Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
This addresses the problem of aligning AI behaviors with human preferences across diverse modalities for AI researchers and practitioners, representing an incremental advancement in reward modeling.
The paper tackles the challenges of modality imbalance and preference rigidity in reward models by proposing Omni-Reward, a generalist omni-modal reward modeling approach with free-form preferences, which achieves strong performance on a new benchmark covering nine tasks across five modalities.
Reward models (RMs) play a critical role in aligning AI behaviors with human preferences, yet they face two fundamental challenges: (1) Modality Imbalance, where most RMs are mainly focused on text and image modalities, offering limited support for video, audio, and other modalities; and (2) Preference Rigidity, where training on fixed binary preference pairs fails to capture the complexity and diversity of personalized preferences. To address the above challenges, we propose Omni-Reward, a step toward generalist omni-modal reward modeling with support for free-form preferences, consisting of: (1) Evaluation: We introduce Omni-RewardBench, the first omni-modal RM benchmark with free-form preferences, covering nine tasks across five modalities including text, image, video, audio, and 3D; (2) Data: We construct Omni-RewardData, a multimodal preference dataset comprising 248K general preference pairs and 69K instruction-tuning pairs for training generalist omni-modal RMs; (3) Model: We propose Omni-RewardModel, which includes both discriminative and generative RMs, and achieves strong performance on Omni-RewardBench as well as other widely used reward modeling benchmarks.