MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning

• URL: http://arxiv.org/abs/2605.08512v2
• Date: Thu, 14 May 2026 17:53:54 GMT
• Title: MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning
• Abstract summary: We introduce MoMo, a preference-conditioned contrastive planner.<n>MoMo learns a joint conditioning of the representation geometry and latent prediction operator.<n>Across six environments, MoMo smoothly adapts plan safety according to user preferences, yielding improved temporal and preferential consistency over state augmentation baselines.
• Score: 1.7281573530896264
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Differentiable Object Pose Connectivity Metrics for Regrasp Sequence Optimization [13.078429762098631]
  Regrasp planning is often required when one pick-and-place cannot transfer an object from an initial pose to a goal pose.<n>We propose an implicit multi-step regrasp planning framework based on differentiable pose sequence connectivity metrics.
  arXiv  Detail & Related papers  (2026-04-16T07:47:57Z)
• Temporal Straightening for Latent Planning [58.131390107122456]
  We introduce temporal straightening to improve representation learning for latent planning.<n>We show that reducing curvature makes the Euclidean distance in latent space a better proxy for the geodesic distance.
  arXiv  Detail & Related papers  (2026-03-12T17:49:47Z)
• Flexible Locomotion Learning with Diffusion Model Predictive Control [46.432397190673505]
  We present Diffusion-MPC, which leverages a learned generative diffusion model as an approximate dynamics prior for planning.<n>Our design enables strong test-time adaptability, allowing the planner to adjust to new reward specifications without retraining.<n>We validate Diffusion-MPC on real world, demonstrating strong locomotion and flexible adaptation.
  arXiv  Detail & Related papers  (2025-10-05T14:51:13Z)
• A Unified Theory of Compositionality, Modularity, and Interpretability in Markov Decision Processes [1.3044677039636754]
  We introduce Option Kernel Bellman Equations (OKBEs) for a new reward-free Markov Decision Process.<n>OKBEs directly construct and optimize a predictive map called a state-time option kernel (STOK) to maximize the probability of completing a goal.<n>We argue that reward-maximization is in conflict with the properties of compositionality, modularity, and interpretability.
  arXiv  Detail & Related papers  (2025-06-11T08:21:22Z)
• Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts [79.18608192761512]
  Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable.<n>We propose a Few-Shot Prototypical Concept Classification framework that mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment.<n>Our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.
  arXiv  Detail & Related papers  (2025-06-05T06:39:43Z)
• Latent Diffusion Planning for Imitation Learning [78.56207566743154]
  Latent Diffusion Planning (LDP) is a modular approach consisting of a planner and inverse dynamics model.<n>By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data.<n>On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches.
  arXiv  Detail & Related papers  (2025-04-23T17:53:34Z)
• Adaptive Planning with Generative Models under Uncertainty [20.922248169620783]
  Planning with generative models has emerged as an effective decision-making paradigm across a wide range of domains. While continuous replanning at each timestep might seem intuitive because it allows decisions to be made based on the most recent environmental observations, it results in substantial computational challenges. Our work addresses this challenge by introducing a simple adaptive planning policy that leverages the generative model's ability to predict long-horizon state trajectories.
  arXiv  Detail & Related papers  (2024-08-02T18:07:53Z)
• SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation [11.011219709863875]
  We propose a new end-to-end autonomous driving paradigm named SparseDrive. SparseDrive consists of a symmetric sparse perception module and a parallel motion planner. For motion prediction and planning, we review the great similarity between these two tasks, leading to a parallel design for motion planner.
  arXiv  Detail & Related papers  (2024-05-30T02:13:56Z)
• Planning with Diffusion for Flexible Behavior Synthesis [125.24438991142573]
  We consider what it would look like to fold as much of the trajectory optimization pipeline as possible into the modeling problem. The core of our technical approach lies in a diffusion probabilistic model that plans by iteratively denoising trajectories.
  arXiv  Detail & Related papers  (2022-05-20T07:02:03Z)
• Visual Learning-based Planning for Continuous High-Dimensional POMDPs [81.16442127503517]
  Visual Tree Search (VTS) is a learning and planning procedure that combines generative models learned offline with online model-based POMDP planning. VTS bridges offline model training and online planning by utilizing a set of deep generative observation models to predict and evaluate the likelihood of image observations in a Monte Carlo tree search planner. We show that VTS is robust to different observation noises and, since it utilizes online, model-based planning, can adapt to different reward structures without the need to re-train.
  arXiv  Detail & Related papers  (2021-12-17T11:53:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.