π Introducing PhysicsAgentABM!
We propose a novel Physics-Guided Generative Agent Based Modeling framework for scalable and calibrated simulation of complex social systems!
β‘ 6.7x fewer API calls, 2.1-3.4x cost reduction
π― Superior temporal accuracy across all domains (EETE, ET-F1)
π Calibrated uncertainty (near-diagonal reliability curves)
π Robust to regime shifts (policy shocks, market crashes, viral events)
Huge kudos to my collaborator @inhan_y , Prof. @LiJundong and my advisor @jiamingcui1997!
π Introducing PhysicsAgentABM!
We propose a novel Physics-Guided Generative Agent Based Modeling framework for scalable and calibrated simulation of complex social systems!
β‘ 6.7x fewer API calls, 2.1-3.4x cost reduction
π― Superior temporal accuracy across all domains (EETE, ET-F1)
π Calibrated uncertainty (near-diagonal reliability curves)
π Robust to regime shifts (policy shocks, market crashes, viral events)
Huge kudos to my collaborator @inhan_y , Prof. @LiJundong and my advisor @jiamingcui1997!
So grateful for the incredible students and alumni of GEMLAB! Together, we published 4 main conference papers + 4 workshop papers at @NeurIPSConf. Youβre all absolute gems π
GEMLAB is heading to @NeurIPSConf! π Weβre presenting 4 main conference papers (including 1 spotlight β) + 4 workshop papers. Come say hi & check out our work! Details below π
π Thrilled to share that 2 of my papers got into NeurIPS! Huge thanks to my collaborators and our amazing advisor, Dr. Pinar Yanardag @PINguAR at @SanghaniCtrVT!
πCanβt wait to present our work in San Diego this December!
#NeurIPS2025