Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
机构 * University of Waterloo(多伦多大学) ; Hong Kong University of Science and Technology(香港科技大学) ; University of Science and Technology of China(中国科学技术大学) ; Vector Institute(向量研究所)
专题命中 推理与问题求解 :large language model(abstract);language model(abstract);instruction tuning(abstract);分类 cs.CL、cs.AI
Comments Project Page: https://tiger-ai-lab.github.io/Pixel-Reasoner/, Hands-on Demo: https://huggingface.co/spaces/TIGER-Lab/Pixel-Reasoner