- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper argues that one-step prediction error is a poor proxy for how well a latent world model plans because errors compound over a rollout through the state Jacobians. If the transition is affine in the latent state these Jacobians no longer depend on the state. The authors propose SALT on that basis - a small transition model where the matrix depends on the action trained with a 5-step rollout loss. Compared with a reproduced LeWM, SALT has a higher one step error but plans better on four environments (92.7% vs 82.7% average success) with the largest gain on OGBench-Cube (94% vs 67%). It is also much smaller and plans about 3 times faster.
Critical strengths
- A simple model with a strong result. A transition that is linear in the state, with a predictor about 16 times smaller plans better and about 3 times faster than a Transformer predictor. On Cube the gain is large and it holds at longer horizons, on Cube-Double, and against the published LeWM number.
- The limits are stated plainly. The authors say where their analysis does not apply and the 2×2 ablation (transition structure x training loss) shows what each part contributes.
Critical weaknesses
- It is not shown that the affine structure is what helps. SALT trained with the one-step loss is barely better than LeWM so most of the gain comes with rollout training. SALT also differs in size and in its input (one frame instead of three) with no small nonlinear predictor trained the same way to compare against. Since the title credits the affine structure, this is the main issue for my score.
- The size of the gain is uncertain. Each method in Tables 1 and 3 is a single trained model, and on PushT and Cube the reproduced LeWM is weaker than the numbers reported in the LeWM paper. Those numbers come from a different protocol, so they are not a direct comparison, but against them SALT loses on PushT and gains less on Cube.
Questions for authors
Clarifications
- Can you put the published LeWM numbers in Table 1, explain why your reproduction is lower and report both methods over several training seeds? If the gains hold I would raise my score.
- Can you add a small nonlinear predictor (e.g. an MLP with < 1M parameters) that takes the same input as SALT and is trained with the same rollout loss? If it matches SALT the gain comes from size and training rather than the affine structure and the framing should change.
- How exactly is LeWM trained with the rollout loss given its three-frame history? Was it tuned for this setting?
Suggestions (not decisive)
- Related work: the idea that one-step accuracy does not reflect control quality goes back at least to "Objective Mismatch" (Lambert et al., 2020). Locally linear and Koopman-style latent dynamics for control (PCC, RCE, Koopman MPC) belong in that discussion along with prior rollout-loss results for JEPA predictors (Terver et al., 2026, which the paper cites only for design choices and Lipschitz error bounds; V-JEPA 2-AC, Assran et al., 2025).
- Prop. 2 is a known fact. "We show" in the abstract overstates the theory. It works better as motivation for the design.