Determine whether JEPA alignment improves decisions

Determine whether the JEPA alignment terms improve decision performance, rather than merely reshaping the learned representation, using a full-length control with the alignment weight set to zero and a readout that uses the reshaped representation.

Background

The report states that the independent control isolating the JEPA alignment terms was short and demonstrated a change in representation retrieval, but did not establish an improvement in decisions. It therefore identifies the causal effect of the alignment objectives on judgment quality as unresolved and proposes a longer zero-alignment control with an appropriate readout as the relevant evaluation.

References

The alignment terms are isolated only by a short independent control, which shows a reshaped representation but not yet a decision gain. The head's subspace also captures less of $g$ than before, so a full-length control with $\lambda = 0$ and a readout that uses the reshaped representation come next.

— Bongard: Training Machine Intuition  (2609.39111 - Ding et al., 30 Sep 2026) in Section 7, Limitations

Why the success rate of the frozen V-JEPA 2 falls while its readout improves is unresolved.

— Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning  (2610.01224 - Hara et al., 1 Oct 2026) in Appendix, Section “Frozen-encoder systems: scope of replication and an exception,” paragraph “Interventions on the cost side”

In particular, downstream closed-loop control remains untested, so the present diagnostics do not establish whether stronger or better-aligned action responses would improve decision making.

— Counterfactual Action Evaluation, Observation Bottlenecks, and Representation Geometry in Joint-Embedding Predictive World Models  (2610.02860 - Subramanian, 2 Oct 2026) in Section 6, Discussion and limitations

Finally, we measure transferred structure by probing accuracy alone, so whether better $Q$ decodability yields better physical decisions remains to be shown on a task whose outcome is not a function of $Q$.

— How Much Physics Can Vision Learn from Audio? Probing and Distilling Damping Structure  (2610.22221 - Afolabi et al., 15 Oct 2026) in Section 6, Limitations