6 papers · 1 filter
Analytic Bridge Diffusions for Controlled Path Generation
Michael Chertkov
Most modern bridge-diffusion methods achieve finite-time transport by specifying an interpolation, Schrodinger-bridge, or stochastic-control objective and then learning the associa…
Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth
Michael Chertkov
An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a…
Generative Stochastic Optimal Transport: Guided Harmonic Path-Integral Diffusion
Michael Chertkov
We introduce Guided Harmonic Path-Integral Diffusion (GH-PID), a linearly-solvable framework for guided Stochastic Optimal Transport (SOT) with a hard terminal distribution and sof…
Adaptive Path Integral Diffusion: AdaPID
Michael Chertkov, Hamidreza Behjoo
Diffusion-based samplers -- Score Based Diffusions, Bridge Diffusions and Path Integral Diffusions -- match a target at terminal time, but the real leverage comes from choosing the…
Sampling Decisions: Exact Path-Space Control for Physics-Informed Generative Sampling
Michael Chertkov, Sungsoo Ahn, Hamidreza Behjoo
Scientific generative models must turn tractable local decisions into globally correlated samples that respect physical constraints. We introduce Sampling Decisions, a finite-horiz…
Mixing Artificial and Natural Intelligence: From Statistical Mechanics to AI and Back to Turbulence
Michael Chertkov
The paper reflects on the future role of AI in scientific research, with a special focus on turbulence studies, and examines the evolution of AI, particularly through Diffusion Mod…