{"id":"a29c3978-dc39-4b62-9d22-d61d0d0633fe","slug":"hf-model-etri-vilab-multihopspatial-qwen3-vl-4b-instruct-1wi756z-1b","name":"MultiHopSpatial-Qwen3-VL-4B-Instruct","description":"Hugging Face model etri-vilab/MultiHopSpatial-Qwen3-VL-4B-Instruct. Task: image text to text. 69 downloads. 3 likes.","capabilities":["safetensors","qwen3_vl","spatial-reasoning","multi-hop","grounding","vision-language","qwen3-vl","GRPO","image-text-to-text","conversational","en","dataset:etri-vilab/MultihopSpatial","arxiv:2603.18892","base_model:Qwen/Qwen3-VL-4B-Instruct","base_model:finetune:Qwen/Qwen3-VL-4B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":36,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:50.590Z"}