3 papers
cs.AI2026
Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners
Alec Helbling, Andrey Bryutkin, Mauro Martino +3
Structured reasoning requires making and revising interdependent decisions to reach a globally consistent solution. Existing architectures struggle with this: autoregressive models…
cs.LG2025
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…
stat.ML2025
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…