datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
thinking_berkeley_rpt_lerobot_output_qwen3vlRPTS-Eval
Dataset Card
This repository contains the data presented in RPTS: Tree-Structured Reasoning Process Scoring for Faithful Multimodal Evaluation
Code: https://github.com/wang-hao-feng/RPTS
Dataset Details
Dataset Information
Total: 390 multimodal reasoning data for English and Chinese
Three types of relationships between modalities
Example
For more information of RPTS-Eval, please refer to our paper.
fashion-dataset-hd