Unified Reward Model for Multimodal Understanding and Generation

• URL: http://arxiv.org/abs/2503.05236v1
• Date: Fri, 07 Mar 2025 08:36:05 GMT
• Title: Unified Reward Model for Multimodal Understanding and Generation
• Authors: Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, Jiaqi Wang,
• Abstract summary: 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.
• Score: 32.22714522329413
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in human preference alignment have significantly enhanced multimodal generation and understanding. A key approach is training reward models to guide preference optimization. However, existing models are often task-specific, limiting their adaptability across diverse visual applications. We also argue that jointly learning to assess multiple tasks may foster a synergistic effect, where improved image understanding enhances image generation assessment, and refined image evaluation benefits video assessment through better frame analysis. To this end, this paper proposes UnifiedReward, the first unified reward model for multimodal understanding and generation assessment, enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment. Specifically, (1) we first develop UnifiedReward on our constructed large-scale human preference dataset, including both image and video generation/understanding tasks. (2) Then, it is utilized to automatically construct high-quality preference pair data based on the vision models, fine-gradually filtering their outputs through pair ranking and point sifting. (3) Finally, these data are used for their preference alignment through Direct Preference Optimization (DPO). Experimental results demonstrate that joint learning to assess diverse visual tasks can lead to substantial mutual benefits and we apply our pipeline to both image and video understanding/generation tasks, significantly improving the performance in each domain.

Related papers

• Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Preference Understanding [29.191627597682597]
  We present a framework incorporating human-in-the-loop feedback, leveraging a well-trained reward model aligned with user preferences. Our approach consistently surpasses competing models in user satisfaction, especially in multi-turn dialogue scenarios.
  arXiv  Detail & Related papers  (2025-04-25T09:35:02Z)
• Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data [35.229595049396245]
  We propose a novel visual rejection sampling framework to improve the cognition and explainability of LMMs.<n>Our approach begins by synthesizing interpretable answers that include human-verifiable visual features.<n>After each round of fine-tuning, we apply a reward model-free filtering mechanism to select the highest-quality interpretable answers.
  arXiv  Detail & Related papers  (2025-02-19T19:05:45Z)
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step [77.86514804787622]
  Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks.<n>We provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation.<n>We propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:43Z)
• Multimodal Preference Data Synthetic Alignment with Reward Model [23.978820500281213]
  We propose a new framework in generating synthetic data using a reward model as a proxy of human preference for effective multimodal alignment with DPO training.<n>Experiment results indicate that integrating selected synthetic data, such as from generative and rewards models can effectively reduce reliance on human-annotated data.
  arXiv  Detail & Related papers  (2024-12-23T09:29:40Z)
• Scalable Ranked Preference Optimization for Text-to-Image Generation [76.16285931871948]
  We investigate a scalable approach for collecting large-scale and fully synthetic datasets for DPO training. The preferences for paired images are generated using a pre-trained reward function, eliminating the need for involving humans in the annotation process. We introduce RankDPO to enhance DPO-based methods using the ranking feedback.
  arXiv  Detail & Related papers  (2024-10-23T16:42:56Z)
• MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models [85.30735602813093]
  Multi-Image Augmented Direct Preference Optimization (MIA-DPO) is a visual preference alignment approach that effectively handles multi-image inputs. MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats.
  arXiv  Detail & Related papers  (2024-10-23T07:56:48Z)
• 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)
• Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models [85.96013373385057]
  Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimization with such reward models, which serve as mere proxy objectives, can compromise the performance of fine-tuned models. We propose TextNorm, a method that enhances alignment based on a measure of reward model confidence estimated across a set of semantically contrastive text prompts.
  arXiv  Detail & Related papers  (2024-04-02T11:40:38Z)
• Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances [49.631908848868505]
  Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. We investigate the differences in CLIP performance among various neural architectures. We propose a simple, yet effective approach to combine predictions from multiple backbones, leading to a notable performance boost of up to 6.34%.
  arXiv  Detail & Related papers  (2023-12-22T03:01:41Z)
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision [74.9260745577362]
  This paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC) principles. We construct three propagative modules to effectively solve the optimization models with flexible combinations. Experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC.
  arXiv  Detail & Related papers  (2020-12-10T03:24:53Z)

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.