Beyond Linear Paths: Generalized Interpolation for Flow-Based Generative Modeling

Flow-based generative models learn to transform random noise into molecular conformations by following a prescribed interpolation path between the two. Straight-line (linear) interpolation is the usual choice, but it is only one of many possible paths. We compare four paths within a single affine framework, x t = α t x+ β t z : linear, trigonometric, spherical and a new operator-based path in which each degree of freedom follows its own schedule. Linear interpolation is a limiting case of both the operator-based and spherical paths. The operator-based path bends inside it (contracted), whereas the trigonometric and spherical paths bend outside it (expanded). We train the same Transformer velocity field with each path on a three-well potential, the mini-protein Trp-cage and the intrinsically disordered protein α-synuclein. All four paths reproduce the reference distributions with comparable accuracy, but they get there differently. The trigonometric and spherical paths resolve conformational basins early and approach the reference smoothly. The operator-based path delays part of the transport, so some features stall or briefly diverge before converging sharply. An exact relation between the rate of change of the KL divergence and the alignment of the learned velocity with the score difference, together with closed-form moments of each path, explains these differences. The choice of interpolation path therefore controls how a flow model converges, not only where it ends.

Authors

Institutions

Publication Details

Journal
bioRxiv (Cold Spring Harbor Laboratory)
Published
2026-11-18
DOI
https://doi.org/10.64898/2026.11.16.767201
Primary Topic
Protein Structure and Dynamics
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Beyond Linear Paths: Generalized Interpolation for Flow-Based Generative Modeling

Jagannath Mondal, Nagesh B E
2 links
bioRxiv (Cold Spring Harbor Laboratory)
Protein Structure and Dynamics
preprint

Beyond Linear Paths: Generalized Interpolation for Flow-Based Generative Modeling

Jagannath Mondal, Nagesh B E
preprint en

Abstract

Flow-based generative models learn to transform random noise into molecular conformations by following a prescribed interpolation path between the two. Straight-line (linear) interpolation is the usual choice, but it is only one of many possible paths. We compare four paths within a single affine framework, x t = α t x+ β t z : linear, trigonometric, spherical and a new operator-based path in which each degree of freedom follows its own schedule. Linear interpolation is a limiting case of both the operator-based and spherical paths. The operator-based path bends inside it (contracted), whereas the trigonometric and spherical paths bend outside it (expanded). We train the same Transformer velocity field with each path on a three-well potential, the mini-protein Trp-cage and the intrinsically disordered protein α-synuclein. All four paths reproduce the reference distributions with comparable accuracy, but they get there differently. The trigonometric and spherical paths resolve conformational basins early and approach the reference smoothly. The operator-based path delays part of the transport, so some features stall or briefly diverge before converging sharply. An exact relation between the rate of change of the KL divergence and the alignment of the learned velocity with the score difference, together with closed-form moments of each path, explains these differences. The choice of interpolation path therefore controls how a flow model converges, not only where it ends.

bioRxiv (Cold Spring Harbor Laboratory)
Tata Institute of Fundamental Research (IN)
Department of Atomic Energy, Government of India
Protein Structure and Dynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon