mlsanityData to 7 Oct 2026

LASER: Learning Active Sensing for Continuum Field Reconstruction

arXiv 2604.19355 ↗First posted 21 Apr 2026cs.LG cs.AI cs.CEcited by 0

Not on the map. Why?

Abstract (arXiv)

High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. Conventional reconstruction methods typically rely on fixed sensor layouts, which cannot adapt to evolving physical states. We propose LASER, a unified, closed-loop framework that formulates active sensing as a Partially Observable Markov Decision Process (POMDP). At its core, LASER employs a continuum field latent world model that captures the underlying physical dynamics and provides intrinsic reward feedback. This enables a reinforcement learning policy to simulate ''what-if'' sensing scenarios within a latent imagination space. By conditioning sensor movements on predicted latent states, LASER navigates toward potentially high-information regions beyond current observations. Our experiments demonstrate that LASER consistently outperforms static and offline-optimized strategies, achieving high-fidelity reconstruction under sparsity across diverse continuum fields.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

36 of 45 references.

References · 36

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2022Scalable Diffusion Models with Transformerscited by 5,931
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  7. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  8. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  9. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  10. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  11. 2025Group Sequence Policy Optimizationcited by 788
  12. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
24 more
  1. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  2. 2021Machine learning accelerated computational fluid dynamicscited by 461
  3. 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 396
  4. 2023GNOT: A General Neural Operator Transformer for Operator Learningcited by 321
  5. 2017PDE-Net: Learning PDEs from Datacited by 304
  6. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 299
  7. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 205
  8. 2026GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimizationcited by 175
  9. 2022Predicting Physics in Mesh-reduced Space with Temporal Attentioncited by 82
  10. 2023Operator Learning with Neural Fields: Tackling PDEs on General Geometriescited by 80
  11. 2022Continuous PDE Dynamics Forecasting with Implicit Neural Representationscited by 71
  12. 2023Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformerscited by 54
  13. 2022Learning to Accelerate Partial Differential Equations via Latent Global Evolutioncited by 38
  14. 2024AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fieldscited by 38
  15. 2022NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fieldscited by 36
  16. 2022Transform Once: Efficient Operator Learning in Frequency Domaincited by 20
  17. 2024Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networkscited by 18
  18. 2022Latent Neural ODEs with Sparse Bayesian Multiple Shootingcited by 17
  19. 2025PhySense: Sensor Placement Optimization for Accurate Physics Sensingcited by 11
  20. 2024Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Videocited by 8
  21. 2026Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?cited by 8
  22. 2024Space and Time Continuous Physics Simulation From Partial Observationscited by 6
  23. 2024EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutionscited by 4
  24. 2024Learning Spatiotemporal Dynamical Systems from Point Process Observationscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascade
  2. 2026Active World-Model with 4D-informed Retrieval for Exploration and Awareness
  3. 2026PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce Measurements
  4. 2025Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation
  5. 2026StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
  6. 2026DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration
  7. 2026Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
  8. 2026PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics