Papers & Surveys

ScientificML

AECSF addresses Bayesian state estimation in high-dimensional nonlinear dynamical systems through adaptive ensemble conditional score filtering, targeting particle-weight collapse and preserving non-Gaussian posterior structure.

ScientificML

AutoPDEBench benchmarks automated LLM-based research for designing neural PDE solvers, with attention to domain-specific challenges such as varying parameters and high-speed flows.

Materials

CP-Agent is an agentic harness for crystal plasticity simulation workflows in polycrystalline metals, automating heterogeneous tool configuration, multi-step data pipeline orchestration, and constitutive parameter calibration against experiments.

Multibody/Robotics

This paper studies how external body knowledge, successful experience, and executable skills improve GPT-6-Astra control of an XLeRobot in simulated and physical elevator-button tasks, focusing on robot manipulation and Sim2Real transfer.

Geophysics

TaiJi introduces a spatiotemporal adaptive ensemble framework that fuses data-driven machine-learning weather models with physics-based numerical weather prediction forecasts using state-conditional weighting across variables, pressure levels, lead times, and regions.

ScientificML

This paper develops uncertainty quantification for Next Generation Reservoir Computing in memory-driven nonlinear dynamical systems, focusing on Bayesian ridge regression and conformal prediction intervals for efficient forecasting.

Materials

Uses explicit-ion molecular dynamics and charge-regulation Monte Carlo simulations to compute the interaction force between two spherical, charge-regulated amphoteric nanoparticles, addressing how adjustable surface ionization governs their electrostatic interaction behavior.

Multibody

This robotics paper studies humanoid badminton skills using limited human motion data to support precise racket control, timely shuttle-contact decisions, and dynamic whole-body coordination.

Electromagnetics

This paper develops a physics-driven deterministic framework for indoor pinching-antenna systems that jointly captures in-waveguide field evolution, sequential pinching-antenna power extraction, and site-specific indoor multipath propagation.

Electromagnetics

This paper studies electromagnetic control of resonance and quality factor in a side-coupled microcavity made from a two-dimensional photonic crystal of silicon rods in an aqueous analyte. It uses plane-wave expansion and finite-difference time-domain computation to examine evanescent Bloch tunnelling and finite-cell corrections.

Multibody

This paper investigates Lagrangian and Hamiltonian neural network models for dissipative mechanical systems with explicit time dependence, using damped and undamped one-dimensional harmonic oscillators as simulated systems.

Structural

This paper studies rolling-element bearing fault diagnosis from vibration, a physical-sensing task, under operating-condition shift and a held-out-bearing protocol. It compares neural-operator and convolutional models while assigning each physical bearing entirely to either training or testing.

Structural

This paper applies extreme learning machines to model aerodynamic self-excited forces in long-span bridge-deck cross-sections, supporting the prediction of aerodynamic instabilities and bridge safety. The approach uses forced-oscillation data from CFD or wind-tunnel experiments.

CFD

This paper applies physics-informed neural networks to reconstruct molten pool flow fields from high-speed video for wire-arc directed energy deposition, where extreme temperatures and intense arc illumination make direct flow sensing difficult.

Materials

The paper applies knowledge-driven multi-view retrieval and explanation to identify crystalline phases from X-ray diffraction patterns, addressing reference-pattern scarcity in high-throughput materials discovery.

ScientificML

PhiBE-Flow targets physical systems with stochastic evolution, generating continuous-time trajectories consistent with probability densities inferred from discrete observations by estimating the induced probability velocity field.

ScientificML

SPOpInf is a non-intrusive method that learns stochastic differential equations from data for quadratically nonlinear systems with additive noise, supporting reduced-order modeling of complex stochastic dynamics and turbulent flows.

CFD

This paper presents a quantum Carleman lattice Boltzmann scheme for fluid collision dynamics, using a multi-relaxation-time operator in a weighted Hermite moment basis to support coherent multi-step evolution.

Fluid Dynamics

This paper studies wave breaking and a structure-preserving fully discrete method for the stochastic Camassa–Holm equation, a nonlinear shallow-water wave model with additive random forcing. It analyzes finite-time wave breakdown and derives an initial-slope condition under an additional moment assumption.

CFD

A physics-enhanced neural operator incorporates the film-cooling superposition principle to improve temperature-field prediction for turbine endwalls with varying numbers of film holes.