4 papers
Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement
Alec Helbling, Andrey Bryutkin, Mauro Martino +2
Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puz…
Neural Triangular Transport Maps: A New Approach Towards Sampling in Lattice QCD
Andrey Bryutkin, Youssef Marzouk
Lattice field theories are fundamental testbeds for computational physics; yet, sampling their Boltzmann distributions remains challenging due to multimodality and long-range corre…
Canonical Bayesian Linear System Identification
Andrey Bryutkin, Matthew E. Levine, Iñigo Urteaga +1
Standard Bayesian approaches for linear time-invariant (LTI) system identification are hindered by parameter non-identifiability; the resulting complex, multi-modal posteriors make…
HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
Andrey Bryutkin, Jiahao Huang, Zhongying Deng +3
We present a novel graph transformer framework, HAMLET, designed to address the challenges in solving partial differential equations (PDEs) using neural networks. The framework use…