- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes LSB, an object-centric world model that separates object state, shared dynamics, and embodiment-specific action encoding. Explicit object states enable prediction, collision queries, and counterfactual rollouts through direct velocity edits. Experiments in a synthetic 2D physics environment evaluate transfer across embodiments, physics regimes, object counts, and rollout horizons, with reported advantages over flat-latent baselines.
Critical strengths
-
The paper addresses an important limitation of predictive world models: supporting targeted queries and object-level interventions, rather than only forecasting future states.
-
The evaluation considers multiple embodiments, physics regimes, object counts, and rollout horizons. Alternative dynamics architectures and training objectives also help explore the sensitivity of the proposed design.
Critical weaknesses
There are two critical implementation errors in the submitted code, that affect the claim in the paper:
-
CLS+v’s evaluation interface discards the intervention velocity. In
lsb/eval/cls_wrap.py:46,CLSWM.predictcallsstep_emb(emb, action, body)without passingstate.v. Consequently,lsb/model/cls_baseline.py:65–66, substitutes zero velocities. This differs from the training interface, which correctly passesv=state.vatLine 108–109. Thus, editing velocity cannot affect CLS+v’s predictions through the supplied evaluation path, invalidating the central claim that the baseline receives identical intervention information. -
Object matching incorrectly conflates predicted-slot and ground-truth-object indices. In
lsb/model/state.py:127,139:143,hungarian_matchuses a singleusedset for both index spaces. Acceptingslot 0 → object 1therefore blocks the valid assignmentslot 1 → object 0. In a minimal test, merely permuting geometrically perfect predictions changes the reported error from 0 to 0.75. This matcher is used in both training supervision (lsb/train/losses.py:8) and evaluation (lsb/eval/general.py:15–21), so the problem potentially affects both learned representations and reported comparisons.
Questions for authors
N/A