paper-with-me

Papers

CurEvo: Curriculum-Guided Self-Evolution for Video Understanding

2026-04-29 · Guiyi Zeng, Junqing Yu, Yi-Ping Phoebe Chen, Xu Chen, Wei Yang, Zikai Song arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.26707

Code (0)

등록된 구현이 없습니다.

Tasks

Question Generation

Similar Papers 제목 키워드 기반

Guided Self-Evolving LLMs with Minimal Human Supervision

2025-12-02 · Wenhao Yu, Zhenwen Liang, Chengsong Huang, Kishan Panaganti 외 arxiv

AI self-evolution has long been envisioned as a path toward superintelligence, where models autonomously acquire, refine, and internalize knowledge from their own learning experiences. Yet in practice, unguided self-evol…

Question Generation

Video-Guided Curriculum Learning for Spoken Video Grounding

2022-09-01 · Yan Xia, Zhou Zhao, Shangwei Ye, Yang Zhao 외

In this paper, we introduce a new task, spoken video grounding (SVG), which aims to localize the desired video fragments from spoken language descriptions. Compared with using text, employing audio requires the model to …

Video Grounding

Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval

2026-03-17 · Weiqing Li, Jinyue Guo, Yaqi Wang, Haiyang Xiao 외 arxiv

Visual-language models (VLMs) excel at data mappings, but real-world document heterogeneity and unstructuredness disrupt the consistency of cross-modal embeddings. Recent late-interaction methods enhance image-text align…

Cross-Modal RetrievalContrastive Learning

SPICE: Synergy and Partial Information Based Curriculum Evolution

2026-06-15 · Ankush Pratap Singh, Houwei Cao, Yong Liu arxiv

Multimodal learning exploits complementary information across heterogeneous modalities. The informativeness of each modality can vary widely across samples and training stages. Existing multimodal curriculum learning str…

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

2026-04-03 · Jacob Dineen, Aswin RRV, Zhikun Xu, Ben Zhou arxiv

Co-evolutionary self-play, where one language model generates problems and another solves them, promises curriculum learning without human supervision. The promise breaks down early in practice. The proposer converges to…

Mathematical Reasoning