11 papers
PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement
Yian Wang, Han Yang, Minghao Guo +5
Automatically generating interactive 3D environments is crucial for scaling up robotic data collection in simulation. While prior work has primarily focused on 3D asset placement,…
Learning Linear Attention in Polynomial Time
Morris Yau, Ekin Akyürek, Jiayuan Mao +3
Previous research has explored the computational expressivity of Transformer models in simulating Boolean circuits or Turing machines. However, the learnability of these simulators…
Scaling up the think-aloud method
Daniel Wurgaft, Ben Prystawski, Kanishk Gandhi +3
The think-aloud method, where participants voice their thoughts as they solve a task, is a valuable source of rich data about human reasoning processes. Yet, it has declined in pop…
Can Large Language Models Understand Symbolic Graphics Programs?
Zeju Qiu, Weiyang Liu, Haiwen Feng +7
Against the backdrop of enthusiasm for large language models (LLMs), there is a growing need to scientifically assess their capabilities and shortcomings. This is nontrivial in par…
Compositional Physical Reasoning of Objects and Events from Videos
Zhenfang Chen, Shilong Dong, Kexin Yi +5
Understanding and reasoning about objects' physical properties in the natural world is a fundamental challenge in artificial intelligence. While some properties like colors and sha…
People use fast, goal-directed simulation to reason about novel games
Cedegao E. Zhang, Katherine M. Collins, Lionel Wong +3
People can evaluate features of problems and their potential solutions well before we can effectively solve them. When considering a game we have never played, for instance, we mig…