Spaces:

dylanebert
/

3d-arena

Running

Are there any annotation datasets available for 3D human preference alignment?

by tianyilt - opened Mar 12

Mar 12

Similar to how MTBench provides data for LLM evaluation (enabling LLM-as-judge approaches and human preference reward models), I'm wondering if this project plans to create a corresponding dataset for pair-wised 3D human preference alignment.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment