Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding 文章

ArXiv CS.CV2026-06-01NEWSen作者: Yuefei Chen, Jiang Liu, Xiaodong Lin, Ruixiang Tang
查看原文 →
关系图谱

Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding · 相关技术

相关技术

Vision Language Models