Paper-Conference

HugAgent: Benchmarking LLMs for Simulation of Individualized Human Reasoning
Simulating human reasoning in open-ended tasks has been a long-standing aspiration in AI and cognitive science. While large language …
Chance Jiajie Li, Zhenze Mo, Yuhan Tang, Ao Qu, Jiayi Wu, Kaiya Ivy Zhao, Yulu Gan, Jie Fan, Jiangbo Yu, Hang Jiang, Paul Pu Liang, Jinhua Zhao, Luis Alberto Alonso Pastor, Kent Larson
Cite arXiv
Assessing Adaptive World Models in Machines with Novel Games
Human intelligence exhibits a remarkable capacity for rapid adaptation and effective problem-solving in novel and unfamiliar contexts. …
Lance Ying, Katherine M. Collins, Prafull Sharma, Cedric Colas, Kaiya Ivy Zhao, Adrian Weller, Zenna Tavares, Phillip Isola, Samuel J. Gershman, Jacob D. Andreas, Thomas L. Griffiths, Francois Chollet, Kelsey R. Allen, Joshua B. Tenenbaum
Cite arXiv
Simulating Society Requires Simulating Thought
Simulating society with large language models (LLMs), we argue, requires more than generating plausible behavior; it demands …
Chance Jiajie Li, Jiayi Wu, Zhenze Mo, Ao Qu, Yuhan Tang, Kaiya Ivy Zhao, Yulu Gan, Jie Fan, Jiangbo Yu, Jinhua Zhao, Paul Pu Liang, Luis Alonso, Kent Larson
Cite arXiv
Cross-Modal Alignment Regularization: Enhancing Language Models with Vision Model Representations
Cross-modal distillation has emerged as a critical technique for leveraging strengths across different modalities. However, existing …
Yulu Gan, Kaiya Ivy Zhao, Phillip Isola
Cite URL
Enhancing Understanding in Generative Agents through Active Inquiring
As artificial intelligence advances, Large Language Models (LLMs) have evolved beyond being just tools, becoming more like human-like …
Jiaxin Ge, Kaiya Zhao, Manuel Cortes, Jovana Kondic, Shuying Luo, Michelangelo Naim, Andrew Ahn, Guangyu Robert Yang
Cite URL