AI RESEARCH
CurEvo: Curriculum-Guided Self-Evolution for Video Understanding
arXiv CS.LG
•
ArXi:2604.26707v1 Announce Type: cross Recent advances in self-evolution video understanding frameworks have nstrated the potential of autonomous learning without human annotations. However, existing methods often suffer from weakly controlled optimization and uncontrolled difficulty progression, as they lack structured guidance throughout the iterative learning process. To address these limitations, we propose CurEvo, a curriculum-guided self-evolution framework that