Benchmark

LoopNav Benchmark

What is LoopNav?

A video-action dataset containing many loop-based navigation dataset in Minecraft environment, aiming to boost the spatial consistency and providing insight…

Released: 2025-05-15
Modality: multimodal
Evaluates: 多模态, Multimodal, 长文本, Long-Context, 智能体, Agent, navigation, consistency, 物理智能, Embodied AI, 长上下文, Long Context, 具身交互, Embodied Interaction, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported
Openness: unknown
Importer: OpenCompass Hub
Reported scores: 0

Source provenance

Original evidence https://hub.opencompass.org.cn/dataset-detail/LoopNav

LoopNav paper and code

Paper https://arxiv.org/abs/2505.22976
Code https://github.com/Kevin-lkw/LoopNav

No reported scores are on record for this benchmark yet.

Which sources cite LoopNav?

LoopNav

Related 多模态, Multimodal, 长文本, Long-Context, 智能体, Agent, navigation, consistency, 物理智能, Embodied AI, 长上下文, Long Context, 具身交互, Embodied Interaction, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported benchmarks