FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models

• URL: http://arxiv.org/abs/2609.09905v1
• Date: Wed, 09 Sep 2026 09:03:59 GMT
• Title: FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
• Abstract summary: FlowCPO is an offline forward-KL objective that uses both preferred and dispreferred samples without online rollouts.<n>We show that FlowCPO achieves higher mean GenEval and OCR scores than the evaluated baselines.<n>In the out-of-domain setting, the results are mixed, with the best GenEval result but lower reward scores than CFT on several metrics.
• Score: 17.73780737579933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains unclear. In particular, existing forward-process alignment methods require fresh samples from the current model, while offline methods based on fixed preference pairs rely primarily on positive-only fine-tuning or DPO-style likelihood-ratio surrogates. We organize these approaches through a divergence-based framework and introduce FlowCPO, an offline forward-KL objective that uses both preferred and dispreferred samples without online rollouts. For linear interpolation, we show under explicit regularity conditions that the forward-KL objective is bounded by a contrastive flow matching loss, yielding a tractable surrogate on fixed data. We further show that this loss is nonnegative, whereas the signed regression loss of simplified FlowDPO can be unbounded below. In the in-domain setting, FlowCPO achieves higher mean GenEval and OCR scores than the evaluated baselines, reaching 0.84 and 0.87 versus 0.81 and 0.74 for FlowDPO at CFG 3.0. In the out-of-domain setting, the results are mixed, with the best GenEval result but lower reward scores than RFT on several metrics.

Related papers

• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models [61.74572554094633]
  We argue that ratio clipping is structurally ill-suited for flow models.<n>We propose Flow-DPPO, which replaces ratio clipping with a divergence proximal constraint.<n> Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency.
  arXiv  Detail & Related papers  (2026-06-09T15:59:57Z)
• TPMM-DPO: Trajectory-aware Preference-guided Model Merging for Iterative Direct Preference Optimization [0.0]
  We propose TPMM-DPO, a trajectory-aware preference-guided model merging method.<n>In contrast to conventional iterative DPO, TPMM-DPO effectively mitigates error accumulation induced by noisy preferences.
  arXiv  Detail & Related papers  (2026-05-22T09:11:20Z)
• Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models [5.527466367347639]
  We derive a generalized DPO objective that covers both diffusion and flow-matching via a unified reverse-time SDE framework.<n>We propose Linear-DPO, which replaces the aggressive sigmoid-based utility function with a sustained linear utility and incorporates an EMA-updated reference model.
  arXiv  Detail & Related papers  (2026-05-20T12:54:51Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models [90.45197506653341]
  Large reasoning models generate intermediate reasoning traces before producing final answers.<n> aligning LRMs with human preferences, a crucial prerequisite for model deployment, remains underexplored.<n>A common workaround optimized a single sampled trajectory, which introduces substantial gradient variance from trace sampling.
  arXiv  Detail & Related papers  (2025-10-06T17:58:01Z)
• DiffusionNFT: Online Diffusion Reinforcement with Forward Process [99.94852379720153]
  Diffusion Negative-aware FineTuning (DiffusionNFT) is a new online RL paradigm that optimize diffusion models directly on the forward process via flow matching.<n>DiffusionNFT is up to $25times$ more efficient than FlowGRPO in head-to-head comparisons, while being CFG-free.
  arXiv  Detail & Related papers  (2025-09-19T16:09:33Z)
• Preference Trajectory Modeling via Flow Matching for Sequential Recommendation [50.077447974294586]
  Sequential recommendation predicts each user's next item based on their historical interaction sequence.<n>FlowRec is a simple yet effective sequential recommendation framework.<n>We construct a personalized behavior-based prior distribution to replace Gaussian noise and learn a vector field to model user preference trajectories.
  arXiv  Detail & Related papers  (2025-08-25T02:55:42Z)
• Calibrated Multi-Preference Optimization for Aligning Diffusion Models [90.15024547673785]
  Calibrated Preference Optimization (CaPO) is a novel method to align text-to-image (T2I) diffusion models.<n>CaPO incorporates the general preference from multiple reward models without human annotated data.<n> Experimental results show that CaPO consistently outperforms prior methods.
  arXiv  Detail & Related papers  (2025-02-04T18:59:23Z)
• Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching [13.634043135217254]
  We propose Flow Matching-based Posterior Sampling (FMPS) to expand its application scope.<n>This correction term can be reformulated to incorporate a surrogate score function.<n>We show that FMPS achieves superior generation quality compared to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-11-12T08:14:39Z)

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.