Files
Video-MTR/README.md
ModelHub XC 5bd9f1db39 初始化项目,由ModelHub XC社区提供模型
Model: Phoebe13/Video-MTR
Source: Original Platform
2026-09-08 10:45:17 +08:00

462 B

license, language, base_model, pipeline_tag
license language base_model pipeline_tag
apache-2.0
en
Qwen/Qwen2.5-VL-7B-Instruct
visual-question-answering

Video-MTR

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding.

This checkpoint extends Qwen2.5-VL-7B-Instruct with a multi-turn frame-retrieval policy trained via PPO, with an 80-frame video input budget.

References