Jiang Liu

Hi, I wonder if you can provide the pre-trained + fine-tuned SeqTR segmentation models for RefCOCO and RefCOCO+. Thanks a lot!

referring expression comprehension number do not match

2

Hi, Thanks for sharing the great work. I ran the inference code for referring expression comprehension, but it looks like the numbers I got do not match what's reported here...

question about ref-davis evaluation

1

Hi, thanks for sharing the great work. I have a question about the ref-davis evaluation. After running the evaluation script, I see that there is a `global_results-val.csv ` file generated...

why customized optimizers?

5

### ❓ The question Hi OLMo team, thanks for the great work! As I browse through the codebase, I noticed that you have implemented your own optimizers instead of using...

Hi @lwye , I see that in your codes you compute both mean IoU and overall IoU. Which one do you report in your paper? Is it overall IoU? Thanks!

Finetuning config file

3

### ❓ The question Hi, I am wondering if you can provide your config file for finetuning on the Tulu V2 dataset? It would be helpful for reproducing the finetuning...