- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies whether a pretrained JEPA transition predictor can serve as a direct visuomotor policy backbone. LTM-Policy combines an action-query policy route with an action-conditioned future-prediction route, using a frozen visual encoder and a flow-matching action head. It reports 97.4% average success on LIBERO, controlled initialization and future-supervision ablations, and evaluations on LIBERO-Plus and three real-robot tasks.
Critical strengths
-
The paper asks a useful, focused question beyond visual encoder transfer. With architecture and observations fixed, pretrained predictor weights improve LIBERO-Long from 83.2% to 94.4% under the same future-supervision objective (Table 3).
-
The initialization-by-objective comparison is informative. Pretraining also helps with action-only training, while future supervision adds another 5.4 points to the pretrained model on Long. This separates two plausible sources of improvement.
-
The policy avoids video rollout and search at deployment. The low-data results and physical demonstrations make the transfer idea more convincing than benchmark accuracy alone.
Critical weaknesses
-
Table 3 removes future supervision as a whole, without separating the policy-future and world-future losses. It therefore does not establish whether the proposed dual-route design is needed beyond a simpler policy with one auxiliary prediction loss.
-
The benchmark comparisons mix task-ID conditioning with language-conditioned policies. The paper acknowledges this, but Table 2 still includes an unaffected language category in the 67.4% headline average; the non-language score is 62.6%. Matched comparisons would better support the robustness claim.
-
Uncertainty around the gains is not reported across independent training runs. The real-robot study has only 20 trials per task and no comparison policy, so it establishes feasibility more clearly than a transfer advantage on hardware.
Questions for authors
-
Can you separate the two future losses while keeping action-supervised updates and training compute matched? Which route accounts for the improvement on Long?
-
How does LTM-Policy compare with a strong baseline under the same task conditioning and camera inputs, particularly on the non-language LIBERO-Plus categories?
-
How stable are the Table 3 gains across training seeds, and is there a matched action-only or random-initialization baseline for the physical tasks?
Thank you for the clarifications and the additional experiments. The response explains the practical advantages of deployment without video generation or planning. However, beyond extending the idea of transfer learning to the JEPA framework, it remains unclear what substantive conceptual advance this work makes over existing WAM approaches. The additional experiments show that the benefit of pretrained initialization does not depend on downstream future prediction supervision, but they still do not establish that the improvement in downstream performance is due to action-conditioned transition knowledge. I therefore maintain my score.