analiza aiqbench
FreeBridge introduces a Schrödinger Bridge formulation for single-cell transition modeling that enforces geometric constraints within a fixed cellular manifold to prevent biologically implausible intermediate trajectories. By leveraging instance-segmented representations and empirical latent support regularization, the method improves endpoint fidelity and mechanism-of-action retention across multiple high-content imaging datasets. This work underscores the critical role of geometric grounding in generating interpretable perturbation dynamics where only control and treated population marginals are observable.
FreeBridge: Variational Schr\"odinger Bridges for Cellular Transition Dynamics
arXiv:2606.11286v1 Announce Type: new Abstract: High-content imaging assays quantify cellular responses to chemical and genetic perturbations, yet continuous trajectories of individual cells are unobservable because cells are chemically fixed at acquisition. Perturbation modeling therefore reduces to inferring stochastic transport between control and treated populations observed only as separate marginals. While recent generative models achieve strong end-point alignment, boundary consistency does not determine intermediate evolution: multiple stochastic processes may connect identical marginals while traversing regions unsupported by observed single-cell morphologies. We introduce \textbf{FreeBridge}, a Schr\"odinger Bridge formulation for single-cell transition modeling under endpoint-only supervision. FreeBridge defines atomic states as instance-segmented single-cell representations, establishing a fixed cellular manifold, and learns stochastic transport constrained within this geometry via empirical latent support regularization. Across BBBC021, RxRx1, and JUMP, FreeBridge maintains competitive or improved endpoint fidelity and mechanism-of-action retention under a unified evaluation protocol; on BBBC021, it further reduces intermediate support violations. These findings highlight the importance of geometric grounding for biologically interpretable perturbation dynamics. Project page: https://y-research-sbu.github.io/FreeBridge/.
Abstract:High-content imaging assays quantify cellular responses to chemical and genetic perturbations, yet continuous trajectories of individual cells are unobservable because cells are chemically fixed at acquisition. Perturbation modeling therefore reduces to inferring stochastic transport between control and treated populations observed only as separate marginals. While recent generative models achieve strong end-point alignment, boundary consistency does not determine intermediate evolution: multiple stochastic processes may connect identical marginals while traversing regions unsupported by observed single-cell morphologies. We introduce \textbf{FreeBridge}, a Schrödinger Bridge formulation for single-cell transition modeling under endpoint-only supervision. FreeBridge defines atomic states as instance-segmented single-cell representations, establishing a fixed cellular manifold, and learns stochastic transport constrained within this geometry via empirical latent support regularization. Across BBBC021, RxRx1, and JUMP, FreeBridge maintains competitive or improved endpoint fidelity and mechanism-of-action retention under a unified evaluation protocol; on BBBC021, it further reduces intermediate support violations. These findings highlight the importance of geometric grounding for biologically interpretable perturbation dynamics. Project page: this https URL.
Accepted to MICCAI 2026 (early accept). Project page: this https URL
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2606.11286 [cs.LG]
(or arXiv:2606.11286v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.11286 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 268 cuvinte
Subiecte conexe
A Novel Hybrid Quantum Reservoir Computing (nHQRC) for Phase Transition Detection in Non-Equilibrium Dynamical Systems
arXiv · 21 iul. 2026
Multi-marginal temporal Schr\"odinger Bridge Matching from unpaired data
arXiv · 20 iul. 2026
Quantum-Enhanced Sampling of Schr\"odinger Bridges
arXiv · 24 sept. 2026
Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots
arXiv · 12 iun. 2026