- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper studies forgetting of pretrained multimodal capabilities during vision-language-action adaptation. Building on BAGEL and the three-expert formulation inherited from BagelVLA, UAM couples semantic, generative Dorsal, and action experts through MoT. The Dorsal branch receives future-observation prediction supervision and provides complementary visual features for action generation, while all three experts remain trainable without gradient blocking or auxiliary vision-language replay. The main contribution is a controlled study of how Dorsal initialization, input modality, visual-dynamics supervision, and semantic-expert trainability affect retention and control. Validation includes multimodal benchmarks, CALVIN and RoboTwin simulations, and real-robot semantic generalization tests after training on 3,000 trajectories. The strongest configuration retains 96.7% of pretrained scores across four matched multimodal metrics, compared with 54.8% without the Dorsal branch, while improving control and generalization to unseen objects, novel object–target combinations, and instruction variations.
Critical strengths
-
Systematic ablation study
The paper examines how Dorsal initialization, visual versus query inputs, future-observation supervision, and semantic-expert trainability affect multimodal retention and robot control. These comparisons provide useful empirical evidence about forgetting during VLA adaptation.
-
Joint evaluation of retention and control
The paper evaluates both pretrained multimodal capabilities and embodied performance, showing that strong retention can coexist with improved control while the semantic expert remains trainable, without auxiliary vision-language replay.
Critical weaknesses
-
The embodied evaluation is relatively limited
Experiments on VLABench, LIBERO-Pro, or LIBERO-Plus would help validate broader generalization and robustness.
-
The analysis of forgetting is not very detailed
The ablations and attention maps show improved retention, but do not fully explain why the Dorsal expert reduces forgetting.
Questions for authors
- What technical changes does UAM introduce beyond BagelVLA, apart from the study of forgetting and retention?
- What evidence beyond the attention maps shows that the Dorsal expert reduces interference with the semantic expert during action training?
- Are additional results available on VLABench, LIBERO-Pro, or LIBERO-Plus to show whether the improvements extend beyond the reported tasks?