CurEvo: Curriculum-Guided Self-Evolution for Video Understanding

TL;DR

CurEvo introduces a curriculum-guided self-evolution framework that dynamically manages task difficulty and evaluation criteria to improve autonomous video understanding across multiple benchmarks.

Contribution

It integrates curriculum learning into self-evolution, creating a structured, progressive learning process for video understanding models.

Findings

Consistently improves accuracy across seven backbones.

Enhances semantic scores on four VideoQA benchmarks.

Validates effectiveness of curriculum-guided self-evolution.

Abstract

Recent advances in self-evolution video understanding frameworks have demonstrated 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 introduces curriculum learning into self-evolution to achieve more structured and progressive model improvement. CurEvo dynamically regulates task difficulty, refines evaluation criteria, and balances data diversity according to model competence, forming a curriculum-guided feedback loop that aligns learning complexity with model capability. Built upon this principle, we develop a multi-dimensional adaptive QA framework that jointly evolves question generation and answer evaluation across perception, recognition, and understanding dimensions, ensuring coherent and measurable curriculum progression. Through this integration, CurEvo transforms weakly controlled self-evolution into a more structured learning process for autonomous video understanding. Across seven backbones, CurEvo consistently improves both benchmark accuracy and evaluator-based semantic score on four VideoQA benchmarks, validating the effectiveness of curriculum-guided self-evolution for video understanding.