Unified Personalized Reward Model for Vision Generation

• URL: http://arxiv.org/abs/2602.02380v2
• Date: Tue, 10 Feb 2026 12:52:22 GMT
• Title: Unified Personalized Reward Model for Vision Generation
• Authors: Yibin Wang, Yuhang Zang, Feng Han, Jiazi Bu, Yujie Zhou, Cheng Jin, Jiaqi Wang,
• Abstract summary: We propose UnifiedReward-Flex, a unified personalized reward model for vision generation.<n>We first distill structured, high-quality reasoning traces from advanced closed-source VLMs to bootstrap SFT.<n>We then perform direct preference optimization (DPO) on carefully curated preference pairs to further strengthen reasoning fidelity and discriminative alignment.
• Score: 27.496220369122494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and subsequently optimize visual generation models via reinforcement learning. However, current RMs suffer from inherent limitations: they often follow a one-size-fits-all paradigm that assumes a monolithic preference distribution or relies on fixed evaluation rubrics. As a result, they are insensitive to content-specific visual cues, leading to systematic misalignment with subjective and context-dependent human preferences. To this end, inspired by human assessment, we propose UnifiedReward-Flex, a unified personalized reward model for vision generation that couples reward modeling with flexible and context-adaptive reasoning. Specifically, given a prompt and the generated visual content, it first interprets the semantic intent and grounds on visual evidence, then dynamically constructs a hierarchical assessment by instantiating fine-grained criteria under both predefined and self-generated high-level dimensions. Our training pipeline follows a two-stage process: (1) we first distill structured, high-quality reasoning traces from advanced closed-source VLMs to bootstrap SFT, equipping the model with flexible and context-adaptive reasoning behaviors; (2) we then perform direct preference optimization (DPO) on carefully curated preference pairs to further strengthen reasoning fidelity and discriminative alignment. To validate the effectiveness, we integrate UnifiedReward-Flex into the GRPO framework for image and video synthesis, and extensive results demonstrate its superiority.

Related papers

• 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)
• SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models [53.19726629537694]
  Post-training alignment of video generation models with human preferences is a critical goal.<n>Current data collection paradigms, reliant on in-prompt pairwise annotations, suffer from labeling noise.<n>We propose SoliReward, a systematic framework for video RM training.
  arXiv  Detail & Related papers  (2025-12-17T14:28:23Z)
• RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems [85.16327248973387]
  We develop RoleRM, a reward model trained with Continuous Implicit Preferences (CIP)<n>We show RoleRM surpasses strong open- and closed-source reward models by over 24% on average.<n>Our findings highlight the importance of continuous preference representation and annotation consistency, establishing a foundation for subjective alignment in human-centered dialogue systems.
  arXiv  Detail & Related papers  (2025-12-11T12:04:46Z)
• Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models [16.152962349146275]
  We propose Reflective Personalization Optimization (RPO), a framework that redefines the personalization paradigm by decoupling content generation from alignment.<n>RPO operates in two distinct stages: first, a base model generates a high-quality, generic response; then, an external reflection module explicitly rewrites this output to align with the user's preferences.<n> Comprehensive experiments on the LaMP benchmark demonstrate that RPO, by decoupling content generation from personalization, significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-07T14:48:49Z)
• Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization [63.169050703903515]
  We propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL)<n>Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data.<n>Experiments demonstrate that Aes-R1 improves the backbone's average PLCC/SRCC by 47.9%/34.8%.
  arXiv  Detail & Related papers  (2025-09-26T04:55:00Z)
• ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization [20.935028961216325]
  ConceptMix++ is a framework that disentangles prompt phrasing from visual generation capabilities.<n>We show that optimized prompts significantly improve compositional generation performance.<n>These findings demonstrate that rigid benchmarking approaches may significantly underrepresent true model capabilities.
  arXiv  Detail & Related papers  (2025-07-04T03:27:04Z)
• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning [31.727984223052648]
  This paper proposes UnifiedReward-Think, the first unified multimodal CoT-based reward model.<n>We first use a small amount of image generation preference data to distill the reasoning process of GPT-4o.<n>We then prepare large-scale unified multimodal preference data to elicit the model's reasoning process across various vision tasks.
  arXiv  Detail & Related papers  (2025-05-06T08:46:41Z)
• Unified Reward Model for Multimodal Understanding and Generation [32.22714522329413]
  This paper proposes UnifiedReward, the first unified reward model for multimodal understanding and generation assessment.<n>We first develop UnifiedReward on our constructed large-scale human preference dataset, including both image and video generation/understanding tasks.
  arXiv  Detail & Related papers  (2025-03-07T08:36:05Z)
• Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms [91.19304518033144]
  We aim to align vision models with human aesthetic standards in a retrieval system. We propose a preference-based reinforcement learning method that fine-tunes the vision models to better align the vision models with human aesthetics.
  arXiv  Detail & Related papers  (2024-06-13T17:59:20Z)
• Calibrated Self-Rewarding Vision Language Models [27.686545023186852]
  Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image. We propose the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning.
  arXiv  Detail & Related papers  (2024-05-23T14:30:33Z)
• Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation [87.50120181861362]
  VisionPrefer is a high-quality and fine-grained preference dataset that captures multiple preference aspects. We train a reward model VP-Score over VisionPrefer to guide the training of text-to-image generative models and the preference prediction accuracy of VP-Score is comparable to human annotators.
  arXiv  Detail & Related papers  (2024-04-23T14:53:15Z)

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.