MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909042830475264 |
|---|---|
| author | Syed, Yusuf Parimi, Viraj Williams, Brian |
| author_facet | Syed, Yusuf Parimi, Viraj Williams, Brian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08512 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning Syed, Yusuf Parimi, Viraj Williams, Brian Machine Learning 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. |
| title | MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.08512 |