mlsanityData to 14 Oct 2026

Valdi: Value Diffusion World Models

arXiv 2607.00917 ↗First posted 1 Jul 2026cs.LG cs.AIcited by 0

On the map: World models → Latent predictive world models

also in 1 more
Abstract (arXiv)

World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive enough to represent uncertain futures. Diffusion models offer a natural mechanism for modeling uncertain dynamics, yet their iterative inference procedure makes them difficult to use for low-latency latent planning. We bridge this gap with Value Diffusion World Models (Valdi), combining end-to-end online training for MPC with a latent diffusion dynamics model. In preliminary experiments on the CarRacing environment, we show that Valdi, using a single diffusion step at both training and inference, matches a deterministic MLP baseline. Our experiments expose a trade-off between predictive multimodality and control performance in this setup. Code is available at https://github.com/Kit115/ValueDiffusionWorldModels.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Latent predictive world models, one of 11 directions in World models. Builds on 21 of its 28 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

21 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels13 Mar
  2. 2022Temporal Difference Learning for Model Predictive Control9 Mar
  3. 2018Learning Latent Dynamics for Planning from Pixels12 Nov

Other references · 18

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2015Continuous control with deep reinforcement learningcited by 3,407
  6. 2022Video Diffusion Modelscited by 2,305
  7. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  8. 2018World Modelscited by 1,513
  9. 2023Mastering Diverse Domains through World Modelscited by 1,253
  10. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  11. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  12. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
6 more
  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  2. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 347
  3. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 300
  4. 2025LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristicscited by 254
  5. 2025Training Agents Inside of Scalable World Modelscited by 136
  6. 2025ReSim: Reliable World Simulation for Autonomous Drivingcited by 44

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL
  2. 2026Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization
  3. 2024Diffusion Model Predictive Control
  4. 2025Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making
  5. 2024Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning
  6. 2026A Control Theory of Predictability in Latent World Models
  7. 2024Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
  8. 2025Diffusion-Based Forecasting for Uncertainty-Aware Model Predictive Control