- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents GeoMerge-OPD, a framework for combining multiple VLA experts into a single policy. Its main contribution is a regularizer that makes experts easier to merge. The merged policy is then refined through on-policy distillation. Experiments with two VLA backbones on SIMPLE, LIBERO, and LIBERO-PRO show the promising results.
Critical strengths
- The paper offers an insightful approach to improving mergeability by analyzing and regularizing expert responses before merging. Ablations across multiple merging methods and two VLA backbones show that regularized experts merge more successfully than standard experts, while largely preserving individual expert performance. This provides convincing evidence for the practical value of the proposed regularizer.
- The paper provides substantial theoretical and empirical support, with carefully designed comparisons. TIES, WUDI, and RegMean++ also use G-isometry-regularized experts, while Joint FT is evaluated from both the pretrained base and the same regularized merge used by the proposed method. These controls make the comparisons more informative and help separate the benefits of initialization from those of subsequent training.
Critical weaknesses
The benefit of velocity-field supervision over final-action distillation remains unclear. Although the paper motivates its objective through a local KL formulation, it does not compare against a simpler baseline that learns from the teachers’ final actions under the same initialization and interaction budget. This makes it difficult to determine whether the gains come from the proposed distillation design or from access to dense teacher supervision more generally.
Questions for authors
Some tasks may benefit from stronger responses along particular directions. Have you observed cases where the regularizer hurts individual expert performance, and how sensitive is this trade-off to the regularization strength?
5 comments
Response to Reviewer hu18 (2/2)
【part 2/2】
Q1. Does regularization hurt individual expert performance, and how sensitive is this to its strength?
A Q1. Thank you for the question. To address your concern about regularization strength, we added a regularization-strength ablation on SIMPLE. We test , with the default strength in the submitted paper set to . All groups use the same remaining expert-training configuration and RegMean++ merging setup. For each nonzero strength, we initialize the student with the corresponding merged model and use the task-specific experts trained at that strength as teachers for OPD. The results are as follows:
| BendPick expert (%) | CloseDoor expert (%) | OpenOven expert (%) | Expert avg. (%) | Static merge avg. (%) | GeoMerge-OPD avg. (%) | |
|---|---|---|---|---|---|---|
| 0 (Standard FT) | 90.0 | 100.0 | 100.0 | 96.7 | 3.3 | 23.3 |
| 0.5 | 100.0 | 100.0 | 100.0 | 100.0 | 20.0 | 43.3 |
| 1.0 (default) | 100.0 | 100.0 | 100.0 | 100.0 | 40.0 | 86.7 |
| 2.0 | 90.0 | 100.0 | 90.0 | 93.3 | 46.7 | 86.7 |
Note: The OPD result is taken from the fixed-teacher initialization comparison in Table 8 of the submitted paper and is included as a reference.
The following per-task results further show skill retention after OPD at different regularization strengths:
| BendPick | CloseDoor | OpenOven | GeoMerge-OPD avg. (%) | |
|---|---|---|---|---|
| 0 (Standard FT) | 0/10 | 6/10 | 1/10 | 23.3 |
| 0.5 | 3/10 | 5/10 | 5/10 | 43.3 |
| 1.0 (default) | 8/10 | 10/10 | 8/10 | 86.7 |
| 2.0 | 7/10 | 10/10 | 9/10 | 86.7 |
Within the tested range of regularization strengths, the task-specific experts maintain high overall success rates, with small decreases on individual tasks under stronger regularization. Weaker regularization already improves skill integration, but its performance remains below the default setting. Further increasing the strength yields similar average performance after OPD to the default. The default regularization strength in the submitted paper therefore provides a useful balance between preserving individual expert capabilities and integrating multiple skills.
Looking Forward to Your Further Feedback
Thank you for your thoughtful comments and for raising clear and important questions. Your feedback is helping us strengthen the paper, and we sincerely appreciate your time and effort.
In our rebuttal, we have responded to the points you raised. We would appreciate hearing whether our responses have addressed your concerns and whether you have any remaining questions. We look forward to further discussion and suggestions, as they will help us improve the quality of the paper.
If your concerns have been satisfactorily addressed, we would be grateful if you would consider updating your score accordingly.
Response to Reviewer hu18 (1/2)
【part 1/2】
We would like to thank the reviewer for appreciating our analysis of expert responses and the controlled comparisons. We provide an additional final-action distillation comparison and a regularization-strength ablation on SIMPLE, which we hope can address your concerns.
W1. What does velocity-field supervision add over final-action distillation?
A W1. Thank you for the suggestion. To clarify the benefit of velocity-field supervision, we added a final-action distillation baseline that trains the student using teacher-generated actions as labels. Both settings use the same G-regularized initialization and task-specific teachers, with matched environment-interaction and optimizer-update budgets. This comparison evaluates learning from the teachers' final actions versus teacher velocity-field supervision at the student's intermediate action-flow states.
Under these matched conditions, velocity-field distillation achieves higher success across all three benchmarks. This shows that supervising the student's intermediate action-generation states with teacher velocity-field targets improves the shared policy's closed-loop performance relative to final-action distillation.