Jinda Jia

icon indicating a website link https://jindajia.github.io/

icon company Indiana University Bloomington icon location Bloomington icon location Ph.D. Student in Intelligent Systems Engineering Indiana University

Results 2 issues of Jinda Jia

Paper only load abstract

2 comment

https://arxiv.org/pdf/2111.09562.pdf

Can not reproduce MVBench benchmark results on Qwen2.5-VL-3B-Instruct model

Testing on Qwen2.5-VL-3B-Instruct with **MVBench**. However, the results can not reach to what in reports. I'm using [lmms_eval](https://github.com/EvolvingLMMs-Lab/lmms-eval) to run this test. The running command and results are given below....