1.
Zhao Y, Wang S, Li J. LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 19];40(41):34994-5002. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40804