AI RESEARCH
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
arXiv CS.LG
•
ArXi:2603.09206v1 Announce Type: cross Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention. While recent approaches have nstrated that LLM agents can self-evolve from scratch with little to no data, VLMs