Support long video VLM training
Open
multimodal
- Dominant language
- Python
- Stars
- 2k
- Forks
- 561
- Avg merge
- 4d 5h
- Merged PRs (30d)
- 145
Description
Add support for handling long videos similar to LongVILA-R1 (https://arxiv.org/pdf/2507.07966)
Contributor guide
Assessment
This issue has not been assessed yet.