- Rating
- 1(−1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
In LeWM and PLDM, the planning objective is the distance between the predicted final state and the goal. This objective is symmetric and blind to obstacles, which leads to poor planning performance. The authors propose TGCC, a post-hoc add-on that keeps the world model frozen. It builds a directed graph from offline trajectories, uses BFS to label which state pairs are reachable, and distills these labels into a small network that serves as a control cost. The authors show that with this cost, the world model's planning performance improves.
Critical strengths
- The paper proposes a lightweight, general fix that could be applied anywhere.
- Experiments on the benchmarks show that it matches or beats all baselines across four tasks.
- The paper provides clean supporting analysis in Two-Room, and the ablations show that the components are complementary and that directionality helps.
Critical weaknesses
- The core idea, learning a directed, goal-conditioned distance from offline trajectory connectivity and using it as a planning cost, is well established. Applying it to world models and CEM does not overcome any new challenges or provide additional insights.
- Weak experimental evaluation: the tasks are short-horizon standard benchmarks, and the qualitative examples are selected failure cases. The authors claim that Figure S1 shows cases where LeWM fails and TGCC succeeds, but the PushT example is clearly a failure, since the T's final position is even farther from the goal than its initial position.
Questions for authors
- How does the method perform on out-of-distribution (OOD) states or goals?
- What assumptions does graph construction make about the dataset? For example, trajectories presumably need to share overlapping or nearby states so that disjoint trajectories can be connected.
I thank the authors for their hard work and the many detailed additional results.
On motivation and contribution. In my view, a robotics paper ultimately aims to complete the task. Taking PushT as a concrete example: if the final pose has a larger error than the initial pose, I would not consider the episode a success. If the paper instead targets a different problem, such as feature prediction rather than trajectory planning, then this task is not an appropriate way to demonstrate its performance. Comparisons with baselines cannot resolve this concern.
On novelty and generalization. I now better understand the problem the authors aim to solve: distilling global, demonstration-derived information into a local, step-wise planning cost through a separate network, without modifying the encoder. However, this raises a concern about generalization. I am less concerned with visual shifts (color, shape) than with layout shifts. The world model learns local one-step dynamics, which can transfer to new layouts, whereas hη distills global multi-step reachability from the specific training trajectories. Table 3 (Spearman 0.949) and Table 2 (99.2% on Two-Room using hη alone) suggest that it has memorized the topology of the training layout. I would therefore expect it to mislead the planner when the layout changes, for example, when the doorway in Two-Room is moved while hη remains trained on the original map. Rebuilding the graph would require data from the new layout, which undermines the zero-shot planning motivation of JEPA world models. Could the authors evaluate this setting?