{"id":"2602.02994","title":"Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation","url":"https://codeofpaper.com/paper/2602.02994","arxiv_url":"https://arxiv.org/abs/2602.02994","published":"2026-02-03","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}