I will be at #NeurIPS2024 from December 10-16. Thrilled to present our oral paper(MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making) on Friday, December 13th (15:50-16:10 PST). 🔍 Learn more: Project page:

RT @shan23chen: Awesome study lead by Keno! Lead by @ybkim95_ai and @HyewonMandyJ We are trying to get a perspective from AI researchers a…

RT @Orson_Xu: [Please RT📢] SEA Lab ( is hiring 1 postdoc in Spring/Fall'25 and 1-2 PhD in Fall'25! We build next-g…

@chanwoopark20 @HyewonMandyJ I am open to any forms of collaboration for the future work in Healthcare AI domain especially on multi-agent LLM, healthcare AI and wearable sensors. Also, I am actively looking for PhD positions this Fall.

@chanwoopark20 @HyewonMandyJ Our ablation show that the adaptive setting outperforms static complexity settings, with 81.2% accuracy on text-only queries. Most text-only queries were high complexity, while image+text and video+text queries were often low complexity, suggesting visual cues simplify decisions.

@chanwoopark20 @HyewonMandyJ Our findings show that MDAgents consistently reach consensus across different data modalities. text+video modalities converge quickly, while text+image and text-only modalities show a more gradual alignment. Despite varying speeds, all modality cases eventually converged.

@baggeontae18 @chanwoopark20 @HyewonMandyJ the arxiv paper will be updated! sorry for the inconvenience.

@chanwoopark20 @HyewonMandyJ Our ablations reveal that our approach can optimize performance with fewer agents (N=3), improves decision-making at extreme temperatures, and reduces computational costs, making it more efficient and adaptable than Solo and Group settings, especially in complex medical cases.

@chanwoopark20 @HyewonMandyJ Solo settings excel in simpler tasks, achieving up to 83.9% accuracy, while group settings outperform in complex, multi-modal tasks, with up to 91.9% accuracy.

@chanwoopark20 @HyewonMandyJ Surprisingly, our MDAgents significantly outperforms both Solo and Group setting methods, showing the best performance in 7 out of 10 benchmarks. This comprehends both textual information with high precision and visual data.

@chanwoopark20 @HyewonMandyJ MDAgents follows four stages: 1) Medical complexity check to categorize the query 2) Expert recruitment selecting PCC for low and MDT/ICT for moderate and high complexity 3) Initial assessment 4) Collaborative discussion between LLM agents 5) Final decision making by moderator

@chanwoopark20 @HyewonMandyJ Previous approaches in medical decision making have ranged from single- to multi- agent frameworks like voting and debates. However, they often stick to static setups. However, MDAgents dynamically choose the best collaboration structure based on the complexity of medical tasks.

RT @CHILconference: A framework for LLMs to make inference about health based on contextual information and physiological data. Our fine-tu…

Excited to share a #ACL2024 Findings paper "EmpathicStories++: A Multimodal Dataset for Empathy towards Personal Experiences" co-authored with @jocelynjshen. We provide a valuable data for work in empathetic AI, quantitative exploration of cognitive insights and empathy modeling.

@hwchung27 @MIT Thanks for the great talk today Hyung Won!

@taotu831 This is really inspiring work! congrats Tao.

RT @taotu831: What unprecedented opportunities can 1M+ context open up in medicine? Introducing 🩺Med-Gemini, a family of multimodal medica…

I'm excited to share my recent publication in CHIL 2024, "Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data". Our study reveals the potential of LLMs as personal health learners with wearable sensors. Arxiv:

Happy to share our latest paper "Adaptive Collaboration Strategy for LLMs in Medical Decision Making" We introduce MDAgents - a framework that constructs LLM team for medical decision making, showing best performance in 5 out 7 medical benchmarks.