2026
Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning
CVPR 2026
Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience. However, RL for VLMs requires abundant high-quality multimod