Introduces CalorieBench-80K benchmark with CoT calorie reasoning and Food-R1 VLM trained via CoT cold-start then GRPO reinforcement fine-tuning, claiming consistent outperformance on food tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning
Introduces CalorieBench-80K benchmark with CoT calorie reasoning and Food-R1 VLM trained via CoT cold-start then GRPO reinforcement fine-tuning, claiming consistent outperformance on food tasks.