Skip to content

March 21, 2026

Papers

1. EquiEwald: Long-Range MLIPs

Full title: An SO(3)-Equivariant Reciprocal-Space Neural Potential for Long-Range Interactions

  • Authors: Linfeng Zhang¹ (CUHK / Tencent AI Lab), …, Pheng-Ann Heng¹ (CUHK / Tencent AI Lab) [et al.]
  • Link: arXiv:2603.18389
  • Source: arXiv (physics.chem-ph), Mar 19, 2026
  • Why it matters: Directly relevant to Yanhao Deng's MLIP work. Long-range electrostatics are critical for solid electrolytes where Li⁺ migration depends on the electrostatic potential landscape. Current MLIPs (MACE, NequIP) use local environments only — this paper introduces a principled reciprocal-space extension that captures anisotropic multipolar correlations while preserving SO(3) equivariance and energy-force consistency.
  • Key idea: EquiEwald performs equivariant message passing in reciprocal space using learned k-space filters, embedding an Ewald-inspired formulation inside an SO(3)-equivariant neural network. This captures long-range electrostatics without sacrificing the physical consistency that makes modern equivariant MLIPs powerful.
  • Method: SO(3)-equivariant architecture with reciprocal-space message passing, equivariant k-space filters, and equivariant inverse Fourier transform. Benchmarked on periodic and aperiodic systems against ab initio reference data.
  • What is actually new: First MLIP architecture to combine true reciprocal-space long-range treatment with SO(3) equivariance in a unified framework. Previous long-range extensions either broke equivariance or sacrificed energy-force consistency.
  • Potential reuse: Test EquiEwald for halide electrolyte MLIPs (Yanhao) — if it captures long-range electrostatic effects better than local-only MACE, it could improve ionic conductivity predictions, especially for charged defects and interfaces. Also relevant for Umang's electrolyte/electrode interface work.

Scores: Relevance 4 | Novelty 5 | Usefulness 4 | Total: 13

2. Electrostatic MLIP Design Space

Full title: Design Space of Self-Consistent Electrostatic Machine Learning Interatomic Potentials

  • Authors: William J. Baldwin¹ (Cambridge), …, Gábor Csányi¹ (Cambridge) [et al.]
  • Link: arXiv:2603.14700
  • Source: arXiv (physics.chem-ph), Mar 16, 2026
  • Why it matters: From Gábor Csányi's group (creators of MACE). Directly relevant to Yanhao's work — provides a systematic framework for incorporating electrostatics into MLIPs using the MACE architecture. Addresses the same challenge as EquiEwald but from the charge-density coarse-graining perspective.
  • Key idea: Existing electrostatic MLIPs are coarse-grained approximations to DFT. By making this explicit, the paper identifies the full design space of self-consistent electrostatic MLIPs, reveals equivalences between previously proposed models, and identifies fundamental limitations.
  • Method: Theoretical framework viewing electrostatic MLIPs as DFT coarse-graining. Shared charge density representation within MACE architecture. Benchmarked on metal-water interfaces and charged vacancies in SiO₂.
  • What is actually new: A unifying theoretical framework that maps all existing electrostatic MLIP approaches onto a common design space. Shows that current approaches fail on metal-water interfaces and charged vacancies — systems where self-consistency is essential.
  • Potential reuse: Use the framework to design electrostatic extensions for the halide MLIPs (Yanhao). The charged vacancy benchmark is directly analogous to charged point defects in halide electrolytes (Yan Li / Mengke Li's work). Combined with EquiEwald, there are now two complementary approaches to long-range MLIPs worth benchmarking.

Scores:

Relevance 4 | Novelty 4 | Usefulness 4 | Total: 12

3. Hydroxide Ion Transport via MLIP

Full title: Revealing Hydroxide Ion Transport Mechanisms in Anion-Exchange Membranes from MLIP Simulations

  • Authors: Jonas Hänseroth¹ (TU Dresden), …, Christian Dreßler¹ (TU Dresden) [et al.]
  • Link: arXiv:2603.13705
  • Source: arXiv (cond-mat.mtrl-sci), Mar 14, 2026
  • Why it matters: Methodologically relevant to Naibing Wu's polymer electrolyte work. Demonstrates the fine-tuned MLIP workflow for ion transport in a complex heterogeneous membrane — a system analogous to polymer electrolytes.
  • Key idea: Fine-tuned MLIPs enable large-scale MD simulations (>10 ns, >10 nm) of hydroxide ion transport in a commercial anion-exchange membrane. Water content controls the percolation transition from isolated clusters to connected hydrogen-bond networks.
  • Method: Fine-tuned MLIP for membrane systems. Large-scale MD at varying water content. Computed diffusion coefficients and activation energies, validated against experiment.
  • What is actually new: First MLIP-based study of ion transport in commercial anion-exchange membranes at realistic length and time scales.
  • Potential reuse: The fine-tuning workflow for membrane systems is directly transferable to Naibing's polymer electrolyte work. The percolation analysis parallels what's needed for understanding Li⁺ transport in PEO-based and composite polymer electrolytes.

Scores: Relevance 3 | Novelty 4 | Usefulness 3 | Total: 10

4. GPUMDkit: NEP Workflow Toolkit

Full title: GPUMDkit: A User-Friendly Toolkit for GPUMD and NEP

  • Authors: Zihan Yan¹, …, Zheyong Fan² (Xiamen University), …, Yizhou Zhu¹ (Xiamen University) [et al.]
  • Link: arXiv:2603.17367
  • Source: arXiv (cond-mat.mtrl-sci), Mar 18, 2026
  • Why it matters: Practical tool for the group. GPUMD/NEP is one of the fastest MLIP MD engines available. GPUMDkit streamlines the entire workflow from training data preparation to trajectory analysis.
  • Key idea: Comprehensive toolkit that automates format conversion, structure sampling, active learning, property calculation, and data visualization for GPUMD and NEP.
  • Method: Modular Python toolkit wrapping GPUMD and NEP workflows.
  • What is actually new: Lowers the barrier to using GPUMD/NEP for MLIP development and MD simulation. Active learning integration could save significant setup time.
  • Potential reuse: Tim (research engineer) could evaluate GPUMDkit as an alternative/complement to LAMMPS for MLIP-driven MD. Benchmarking NEP vs MACE for halide electrolyte ionic conductivity predictions would be informative.

Scores: Relevance 3 | Novelty 2 | Usefulness 4 | Total: 9

Synthesis

Emerging patterns:

  1. Long-range electrostatics in MLIPs is having a moment. Two major papers this week (EquiEwald and self-consistent electrostatic MLIPs) address the same fundamental limitation from complementary angles — reciprocal-space message passing vs charge-density coarse-graining.

  2. Fine-tuned MLIPs for ion transport in complex media is becoming routine. The anion-exchange membrane paper follows the same playbook as yesterday's polymer electrolyte Bayesian screening: train/fine-tune MLIP → run large-scale MD → extract transport mechanisms.

Gaps and limitations:

  • Both electrostatic MLIP papers lack battery-relevant benchmarks. Neither tests on ionic conductors, charged defects in halides, or electrochemical interfaces.
  • GPUMD/NEP ecosystem remains separate from MACE/NequIP. Cross-architecture benchmarking on the same system is badly needed.

Research Ideas

Idea 1: Benchmark Long-Range MLIPs for Halide Defects

  • Based on: EquiEwald, Electrostatic MLIPs
  • Core hypothesis: Both EquiEwald and self-consistent electrostatic MACE will significantly outperform standard local-only MACE for predicting charged defect formation energies and migration barriers in Li₃YCl₆, but will differ in which defect types they handle best.
  • Why non-obvious: Current benchmarks focus on bulk energies. Defect properties involve subtle long-range electrostatic rearrangements that local models fundamentally cannot capture — but nobody has quantified this for halide electrolytes.
  • Minimal validation plan: (1) Compute Li vacancy, Y vacancy, and antisite defect formation energies in Li₃YCl₆ with standard MACE, self-consistent electrostatic MACE, and EquiEwald. (2) Compare against DFT reference. (3) If differences exceed 50 meV/defect, adopt one of these approaches.

Idea 2: Percolation-Driven Ion Transport in Composite Polymer Electrolytes

  • Based on: Anion-exchange membrane MLIP study
  • Core hypothesis: In composite polymer electrolytes (Naibing's project), Li⁺ transport undergoes a percolation transition controlled by the connectivity of ion-conducting pathways through the polymer-filler interface.
  • Why non-obvious: Most composite polymer electrolyte studies focus on the filler as a static structural modifier. The membrane study shows that transport is governed by dynamic network connectivity.
  • Minimal validation plan: (1) Use a fine-tuned MLIP to run MD of PEO-LiTFSI with varying LLZO nanoparticle loadings. (2) Analyze Li⁺ trajectory networks and compute percolation probability vs filler content. (3) Check for a sharp conductivity transition at critical loading.

Idea 3: NEP vs MACE Benchmark on Li₃YCl₆ Ionic Conductivity

  • Based on: GPUMDkit
  • Core hypothesis: NEP will match or exceed MACE accuracy for Li₃YCl₆ ionic conductivity predictions at 10× lower computational cost for MD, but will be less accurate for off-equilibrium properties like defect formation energies.
  • Why non-obvious: The faster model might perform better for transport properties due to enabling longer simulation times and better statistics.
  • Minimal validation plan: (1) Train NEP and MACE on identical DFT datasets for Li₃YCl₆. (2) Run NVT-MD at 400–700 K. (3) Compare ionic conductivities, activation energies, and Li⁺ diffusion coefficients. (4) Measure wall-clock time per MD step.