Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition
Multimodal Large Language Models (MLLMs) are increasingly used for dietary assessment from meal images, where retrieval-augmented grounding was shown to sharpen nutrition estimates. However, we find this premise no longer holds for current MLLMs. A modern MLLM's direct estimate now matches or surpasses the full retrieval pipeline. This raises a question: if retrieval no longer improves the overall estimate, can it still deliver the two things clinicians value, accurate portions and a traceable, item-by-item record? We pursue this while preserving what matters for clinical adoption: minimal use
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Bruce Coburn →
“Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition”
- LinkedLinked via arxiv author · 85%Jingbo Yue →
“Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition”
- LinkedLinked via arxiv author · 85%Jinge Ma →
“Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition”
- LinkedLinked via arxiv author · 85%Siddeshwar Raghavan →
“Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition”
- LinkedLinked via arxiv author · 85%Gautham Vinod →
“Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition”
- LinkedLinked via arxiv author · 85%Fengqing Zhu →
“Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition”
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agen” ≈ “Fosowl/agenticSeek””