4 papers
Controllable Diverse Sampling through Pullback Directions
Sylvain Dehayem Kenfouo, Aaron Zweig, Mingxuan Zhang +1
Conditional diffusion models can generate high-quality images that align closely with a given prompt. However, samples generated from different random seeds may remain visually sim…
Scalable Contrastive Causal Discovery under Unknown Soft Interventions
Mingxuan Zhang, Khushi Desai, Sopho Kevlishvili +1
Observational causal discovery is only identifiable up to the Markov equivalence class. While interventions can reduce this ambiguity, in practice interventions are often soft with…
Learning Lineage-guided Geodesics with Finsler Geometry
Aaron Zweig, Mingxuan Zhang, David A. Knowles +1
Trajectory inference investigates how to interpolate paths between observed timepoints of dynamical systems, such as temporally resolved population distributions, with the goal of…
Energy Guided Geometric Flow Matching
Aaron Zweig, Mingxuan Zhang, Elham Azizi +1
A useful inductive bias for temporal data is that trajectories should stay close to the data manifold. Traditional flow matching relies on straight conditional paths, and flow matc…