RewardDance: Reward Scaling in Visual Generation

• URL: http://arxiv.org/abs/2509.08826v1
• Date: Wed, 10 Sep 2025 17:59:31 GMT
• Title: RewardDance: Reward Scaling in Visual Generation
• Authors: Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, Hanzhong Guo, Jie Liu, Zeyue Xue, Xiaoxia Hou, Wei Liu, Yan Zeng, Weilin Huang,
• Abstract summary: We introduce RewardDance, a scalable reward modeling framework that overcomes barriers through a novel generative reward paradigm.<n>By reformulating the reward score as the model's probability of predicting a "yes" token, RewardDance intrinsically aligns reward objectives with Vision-Language Models.<n>We show that RewardDance significantly surpasses state-of-the-art methods in text-to-image, text-to-video, and image-to-video generation.
• Score: 28.934614189005856
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critically, the RLHF optimization process is plagued by Reward Hacking issue, where models exploit flaws in the reward signal without improving true quality. To address these challenges, we introduce RewardDance, a scalable reward modeling framework that overcomes these barriers through a novel generative reward paradigm. By reformulating the reward score as the model's probability of predicting a "yes" token, indicating that the generated image outperforms a reference image according to specific criteria, RewardDance intrinsically aligns reward objectives with VLM architectures. This alignment unlocks scaling across two dimensions: (1) Model Scaling: Systematic scaling of RMs up to 26 billion parameters; (2) Context Scaling: Integration of task-specific instructions, reference examples, and chain-of-thought (CoT) reasoning. Extensive experiments demonstrate that RewardDance significantly surpasses state-of-the-art methods in text-to-image, text-to-video, and image-to-video generation. Crucially, we resolve the persistent challenge of "reward hacking": Our large-scale RMs exhibit and maintain high reward variance during RL fine-tuning, proving their resistance to hacking and ability to produce diverse, high-quality outputs. It greatly relieves the mode collapse problem that plagues smaller models.

Related papers

• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling [49.41422138354821]
  We propose a principled reward modeling framework that integrates non-negative factor analysis into the Bradley-Terry preference model.<n>BNRM represents rewards through a sparse, non-negative latent factor generative process.<n>We show that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T08:14:11Z)
• FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution [87.57784204422218]
  Reinforcement Learning with Human Feedback has proven effective in image generation field guided by reward models to align human preferences.<n>We propose a Fine-grained Perceptual Reward Model (FinPercep-RM) based on ancoder-Decoder architecture.<n>While providing a global quality score, it also generates a Perceptual Degradation Map that spatially localizes and quantifies local defects.
  arXiv  Detail & Related papers  (2025-12-27T16:55:21Z)
• 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)
• One Token to Fool LLM-as-a-Judge [52.45386385722788]
  Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models.<n>We uncover a critical vulnerability even in this reference-based paradigm: generative reward models are systematically susceptible to reward hacking.
  arXiv  Detail & Related papers  (2025-07-11T17:55:22Z)
• Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling [27.11560841914813]
  We introduce REFORM, a self-improving reward modeling framework that enhances robustness by using the reward model itself to guide the generation of falsely scored responses.<n>We evaluate REFORM on two widely used preference datasets Anthropic Helpful Harmless (HH) and PKU Beavertails.
  arXiv  Detail & Related papers  (2025-07-08T21:56:33Z)
• Activation Reward Models for Few-Shot Model Alignment [77.37511364793515]
  We introduce Activation Reward Models (Activation RMs)<n>Activation RMs leverage activation steering to construct well-aligned reward signals using minimal supervision and no additional model finetuning.<n>We demonstrate the effectiveness of Activation RMs in mitigating reward hacking behaviors, highlighting their utility for safety-critical applications.
  arXiv  Detail & Related papers  (2025-07-02T05:10:29Z)
• RM-R1: Reward Modeling as Reasoning [81.50471199906738]
  Reasoning Reward Models (ReasRMs) formulate reward modeling as a reasoning task.<n>We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1.<n>Our models achieve state-of-the-art performance across three reward model benchmarks on average.
  arXiv  Detail & Related papers  (2025-05-05T06:11:12Z)
• Adversarial Training of Reward Models [74.17196154247964]
  We introduce Adv-RM, a novel adversarial training framework that automatically identifies adversarial examples.<n>By leveraging reinforcement learning, Adv-RM trains a policy to expose vulnerabilities in large state-of-the-art reward models.<n>We demonstrate that Adv-RM significantly outperforms conventional reward training.
  arXiv  Detail & Related papers  (2025-04-08T15:38:25Z)
• Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation [25.29877217341663]
  This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences.<n>We introduce Reward-Instruct, a novel and surprisingly simple reward-centric approach for converting pre-trained base diffusion models into reward-enhanced few-step generators.<n>Our experiments on text-to-image generation have demonstrated that Reward-Instruct achieves state-of-the-art results in visual quality and quantitative metrics.
  arXiv  Detail & Related papers  (2025-03-17T11:21:43Z)
• UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality [52.49062565901046]
  Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models with human values.<n>Existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences.<n>We introduce Utility-Conditioned Multi-Objective Alignment (UC-MOA), a novel framework that overcomes these limitations.
  arXiv  Detail & Related papers  (2025-03-10T09:52:42Z)
• Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs [58.18140409409302]
  Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL)<n>Applying RL in broader domains like chatbots and content generation presents unique challenges.<n>We show a case study of reproducing existing reward model ensemble research using embedding-based reward models.
  arXiv  Detail & Related papers  (2025-02-04T19:37:35Z)
• Visual Autoregressive Modeling for Image Super-Resolution [14.935662351654601]
  We propose a novel visual autoregressive modeling for ISR framework with the form of next-scale prediction.<n>We collect large-scale data and design a training process to obtain robust generative priors.
  arXiv  Detail & Related papers  (2025-01-31T09:53:47Z)
• Reward Incremental Learning in Text-to-Image Generation [26.64026346266299]
  We present Reward Incremental Distillation (RID), a method that mitigates forgetting with minimal computational overhead. The experimental results demonstrate the efficacy of RID in achieving consistent, high-quality gradient generation in RIL scenarios.
  arXiv  Detail & Related papers  (2024-11-26T10:54:33Z)
• CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling [27.86204841898399]
  Reward modeling in large language models is susceptible to reward hacking.<n>We propose Context-Aware Reward Modeling (CARMO) to mitigate this problem.<n>We establish a new state-of-the-art performance in zero-shot settings for generative models, achieving a 2.1% improvement on Reward Bench.
  arXiv  Detail & Related papers  (2024-10-28T21:18:49Z)

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.