{"id":"2609.02486","title":"ViSAR: Training-Free Adaptive-k Retrieval for Visual Document Question Answering","url":"https://codeofpaper.com/paper/2609.02486","arxiv_url":"https://arxiv.org/abs/2609.02486","published":"2026-09-02","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}