2 papers
cs.LG2025
Inference-Time Compute Scaling For Flow Matching
Adam Stecklov, Noah El Rimawi-Fine, Mathieu Blanchette
Allocating extra computation at inference time has recently improved sample quality in large language models and diffusion-based image generation. In parallel, Flow Matching (FM) h…
cs.LG2025
Simulation-free Structure Learning for Stochastic Dynamics
Noah El Rimawi-Fine, Adam Stecklov, Lucas Nelson +4
Modeling dynamical systems and unraveling their underlying causal relationships is central to many domains in the natural sciences. Various physical systems, such as those arising…