mlsanityData to 7 Oct 2026

Speculative Sampling For Faster Molecular Dynamics

arXiv 2606.02455 ↗First posted 1 Jun 2026cs.LG cond-mat.mtrl-sci physics.chem-phcited by 1

Not on the map. Why?

Abstract (arXiv)

Molecular dynamics (MD) is a key tool for simulating the dynamical behavior of atomic systems. However, MD is inherently serial, which makes it difficult to increase single-system throughput with concurrent compute. To address this, we introduce Langevin Speculative Dynamics (LSD), a distributed and model-agnostic speculative sampler for accelerating MD without adding relative error. Inspired by speculative methods in language and diffusion modeling, LSD uses a draft model to propose fast simulation steps and verifies them in parallel with a slower target model, applying a transport map from the draft to the target distribution. We extend speculative sampling to second-order Langevin dynamics, derive the achievable speedup as a function of physical parameters, show that LSD generalizes across different systems and draft-target combinations with a 3-9x speedup, and confirm theoretically and empirically that LSD samples trajectories from its target model distribution.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

16 of 32 references.

References · 16

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  2. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  3. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  4. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  5. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  6. 2025UMA: A Family of Universal Models for Atomscited by 99
  7. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 79
  8. 2023Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamicscited by 62
  9. 2018Coupling and Convergence for Hamiltonian Monte Carlocited by 36
  10. 2025Accelerated Diffusion Models via Speculative Samplingcited by 30
  11. 2022Towards Training Billion Parameter Graph Neural Networks for Atomic Simulationscited by 25
  12. 2024The dark side of the forces: assessing non-conservative force models for atomistic machine learningcited by 23
4 more
  1. 2025Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessianscited by 15
  2. 2024AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Accelerationcited by 13
  3. 2025FlashMD: long-stride, universal prediction of molecular dynamicscited by 11
  4. 2023Learning Interatomic Potentials at Multiple Scalescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Accelerating Speculative Diffusions via Block Verificationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion Models are Molecular Dynamics Simulators
  2. 2026Accelerating Diffusion Sampling via Speculative Draft Trees
  3. 2025Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models
  4. 2026Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models
  5. 2026Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback
  6. 2026METALICA: METAdynamics and repLICA exchange for enhanced diffusion sampling
  7. 2023Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics
  8. 2026Composing diffusion priors with explicit physical context via generative Gibbs sampling