About this paper
An end-to-end flow-matching framework generates joint portfolio allocations from raw multi-asset market histories via a cross-asset flow Transformer and a two-stage imitation and group-relative reinforcement learning procedure, improving risk-adjusted returns on cryptocurrency perpetual futures.
Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecasting models and alpha discovery help identify opportunities. However, traditional pipelines often decouple signal forecasting from portfolio construction, potentially misaligning learning with allocation and execution objectives. We present AllocFlow, an end-to-end flow-matching framework that directly generates joint portfolio allocations from raw multi-asset market histories. To capture dependencies among portfolio positions, AllocFlow employs a cross-asset flow Transformer conditioned on…
flow-matching frameworkcross-asset flow Transformertemporal market representationscontinuous signed position weightstwo-stage training schemestrategy-supervised imitationgroup-relative reinforcement learningfrozen policy referenceportfolio-level financial rewardscontinuous allocation policies
- Upvotes
- 22
- Authors
- 8
- Published
- Nov 15, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 12 checks on 2 different days. Its best position was #2 of 30, reached on Nov 17, 13:28 UTC. It dropped off the list after Nov 18, 05:28 UTC.