Search

Time series generation is a crucial research topic in the area of decision-making systems, which can be particularly important in domains like autonomous driving, healthcare, and, notably, robotics. Recent approaches focus on learning in the data space to model time series information. However, the data space often contains limited observations and noisy features. In this paper, we propose TimeLDM, a novel latent diffusion model for high-quality time series generation. TimeLDM is composed of a variational autoencoder that encodes time series into an informative and smoothed latent content and a latent diffusion model operating in the latent space to generate latent information. We evaluate the ability of our method to generate synthetic time series with simulated and real-world datasets and benchmark the performance against existing state-of-the-art methods. Qualitatively and quantitatively, we find that the proposed TimeLDM persistently delivers high-quality generated time series. For example, TimeLDM achieves new state-of-the-art results on the simulated benchmarks and an average improvement of 55% in Discriminative score with all benchmarks. Further studies demonstrate that our method yields more robust outcomes across various lengths of time series data generation. Especially, for the Context-FID score and Discriminative score, TimeLDM realizes significant improvements of 80% and 50%, respectively. The code will be released after publication.

Advances in theoretical calculations boosted the searches for high temperature superconductors, such as sulfur hydrides and rare-earth polyhydrides. However, the required extremely high pressures for stabilizing these superconductors handicapped further implementations. Based upon thorough structural searches, we identified series of unprecedented superconducting technetium-borides at moderate pressures, including TcB (P6$_3$/mmc) with superconducting transition temperature $T_{\text{c}}$ = 20.2 K at ambient pressure and TcB$_2$ (P6/mmm) with $T_{\text{c}}$ = 23.1 K at 20 GPa. Superconductivity in these technetium-borides mainly originates from the coupling between the low frequency vibrations of technetium-atoms and the dominant technetium-4d electrons at the Fermi level. Our works therefore present a fresh group in the family of superconducting borides, whose diversified crystal structures suggest rich possibilities in discovery of other superconducting transition-metal-borides.

DNA supercoils are generated in genome regulation processes such as transcription and replication, and provide mechanical feedback to such processes. Under tension, DNA supercoil can present a coexistence state of plectonemic (P) and stretched (S) phases. Experiments have revealed the dynamic behaviors of plectoneme, e.g. diffusion, nucleation and hopping. To represent these dynamics with computational changes, we demonstrated first the fast dynamics on the DNA to reach torque equilibrium within the P and S phases, and then identified the two-phase boundaries as collective slow variables to describe the essential dynamics. According to the time scale separation demonstrated here, we accordingly developed a two-phase model on the dynamics of DNA supercoiling, which can capture physiologically relevant events across time scales of several orders of magnitudes. In this model, we systematically characterized the slow dynamics between the two phases, and compared the numerical results with that from the DNA polymer physics-based worm-like chain model. The supercoiling dynamics, including the nucleation, diffusion, and hopping of plectoneme, have been well represented and reproduced, using the two-phase dynamic model, at trivial computational costs. Our current developments, therefore, can be implemented to explore multi-scale physical mechanisms of the DNA supercoiling-dependent physiological processes.

The Jarzynski equality (JE), which relates works of non-equilibrium trajectories to the free energy difference of the initial and final states of the non-equilibrium process, provides an efficient way to calculate free energies of systems in simulations and experiments. However, wider applications of the JE are limited by the requirement that the initial distribution of non-equilibrium trajectories must be equilibrium. Here we extend the JE to a matrix form, the Jarzynski matrix equality (JME), which transforms the free energies of metastable conformational regions in the initial system to that of final one. Therefore, we can calculate the free energies from non-equilibrium trajectories which started from an arbitrary initial distribution. We demonstrate the application of the JME in toy models, Lennard-Jones fluids, and polymer chain models, show its good efficiency in calculation of free energy with a satisfactory accuracy. The JME extends applications of the non-equilibrium method in estimate of free energy in complex system where the initial global equilibrium is difficult to reach.

With the traditional equilibrium molecular simulations, it is usually difficult to efficiently visit the whole conformational space in complex systems, which are separated into some metastable conformational regions by high free energy barriers. The applied non-equilibrium process in simulations could enhance the transitions among these conformational regions, and the associated non-equilibrium effects can be removed by employing the Jarzynski equality (JE), then the global equilibrium distribution can be reproduced. However, the original JE requires the initial distribution of the non-equilibrium process is equilibrium, which largely limits the application of the non-equilibrium method in equilibrium sampling. By extending the previous method, the reweighted ensemble dynamics (RED), which re-weights many equilibrium simulation trajectories from arbitrary initial distribution to reproduce the global equilibrium, to non-equilibrium simulations, we present a method, named as re-weighted non-equilibrium ensemble dynamics (RNED), to generalize the JE in the non-equilibrium trajectories started from an arbitrary initial distribution, thus provide an efficient method to reproduce the equilibrium distribution based on multiple independent (short) non-equilibrium trajectories. We have illustrated the validity of the RNED in a one-dimensional toy model and in a Lennard-Jones system to detect the liquid-solid phase coexistence.