8 papers
Discovering High Level Patterns from Simulation Traces
Sean Memery, Kartic Subr
Large Language Models (LLMs) are unable to reliably reason about specific physical systems. Attempts to imbue LLMs with knowledge of the necessary physics concepts have shown great…
PAOLI: Pose-free Articulated Object Learning from Sparse-view Images
Jianning Deng, Kartic Subr, Hakan Bilen
We present a methodology to model articulated objects using a sparse set of images with unknown poses. Current methods require dense multi-view observations and ground-truth camera…
Quadratic-Order Geodesics on Meshes
Yue Ruan, Albert Chern, Tzu-Mao Li +2
We introduce a novel representation and optimization framework for discrete geodesics on triangle meshes that reduces artifacts of linear methods on uneven and coarse discretizatio…
Learned Adaptive Mesh Generation
Zhiyuan Zhang, Amir Vaxman, Stefanos-Aldo Papanicolopulos +1
Elliptic Partial Differential Equations (PDEs) play a central role in computing the equilibrium conditions of physical problems (heat, gravitation, electrostatics, etc.). Efficient…
Language Model Inversion through End-to-End Differentiation
Kevin Yandoka Denamganaï, Kartic Subr
Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determinin…
xInv: Explainable Optimization of Inverse Problems
Sean Memery, Kevin Denamganai, Anna Kapron-King +1
Inverse problems are central to a wide range of fields, including healthcare, climate science, and agriculture. They involve the estimation of inputs, typically via iterative optim…