Wufei Ma

icon indicating a website link https://wufeim.github.io icon indicating an email [email protected]

icon company Johns Hopkins University icon location Baltimore, MD icon location Machine learning and computer vision.

Results 4 issues of Wufei Ma

Trained models for all classes

5 comment

Hi, Thanks for releasing the code and trained models. I'm wondering if the released model is meant for cars only. If so, are there plans to release models for cyclists...

Different embeddings obtained when running with different batch size

1 comment

Thanks for sharing this awesome work. I'm trying a simple symmetric text retrieval demo, which involves computing text embeddings for text retrieval. What I don't understand is why I get...

Importing a scene graph

2 comment

Dear Infinigen authors, Thanks for open-sourcing this great framework! Besides "solving" a scene layout based on the constraints, I am trying to create a scene (i.e., sample procedural models, output...

question

LLaVA v1.5 7b very low performance on TextVQA

3 comment

Dear authors, Thanks for sharing this great codebase. I tried to test LLaVA-v1.5-7b (`llava_v1.5_7b`) model on `TextVQA_VAL` and only get about 21.88 accuracy, which is much lower than the 58.2...