Reward Transport: Property Control in Flow Matching via Noise-Space Alignment

• URL: http://arxiv.org/abs/2607.08781v1
• Date: Sat, 13 Jun 2026 00:17:15 GMT
• Title: Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
• Abstract summary: We show that coupling in flow matching can embed controllable structure directly into the learned flow field.<n>We introduce Reward Transport, which uses optimal transport coupling at training time to align a scalar noise-space coordinate with molecular rewards.<n> Empirically, on ZINC-250K and Guaca, sweeping the scalar induces monotone control of logP and consistent QED control over its operating range.
• Score: 30.541631728490202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as an alignment interface: by matching noise and data according to a target molecular property, it embeds controllable structure directly into the learned flow field. Building on this view, we introduce Reward Transport, which uses optimal transport coupling at training time to align a scalar noise-space coordinate with molecular rewards; at inference, varying this coordinate steers the generated distribution without requiring an oracle, reward model, gradient guidance, or additional computation. In the coupling-preserving limit, thresholding this coordinate recovers the Cross-Entropy Method's truncated reward distribution, providing a principled, continuously adjustable distribution-level control knob. Empirically, on ZINC-250K and GuacaMol, sweeping the scalar induces monotone control of logP and consistent QED control over its operating range; most tellingly, the same knob produces opposite structural responses for different targets, growing molecules for logP but shrinking them for QED, which rules out a generic size bias. The interface is complementary to classifier-free guidance and conditional flow matching, while a negative result under epsilon-prediction diffusion clarifies where coupling-level alignment is structurally absent. Code: https://github.com/KehanGuo2/reward-transport

Related papers

• Networked Admissibility-Preserving Control for Directed Safe Coordination [0.0]
  This paper addresses safety-critical coordination for scalar agents.<n>Agents communicate over a fixed weighted digraph with a directed spanning tree.<n>The synthesis yields an exact cascade in which exponentially decaying realization errors drive nonsymmetric consensus dynamics.
  arXiv  Detail & Related papers  (2026-09-08T19:38:20Z)
• Programmable Cavity Squeezing for Distributed Sensing in a Tweezer Array [0.0]
  We show that a tweezer array in a cavity offers an ideal testbed to engineer quantum states for distributed sensing.<n>Results establish programmable cavity interactions as a scalable route to entanglement tailored to distributed signals.
  arXiv  Detail & Related papers  (2026-08-27T13:45:26Z)
• Distribution Steering via Sliced Optimal Transport Control [2.1485350418225244]
  Distribution steering seeks feedback laws that drive the state law of a system between prescribed initial and terminal distributions.<n>We develop a finite-horizon control framework based on sliced optimal transport.<n>We prove that the randomized controller converges to the averaged sliced flow as the sampling period vanishes.
  arXiv  Detail & Related papers  (2026-08-13T05:00:59Z)
• Adjacency-Based Spectral Proxy Control of Mobile Communication Agents [0.23872611575805827]
  We consider a heterogeneous mobile-agent network composed of uncontrolled task agents and controllable communication agents.<n>Controlling connectivity relies on the eigenvector corresponding to the second-smallest eigenvalue of a graph's Laplacian matrix.<n>We propose A-Fiedler, which replaces the Fiedler embedding with the dominant eigenvector of the adjacency matrix.
  arXiv  Detail & Related papers  (2026-08-12T20:35:02Z)
• PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models [0.8594140167290097]
  Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis.<n>We propose PG-MAP, a training-free framework that formulates inference-time alignment as a trajectory-level Gibbs-MAP / proximal energy optimization.
  arXiv  Detail & Related papers  (2026-06-22T07:36:36Z)
• Invariant Stochastic Filtering on SE(3) for Inertial-Encoder State Estimation of Serial Rigid Manipulators [0.0]
  An invariant extended Kalman filter (IEKF) is developed for state estimation of serial rigid manipulators.<n>The Riccati equation governs the true error covariance rather than a local approximation.<n>A physically separated noise model treats gyroscope and accelerometer channels independently.
  arXiv  Detail & Related papers  (2026-06-21T08:11:39Z)
• Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation [60.41721951405564]
  Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging.<n>Most federated LoRA methods adopt a uniform aggregation rule, which breaks under the encoder-decoder asymmetry in medical segmentation.<n>This mismatch entangles shared anatomy with site-specific biases and harms generalization.<n>We introduce a Subspace Orthogonality Regularizer that penalizes shared-local collinearity in the effective update space.
  arXiv  Detail & Related papers  (2026-06-07T15:39:28Z)
• AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers [24.937985157569823]
  We argue that such timestep-agnostic alignment is suboptimal because the useful granularity of representation supervision changes systematically with the signal-to-noise ratio.<n>In high-noise regimes, diffusion models benefit more from coarse semantic and layout-level anchoring, whereas in low-noise regimes, the training signal should emphasize spatially detailed and structurally faithful refinement.<n>This non-stationary alignment behavior creates a representational mismatch for static single-level supervisors.
  arXiv  Detail & Related papers  (2026-05-05T03:07:29Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• General and Efficient Steering of Unconditional Diffusion [25.225845714398364]
  We present a recipe for efficiently steering unconditional diffusion.<n>without gradient guidance during inference.<n>Our approach is built on two observations about diffusion model structure.<n>Experiments on CIFAR-10, ImageNet, and CelebA demonstrate improved accuracy/quality over-based gradient guidance.
  arXiv  Detail & Related papers  (2026-02-11T21:58:26Z)
• DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling [0.7866885337535715]
  Adversarially guided diffusion sampling often achieves the target class, but sample quality degrades as deviations between the adversarially controlled and nominal trajectories accumulate.<n>We formalize this degradation as a path-space Kullback-Leibler divergence(path-KL) between controlled and nominal (uncontrolled) diffusion processes.<n>We show that minimizing this path-KL simultaneously tightens upper bounds on both the Wasserstein distance and Fréchet Inception Distance (FID), revealing a connection between adversarial control energy and perceptual fidelity.
  arXiv  Detail & Related papers  (2025-12-01T00:15:05Z)
• Fluid Antenna System-assisted Physical Layer Secret Key Generation [64.92952968689636]
  This paper investigates physical-layer generation (PLKG) in multiant base station systems by leveraging a fluid antenna system (FAS) to dynamically radio environments.<n>We propose an assisted PLKG model that integrates transmit beamforming and port selection under independent and spatially correlated environments.<n>It is shown that the sliding window-based port selection method introduced in this paper achieves higher KGR with fewer chains through dynamic port selection.
  arXiv  Detail & Related papers  (2025-09-19T03:01:29Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Optimal State Manipulation for a Two-Qubit System Driven by Coherent and Incoherent Controls [77.34726150561087]
  State preparation is important for optimal control of two-qubit quantum systems. We exploit two physically different coherent control and optimize the Hilbert-Schmidt target density matrices.
  arXiv  Detail & Related papers  (2023-04-03T10:22:35Z)
• Manifold Interpolating Optimal-Transport Flows for Trajectory Inference [64.94020639760026]
  We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) MIOFlow learns, continuous population dynamics from static snapshot samples taken at sporadic timepoints. We evaluate our method on simulated data with bifurcations and merges, as well as scRNA-seq data from embryoid body differentiation, and acute myeloid leukemia treatment.
  arXiv  Detail & Related papers  (2022-06-29T22:19:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.