Single-image nutrition estimation can fail silently when visible foods are missed. Even when a food is correctly identified, its proposed region may not support portion estimation. We propose a framework that uses multimodal large language models (MLLMs) to inventory visible foods and separately verify food identity an...
Jing-Bo Yue, Bruce Coburn, Jin-Ge Ma et al.· 0 citations
PolyMem, an exemplar-free approach that implicitly models rich high-order statistics of the feature distribution to enhance cross-domain robustness, is introduced that effectively alleviates the performance discrepancy while improving the model's performance across domains.
Jin-Ge Ma, Gautham Vinod, Bruce Coburn et al.· 0 citations
Open-KNEAD is introduced, a knowledge-grounded agentic framework for meal nutrition estimation that is training-free and locally deployable, and improves portion estimates over both prior grounding methods and direct estimation in most backbone-dataset settings.
Bruce Coburn, Jing-Bo Yue, Jin-Ge Ma et al.· arXiv.org· 0 citations
The proposed Recursive Self-Correction approach raises model performance from a Political Neutrality Likert scale baseline of 2.14 to 4.56, averaged across all models, demonstrating effective inference-time mitigation of political bias in LLM-generated summaries.
Tejaswi V. Panchagnula, Bruce Coburn, Bryce J. Dietrich et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
