Can EgoLifeQA Benchmark Be Integrated into LMMs-Eval?

[Artessay]

Hi,

Thank you for the great work on EgoLife. It has been very helpful for benchmarking and evaluating large multimodal models on very long video understanding.
I am writing to ask whether it would be possible to integrate the EgoLifeQA Benchmark into the LMMs-Eval framework, which is also developed in your Lab.

Specifically, I would like to ask:

• Is there interest in supporting EgoLifeQA as an evaluation task within LMMs-Eval?
• Are there any technical or design constraints we should be aware of (e.g., data format, evaluation protocol, task abstraction)?
• Would you recommend submitting a PR, or is there a preferred process for proposing new benchmark integrations?

Thank you very much for your time and guidance. I look forward to your thoughts.