etri-vilab/MultihopSpatial download history
etri-vilab/MultihopSpatial is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 903 times (238 in the last 7 days), and 15,210 times in total. It ranks #20,865 among datasets by monthly downloads.
[ECCV 2026] MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Models Project Page | Paper | Model Overview MultihopSpatial is a benchmark designed to evaluate whether vision-language models (VLMs) demonstrate robustn
Models trained on MultihopSpatial
3 models list it as training data.
- etri-vilab/MultiHopSpatial-Qwen3-VL-4B-Instruct 68 downloads in 30 days
- etri-vilab/MultiHopSpatial-Qwen3-VL-8B-Instruct 15 downloads in 30 days
- etri-vilab/MultiHopSpatial-Qwen3-VL-32B-Instruct 14 downloads in 30 days