Hengyue Liang
Hengyue Liang
The eval.py example provided along with the release of ImageNet-A dataset has a severe calculation mistake in calculating the ImageNet-A accuracy given a ImageNet-1K pretrained model. Cause: ImageNet-1K has 1,000...
Hi, it seems that the selective classification experiment part is missing. (Both training and evaluation). Can you upload this code please? Thanks
### Problem Description I was testing brwoser-use and was impressed performance. However, I noticed that browser-use may potentially get stuck on websites that has pop up windows after the website...
### Bug Description The main content displayed o Bing.com cannot be detected. See the attached screenshot:  ### Reproduction Steps Run the following function with any supported LLM backbone (with...