5 papers
ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction
Bojun Zhang, Junhong Liang, Feifei Zhai +2
Vision Language Models (VLMs) have shown great success in general visual tasks, yet they still struggle to deeply understand text within images. In this paper, we introduce ReViCo…
PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks
Bojun Zhang, Hangjian Ye, Hao Zheng +4
Fine-grained 3D part segmentation is crucial for enabling embodied AI systems to perform complex manipulation tasks, such as interacting with specific functional components of an o…
Vision Language Models Are Not (Yet) Spelling Correctors
Junhong Liang, Bojun Zhang
Spelling correction from visual input poses unique challenges for vision language models (VLMs), as it requires not only detecting but also correcting textual errors directly withi…
PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correction
Junhong Liang, Bojun Zhang
Chinese ASR correction is challenging because errors are often \emph{phonetic} (many characters share similar Pinyin) while the correction model must also obey a \emph{length const…
Investigating the Star-Formation Characteristics of Radio Active Galactic Nuclei
Bojun Zhang, Fan Zou, W. N. Brandt +5
The coevolution of supermassive black holes and their host galaxies represents a fundamental question in astrophysics. One approach to investigating this question involves comparin…