- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper adopts test-time training for allowing robotic control models to have weights that can be adapted to allow greater effective context lengths. Concretely, the proposed method adds a learned write gate to fast-weight memory and trains it so that the policy can selectively remember and use memory over long episodes.
Critical strengths
- The design choices are reasonably well-explained. Section 3 is particularly well-written where each component is well-motivated and then the final algorithm is presented in a clear manner.
- The method is SFT-only and does not require RL or other on-policy training methods, which is impressive since the latter are often highly expensive for robotic tasks.
Critical weaknesses
- The scope of novelty is dubious to me. The proposed algorithm’s novelty comes from fine-tuning TTT layers in the vision-language-action model on ordered full episodes instead of independent chunks. Other aspects such as the one adaptation rule per episode does not seem particularly novel to me since it is essentially accumulating gradients over the episode and stepping once, which gives the same gradient as a full episode loss.
- Extremely poor choice of baselines. For the results in Table 2, the only baseline is the base pretrained Karos world-action model and the no-update SFT model. For the real robot experiments (table 4), there is no baseline comparison whatsoever. There’s a wide variety of baselines that one can compare against: these can be open-source models such as RoboTTT, openVLA, CosmosPolicy, MEM, etc. Similarly, the paper requires significantly more ablations. For example, TCA trained with no gate during training as well as deployment, gate trained without TCA, as well as other methods for increasing context lengths of models (PTP [1], keyframes [2], etc.)
- Performance gains are extremely marginal in table 2, the gain of 3.3 points is within the standard error. Same for the results in table 3.
- None of the results show confidence intervals or standard deviation in performance on multiple training seeds.
- Table 3 shows that when , the performance barely changes, in which case the importance of the gate is under serious doubt to the reader.
- Length of demonstrations is not a reliable measure of whether or not the tasks require long-range memory. Most of the tasks in the benchmarks considered have optimal policies that are highly Markovian: the most recent observation captures most of the important information required for solving the task. It would be useful to consider more memory-demanding tasks such as those in [1] or [2] or simple tasks where objects are momentarily occluded for example.
[1] Past-token prediction. https://arxiv.org/pdf/2505.09561 [2] Mem. https://arxiv.org/pdf/2603.03596 [3]. pi 0.5. https://www.pi.website/download/pi05.pdf
Questions for authors
See weaknesses.