Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation

• URL: http://arxiv.org/abs/2606.01833v1
• Date: Mon, 01 Jun 2026 07:46:28 GMT
• Title: Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation
• Abstract summary: Generative emulators of protein dynamics produce plausible trajectories at a fraction of the cost of molecular dynamics.<n>Inspired by classical enhanced sampling, we introduce an implicit, history-dependent bias in the generative space of a pretrained emulator.
• Score: 6.914990300751483
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative emulators of protein dynamics produce plausible trajectories at a fraction of the cost of molecular dynamics, but they inherit their training distribution and tend to revisit known states rather than reach rare ones under long-horizon extrapolation. Inspired by classical enhanced sampling, we introduce an implicit, history-dependent bias in the generative space of a pretrained emulator. Specifically, a history-aware score estimator augments the frozen emulator with a distance-weighted bias that steers reverse-time sampling away from previously generated structures, regularized by an environment-support term. To preserve structural validity at long horizons, a score-based refinement step re-projects drifted samples onto the data manifold using the frozen emulator. Our experiments demonstrate that the method (i) raises diversity by $35\%$ on DynamicPDB-80; (ii) on $12$ zero-shot Fast-Folding proteins, the learned bias alone reaches the unbiased emulator's coverage up to ${\sim}15\times$ faster, and pairing it with refinement reaches the coverage up to ${\sim}37\times$ faster while covering ${\sim}3\times$ as many low-energy states. Code will be released soon.

Related papers

• Fast, accurate, high-resolution simulation of large-scale Fermi-Hubbard models on a digital quantum processor [2.182919491659049]
  We report experimental digital quantum simulation of the one-dimensional Fermi-Hubbard model on a superconducting quantum processor.<n>We encode this problem using up to 120 qubits through an efficient mapping that reduces circuit complexity.<n>We improve accuracy through error suppression to simulate dynamical evolution using up to 90 Trotter steps.
  arXiv  Detail & Related papers  (2026-05-05T17:49:07Z)
• Self-Refining Video Sampling [91.0784344916165]
  We present self-refining video sampling, a simple method that uses a pre-trained video generator trained on large-scale datasets as its own self-refiner.<n> Experiments on state-of-the-art video generators demonstrate significant improvements in motion coherence and physics alignment.
  arXiv  Detail & Related papers  (2026-01-26T15:22:27Z)
• All Emulators are Wrong, Many are Useful, and Some are More Useful Than Others: A Reproducible Comparison of Computer Model Surrogates [0.0]
  We present a large-scale, fully reproducible comparison of $29$ distinct emulators across $60$ canonical test functions and $40$ real emulation datasets.<n>To facilitate rigorous, apples-to-apples comparisons, we introduce the R package textttduqling.<n>This framework allows researchers to compare emulators in a unified environment and makes it possible to replicate or extend previous studies with minimal effort.
  arXiv  Detail & Related papers  (2025-12-09T19:25:50Z)
• Overclocking Electrostatic Generative Models [59.271136356755996]
  PFGM++ operates in an extended data space with auxiliary dimensionality $D$, recovering the diffusion model framework as $Dtoinfty$.<n>We propose Inverse Poisson Flow Matching (IPFM), a novel distillation framework that accelerates electrostatic generative models across all values of $D$.<n>IPFM produces distilled generators that achieve near-teacher or even superior sample quality using only a few function evaluations.
  arXiv  Detail & Related papers  (2025-09-26T15:07:23Z)
• Neural-Network Chemical Emulator for First-Star Formation: Robust Iterative Predictions over a Wide Density Range [0.0]
  We present a neural-network emulator for the thermal and chemical evolution in PopulationIII star formation.<n>We partition the density range into five subregions and train separate deep operator networks (DeepONets) in each region.<n>When applied to randomly sampled thermochemical states, the emulator achieves errors below 10% in over 90% of cases for both temperature and chemical abundances.
  arXiv  Detail & Related papers  (2025-08-22T06:11:03Z)
• Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation [14.39804673747056]
  We investigate whether a similar strategy can be effectively applied to the emulation of dynamical systems.<n>We find that the accuracy of latent-space emulation is surprisingly robust to a wide range of compression rates.<n>We also show that diffusion-based emulators are consistently more accurate than non-generative counterparts.
  arXiv  Detail & Related papers  (2025-07-03T13:32:50Z)
• Pseudo-Simulation for Autonomous Driving [66.1981253104508]
  Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations.<n>Real-world evaluation is often challenging due to safety concerns and a lack of realism.<n>Open-loop evaluation relies on metrics that generally overlook compounding errors.
  arXiv  Detail & Related papers  (2025-06-04T17:57:53Z)
• IAEmu: Learning Galaxy Intrinsic Alignment Correlations [16.805775045014578]
  We introduce IAEmu, a neural network-based emulator that predicts the galaxy position-position ($xi$), position-orientation ($omega$), and orientation-orientation ($eta$) correlation functions.<n>Compared to simulations, IAEmu achieves 3% average error for $xi$ and 5% for $omega$, while capturing $eta$ without overfitting.<n>IAEmu is a powerful surrogate model for galaxy bias and IA studies with direct applications to Stage IV weak lensing surveys.
  arXiv  Detail & Related papers  (2025-04-07T16:19:50Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [57.278726604424556]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers.<n>Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy.<n>We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• SE(3)-Stochastic Flow Matching for Protein Backbone Generation [54.951832422425454]
  We introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3mathrmD$ rigid motions. Our family of FoldFlowgenerative models offers several advantages over previous approaches to the generative modeling of proteins.
  arXiv  Detail & Related papers  (2023-10-03T19:24:24Z)
• Simulation-free Schr\"odinger bridges via score and flow matching [89.4231207928885]
  We present simulation-free score and flow matching ([SF]$2$M) Our method generalizes both the score-matching loss used in the training of diffusion models and the recently proposed flow matching loss used in the training of continuous flows. Notably, [SF]$2$M is the first method to accurately model cell dynamics in high dimensions and can recover known gene regulatory networks simulated data.
  arXiv  Detail & Related papers  (2023-07-07T15:42:35Z)
• AutoSimulate: (Quickly) Learning Synthetic Data Generation [70.82315853981838]
  We propose an efficient alternative for optimal synthetic data generation based on a novel differentiable approximation of the objective. We demonstrate that the proposed method finds the optimal data distribution faster (up to $50times$), with significantly reduced training data generation (up to $30times$) and better accuracy ($+8.7%$) on real-world test datasets than previous methods.
  arXiv  Detail & Related papers  (2020-08-16T11:36:11Z)

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.