Xinyu Fang

icon indicating an email [email protected]

icon company Zhejiang University, Shanghai AI Lab icon location Hangzhou, China; Shanghai, China icon location Ph.D. candidate jointly at Zhejiang University and Shanghai AI Laboratory

Results 7 issues of Xinyu Fang

meet dimension error when running the qfvs downstream tasks

when I using `https://github.com/showlab/UniVTG/blob/main/model.md` this checkpoint (in below picture) ![image](https://github.com/showlab/UniVTG/assets/81462011/c2dd0e7b-8062-4d90-9f19-69aff4e04652) and run with qfvs downstream tasks I meet the issue: First of all, there is no batch size dimension when...

[Model] add support for VideoChat2_HD

merge after MVBench PR

In Progress

[Benchmark] support MVBench

In Progress

Update llava_arch.py for device synchronization of mm_projector outputs

add fps sample in mmbench video

In Progress

[Minor] Align MMMU evaluation method with official

MMMU Official Evaluation Guideline: https://github.com/MMMU-Benchmark/MMMU/blob/main/mmmu/README.md

add support for internvideo, videollama, keye and llava-onevision-1.5

1 comment

also add max_frame setting in fps sampling

WIP