linked papers with an AI index.

activity

20242026

collaborators

Showing cs.CVShow all

1 paper · 1 filter

cs.CV2024

UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models

Xinyu Pi, Mingyuan Wu, Jize Jiang +5

Smaller-scale Vision-Langauge Models (VLMs) often claim to perform on par with larger models in general-domain visual grounding and question-answering benchmarks while offering adv…