Preprint
Aug 2026
FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding
This paper presents FADE, an effective training framework for counterfactual discovery and explanation that is built on an evidence-first, two-stage training paradigm, and demonstrates remarkable robustness when transitioning from constrained MCQs to unconstrained OQA and captioning.
Fufangchen Zhao, Jin-Hu Fu, Jiachen Lei et al.
· 0 citations