- Rating
- 4
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper studies the joint enhancement of understanding and generation capabilities in Unified Multimodal Models (UMMs). It proposes ReasonUni, which connects visual understanding and image generation through an inference-driven image editing and reconstruction task, and designs TreeGRPO, which decomposes the reward for generated images into an understanding branch reward and a generation reward to achieve joint reinforcement learning.
Critical strengths
- The paper introduces a novel approach to supervising visual reasoning through reasoning-augmented reconstruction. The model infers the target state from an editing instruction and uses reconstruction feedback to improve this inference, offering a promising way to strengthen visual reasoning through image generation.
- TreeGRPO is intuitive and well motivated, allowing relatively separate evaluation of the understanding and generation policies for cleaner credit assignment. The latent reward complements this design by avoiding image decoding and external encoding, improving training efficiency while maintaining strong performance.
Critical weaknesses
- The reward ablation settings need more detail. For example, how is GPT-4.1 used for scoring, and how are external encoder features converted into rewards? Please clarify these implementations and whether all variants use the same training settings.
- The motivation for branch-level averaging could be supported more directly. An analysis of within-branch and between-branch reward variance using existing rollouts could help quantify the uncertainty that TreeGRPO aims to mitigate.
Questions for authors
- Could the author provide more details of the reward ablation settings?
- Could the authors provide an analysis of within-branch and between-branch reward variance using existing rollouts to better quantify the uncertainty that TreeGRPO?
3 comments
Thanks for the reply. The rebuttal addresses most of my concerns. I think the comparison with dedicated understanding RL and the multi-seed results are reasonable. I maintain my initial rating and recommend acceptance.
We appreciate your positive assessment of the two experiments we conducted to address the other reviewers’ concerns about ReasonUni’s understanding gains. Thank you again for your thoughtful review and continued support!
Response to Reviewer Qoak
We thank the reviewer for the concrete suggestions.
W1. Reward ablation settings
All reward variants share the same data, training steps, initialization, and optimization settings (K=M=4); only the reward differs:
We will add these details to the supp.
W2. Motivation for averaging rewards within branches
Branch averaging nearly halves ranking errors among descriptions. From existing rollouts, the reward variance is 0.001172 within branches and 0.006012 across branch means. The und. policy, however, learns from the ranking of the K descriptions of an input, which single-image rewards flip often.
We fixed four target descriptions and scored them twice with disjoint sets of generated images. The two evaluations pick different top descriptions 39.90% of the time with one image per description, vs. 22.51% with the average of four (random: 75%). Averaging thus gives the und. policy a markedly more stable signal.