Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

• URL: http://arxiv.org/abs/2510.18053v1
• Date: Mon, 20 Oct 2025 19:46:02 GMT
• Title: Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
• Authors: Jiajun Fan, Tong Wei, Chaoran Cheng, Yuxin Chen, Ge Liu,
• Abstract summary: Adaptive Divergence Regularized Policy Optimization automatically adjusts regularization strength based on advantage estimates.<n>Our implementation with Wasserstein-2 regularization for flow matching generative models achieves remarkable results on text-to-image generation.<n> ADRPO generalizes to KL-regularized fine-tuning of both text-only LLMs and multi-modal reasoning models.
• Score: 31.470613363668672
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong regularization preserves model capabilities but limits reward optimization, while weak regularization enables greater alignment but risks instability or reward hacking. We introduce Adaptive Divergence Regularized Policy Optimization (ADRPO), which automatically adjusts regularization strength based on advantage estimates-reducing regularization for high-value samples while applying stronger regularization to poor samples, enabling policies to navigate between exploration and aggressive exploitation according to data quality. Our implementation with Wasserstein-2 regularization for flow matching generative models achieves remarkable results on text-to-image generation, achieving better semantic alignment and diversity than offline methods like DPO and online methods with fixed regularization like ORW-CFM-W2. ADRPO enables a 2B parameter SD3 model to surpass much larger models with 4.8B and 12B parameters in attribute binding, semantic consistency, artistic style transfer, and compositional control while maintaining generation diversity. ADRPO generalizes to KL-regularized fine-tuning of both text-only LLMs and multi-modal reasoning models, enhancing existing online RL methods like GRPO. In LLM fine-tuning, ADRPO demonstrates an emergent ability to escape local optima through active exploration, while in multi-modal audio reasoning, it outperforms GRPO through superior step-by-step reasoning, enabling a 7B model to outperform substantially larger commercial models including Gemini 2.5 Pro and GPT-4o Audio, offering an effective plug-and-play solution to the exploration-exploitation challenge across diverse generative architectures and modalities.

Related papers

• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation [60.33386541343322]
  We propose a Multimodal Large Language Models framework that integrates Hardness-aware and Noise-regularized preference optimization for Recommendation (HaNoRec)<n>Specifically, HaNoRec dynamically adjusts optimization weights based on both the estimated hardness of each training sample and the policy model's real-time responsiveness.
  arXiv  Detail & Related papers  (2025-11-24T04:10:46Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• Policy Regularized Distributionally Robust Markov Decision Processes with Linear Function Approximation [10.35045003737115]
  Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ.<n>We propose DR-RPO, a model-free online policy optimization method that learns robust policies with sublinear regret.<n>We show that DR-RPO can achieve suboptimality bounds and sample efficiency in robust RL, matching the performance of value-based approaches.
  arXiv  Detail & Related papers  (2025-10-16T02:56:58Z)
• G$^2$RPO: Granular GRPO for Precise Reward in Flow Models [74.21206048155669]
  We propose a novel Granular-GRPO (G$2$RPO) framework that achieves precise and comprehensive reward assessments of sampling directions.<n>We introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales.<n>Our G$2$RPO significantly outperforms existing flow-based GRPO baselines.
  arXiv  Detail & Related papers  (2025-10-02T12:57:12Z)
• ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning [17.928214942495412]
  ACPO employs a dynamic curriculum that orchestrates a principled transition from a stable, near on-policy exploration phase to an efficient, off-policy exploitation phase.<n>We conduct extensive experiments on a suite of challenging multimodal reasoning benchmarks, including MathVista, LogicVista, and MMMU-Pro.<n>Results demonstrate that ACPO consistently outperforms strong baselines such as DAPO and PAPO, achieving state-of-the-art performance, accelerated convergence, and superior training stability.
  arXiv  Detail & Related papers  (2025-10-01T09:11:27Z)
• TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making [75.29820290660065]
  This paper proposes Thought-Centric Preference Optimization ( TCPO) for effective embodied decision-making.<n>It emphasizes the alignment of the model's intermediate reasoning process, mitigating the problem of model degradation.<n>Experiments in the ALFWorld environment demonstrate an average success rate of 26.67%, achieving a 6% improvement over RL4VLM.
  arXiv  Detail & Related papers  (2025-09-10T11:16:21Z)
• Preference-Based Alignment of Discrete Diffusion Models [14.874943508610857]
  We introduce Discrete Diffusion DPO (D2-DPO), the first adaptation of Direct Preference Optimization (DPO) to discrete diffusion models formulated as continuous-time Markov chains.<n>Our approach derives a novel loss function that directly fine-tunes the generative process using preference data while preserving fidelity to a reference distribution.<n>Our results highlight that D2-DPO enables controlled fine-tuning without requiring explicit reward models, making it a practical alternative to reinforcement learning-based approaches.
  arXiv  Detail & Related papers  (2025-03-11T11:07:35Z)
• Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization [14.320131946691268]
  We propose an easy-to-use and theoretically sound fine-tuning method for flow-based generative models.<n>By introducing an online rewardweighting mechanism, our approach guides the model to prioritize high-reward regions in the data manifold.<n>Our method achieves optimal policy convergence while allowing controllable trade-offs between reward and diversity.
  arXiv  Detail & Related papers  (2025-02-09T22:45:15Z)
• Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints [26.274786600234876]
  The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but amplify safety concerns. RLHF has emerged as a promising pathway towards AI alignment but brings forth challenges due to its complexity and dependence on a separate reward model. DPO has been proposed as an alternative, and it remains equivalent to RLHF under the reverse KL regularization constraint. We show that under certain $f$-divergences, including Jensen-Shannon divergence, forward KL divergences and $alpha$-divergences, the complex relationship between the reward and optimal policy can also be simplified
  arXiv  Detail & Related papers  (2023-09-28T08:29:44Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)

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.