- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes PreMerge, a framework for constructing VLA initializations by merging aligned VLM components from models sharing a common pretrained base. The method first combines adaptive parameter weighting with sign-conflict filtering, then learns tensor-level merging coefficients through feature distillation. Experiments on two simulation benchmarks and four real-world manipulation tasks show the improvements. However, actually, I do not really understand the motivation behind it. It seems the method works, but I do not understand why it works. The writing should be improved.
Critical strengths
- The paper addresses a practically relevant question: whether models from different training stages can be reused to construct a better initialization for downstream robot learning.
- Calibration requires no action annotations, and the merged parameters are folded into a single VLM.
- Experiments are overall good.
Critical weaknesses
- The most concern I have is that the connection between feature-change consistency and downstream task quality is insufficiently justified. The calibration target averages source features when their changes relative to the base have nonnegative cosine similarity; otherwise, it preserves the initial merged representation. However, agreement between feature changes does not necessarily imply that those changes are useful for robot control.
For example, both sources could increasingly encode the same background or camera-specific shortcut. Their feature changes would be aligned, yet distilling their average could reinforce a spurious correlation and hurt performance when the background changes, right? On the other hand, the paper does not sufficiently explain when consistency indicates useful shared knowledge rather than shared error. I mean, it depends on how good the models are? And also the variance between the training datasets.
-
The motivation and technical novelty are not clearly articulated. Several central components are inherited from prior work: magnitude-, direction-, and rank-based weighting from WIDEN, sign-conflict erasure from SCE, and feature-distillation-based merging from ProDistill. It is therefore difficult to identify the specific methodological advance. Is the principal novelty the consistency-conditioned teacher-selection rule, the joint multilayer calibration, or their application before target-task action training? The abstract and introduction should state this distinction explicitly and explain the limitation of existing methods that necessitates the proposed modification.
-
Several figures are difficult to read. The framework diagram and some multi-panel analysis figures contain very small text, labels, and equations. This makes an already complex pipeline harder to follow. The symbols are also too numerous; consider adding a symbol table. It's very hard to follow.
Questions for authors
- With the initial merged model, coefficient parameterization, and calibration budget fixed, how does the proposed teacher-selection rule compare with always averaging source features?
- Which layers or feature groups best distinguish the source backbones, and does removing or replacing those groups affect the gains from merging?
- I am curious which layers, token positions, or feature dimensions most clearly distinguish the sources? Do these differences reflect object identity, spatial relationships, physical interactions, or task-irrelevant appearance?