Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning
For researchers in food computing, this work provides a new benchmark and a method that improves reasoning and generalization over supervised fine-tuning, though it is domain-specific and incremental.
Food-R1 introduces CalorieBench-80K, the first food benchmark with chain-of-thought calorie reasoning, and a multi-task VLM trained with reinforcement fine-tuning (GRPO) that outperforms baselines across food tasks.
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 introduce CalorieBench-80K, a large-scale benchmark with curated calorie labels and dietary advice annotations. To the best of our knowledge, it is the first food image benchmark to incorporate Chain-of-Thought (CoT) annotations for calorie reasoning. We also propose Food-R1, a unified food VLM trained in a multi-task learning paradigm to equip the model with broad capabilities. Food-R1 undergoes CoT-based cold-start instruction tuning, followed by reinforcement fine-tuning (RFT) using Group Relative Policy Optimization (GRPO) to improve reasoning and performance. Experiments on CalorieBench-80K and representative benchmarks show that Food-R1 consistently outperforms strong baselines across food-related tasks. The code, model weights, and benchmark annotations are available at the project repository.