Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning

About

Temporally contrastive representation learning induces a latent structure capable of reducing long-horizon planning to inference in a low-dimensional linear system. However, existing contrastive planning work learns a single latent geometry which cannot distinguish multiple valid behaviors trading task efficiency against risk exposure for the same start-goal query. We introduce MoMo, a preference-conditioned contrastive planner allowing a scalar user preference to continuously modulate plan conservativeness at inference time, without retraining. MoMo learns a joint conditioning of the representation geometry and latent prediction operator via Feature-Wise Linear Modulation and low-rank neural modulation, respectively. We show that our formulation preserves the probability density ratio encoded in the representation space that is required for inference-driven contrastive planning, further retaining its inference-time efficiency. Across six environments, MoMo smoothly adapts plan safety according to user preferences, yielding improved temporal and preferential consistency over state augmentation baselines.

Yusuf Syed, Viraj Parimi, Brian Williams• 2026

Related benchmarks

TaskDatasetResultRank
Preference-conditioned planningAnt Habitat
ΔC3.82
4
Preference-conditioned planningUR5
Delta C0.92
4
Preference-conditioned planningPoint Habitat
ΔC7.29
4
Preference-conditioned planningDRONE
ΔC3.42
4
Preference-conditioned planningPoint Four Obstacles
ΔC9.37
4
Preference-conditioned planningPoint Contour
Delta C2.36
4
Showing 6 of 6 rows

Other info

Follow for update