# MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning

arXiv: https://arxiv.org/abs/2605.08512 · HTML: https://mlsanity.com/paper/2605.08512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 61 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 30 of 38)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Successor Features for Transfer in Reinforcement Learning](https://mlsanity.com/paper/1606.05312/) (2016)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation](https://mlsanity.com/paper/1908.08342/) (2019)
- [Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency](https://mlsanity.com/paper/1809.01812/) (2018)
- [Constrained Decision Transformer for Offline Safe Reinforcement Learning](https://mlsanity.com/paper/2302.07351/) (2023)
- [Datasets and Benchmarks for Offline Safe Reinforcement Learning](https://mlsanity.com/paper/2306.09303/) (2023)
- [Robot Motion Planning in Learned Latent Spaces](https://mlsanity.com/paper/1807.10366/) (2018)
- [Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL](https://mlsanity.com/paper/2305.00567/) (2023)
- [Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning](https://mlsanity.com/paper/2106.02866/) (2021)
- [Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data](https://mlsanity.com/paper/2306.03346/) (2023)
- [Conditional Contrastive Learning with Kernel](https://mlsanity.com/paper/2202.05458/) (2022)
- [SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning](https://mlsanity.com/paper/2301.12203/) (2023)
- [Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning](https://mlsanity.com/paper/2402.17217/) (2024)
- [RAIL: Risk-Averse Imitation Learning](https://mlsanity.com/paper/1707.06658/) (2017)
- [Online Risk-Bounded Motion Planning for Autonomous Vehicles in Dynamic Environments](https://mlsanity.com/paper/1904.02341/) (2019)
- [Provably Safe Trajectory Optimization in the Presence of Uncertain Convex Obstacles](https://mlsanity.com/paper/2003.07811/) (2020)
- [Scenario-Based Motion Planning with Bounded Probability of Collision](https://mlsanity.com/paper/2307.01070/) (2023)

## Abstract (arXiv)

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.