AI RESEARCH

Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning

arXiv CS.CV

ArXi:2606.04986v1 Announce Type: new Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reasoning and generalization capabilities. Moreover, high-quality large-scale nutritional annotations remain scarce. To address these issues, we