datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
BasicSpatialAbility
[ACL'25 Main] Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics
[!IMPORTANT]
You can find the sample testing code on GitHub!
This dataset is a benchmark designed for evaluating Multimodal Large Language Models' Basic Spatial Abilities based on authentic Psychometric theories. It is structured specifically to support both Zero-shot and Few-shot evaluation protocols.
Split Name
Role
Description
test
Query Set… See the full description on the dataset page: https://huggingface.co/datasets/EmbodiedCity/BasicSpatialAbility.xlerobot-final-v1-xlerobot_mobile_basics_h264_v1This dataset was created using LeRobot.
Dataset Description
XLeRobot Final v1 whole-body teleoperation smoke test
A public, real-hardware integration record for an XLeRobot-compatible 0.4.0
two-wheel configuration. This is an engineering smoke-test dataset, not a
household-task training benchmark.
Recorded system
Two Seeed Studio Pro SO-101 arms (leader/follower teleoperation)
Differential two-wheel base
Pan/tilt head
Three synchronized RGB… See the full description on the dataset page: https://huggingface.co/datasets/NOJIMA21/xlerobot-final-v1-xlerobot_mobile_basics_h264_v1.BasicSpatialAbility
[ACL'25 Main] Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics
[!IMPORTANT]
You can find the sample testing code on GitHub!
This dataset is a benchmark designed for evaluating Multimodal Large Language Models' Basic Spatial Abilities based on authentic Psychometric theories. It is structured specifically to support both Zero-shot and Few-shot evaluation protocols.
Split Name
Role
Description
test
Query Set… See the full description on the dataset page: https://huggingface.co/datasets/ruaruaxu/BasicSpatialAbility.