Research Digest — 2026-03-20¶
Papers¶
1. Bias in Universal MLIPs and its Effects on Fine-Tuning¶
Source: arXiv (cond-mat.mtrl-sci), Mar 10, 2026 · 📅 2026-03-10 · ↗ Open paper
Universal MLIPs carry systematic biases that persist into fine-tuned models. Periodic fine-tuning (single trajectory, retrain at intervals) dramatically outperforms naive multi-trajectory fine-tuning. Compared naive vs periodic fine-tuning strategies on uMLIPs, analyzed bias through PCA and Q-residual analysis as epistemic uncertainty proxy. Systematic demonstration that how you generate fine-tuning data matters as much as how much. Periodic retraining from evolving trajectories captures dynamics that static datasets miss. Q-residuals as uncertainty proxy for large simulations.
Relevance to DENG.Group
Directly relevant to Yanhao Deng's MLIP work. If you're fine-tuning CHGNet/MACE for halide electrolytes, this paper identifies a concrete failure mode — "naive fine-tuning" generates constrained datasets that don't represent real MD dynamics, causing extrapolation failures. Adopt periodic fine-tuning protocol for halide MLIP development (Yanhao). Use Q-residual analysis to detect when fine-tuned models are extrapolating unsafely during long MD runs. Directly applicable to the \(\ce{Li3YCl_{6-x}Br_x}\) or other halide MLIP workflows.
2. PFP v8: Universal MLIP with r2SCAN Functional¶
Source: arXiv (physics.chem-ph / cond-mat.mtrl-sci), Mar 9 (v2 Mar 18), 2026 · 📅 2026-03-09 · ↗ Open paper
Training uMLIPs on r2SCAN instead of PBE reduces systematic functional error. PFP v8 halves melting point prediction error vs PBE-trained models. Trained Matlantis PFP v8 on large r2SCAN dataset across crystals, molecules, and surfaces. Benchmarked zero-shot predictions against experiment and high-level theory. First large-scale demonstration that uMLIPs can systematically outperform PBE-DFT against experiment without domain-specific fine-tuning. ~130 K average melting point error (vs ~260 K for PBE-trained).
Relevance to DENG.Group
Most MLIPs inherit PBE-level errors (~130 K melting point error). PFP v8 trains on r2SCAN meta-GGA — if it works, this is a step-change in accuracy for thermodynamic predictions relevant to electrolyte stability screening. Test PFP v8 for halide electrolyte phase stability predictions (Yan Li / Mengke Li) — r2SCAN should give more accurate formation energies and defect chemistry. Benchmark against VASP r2SCAN for \(\ce{Li3YCl6}\) before committing to MLIP-only workflows.
3. Predicting Crystal Structures and Ionic Conductivities in Li₃YCl₆₋ₓBrₓ Using Fine-Tuned CHGNet¶
Source: arXiv (cond-mat.mtrl-sci), updated Mar 2, 2026 · 📅 2026-03-02 · ↗ Open paper
Fine-tuned CHGNet on disordered halide structures achieves near-DFT accuracy for total energies and Li-ion dynamics at 10⁴× lower cost. Composition-dependent conductivity trends revealed via ML-MD. Systematic enumeration of ordered structural models from experimentally refined disordered \(\ce{Li3YCl6}\) / \(\ce{Li3YBr6}\), iterative fine-tuning of CHGNet with MD + DFT, NVE/NVT MD for ionic conductivity. Concrete workflow for handling site disorder in halide electrolytes with MLIPs. Demonstrated that Br substitution systematically affects phase stability and conductivity in this ternary system.
Relevance to DENG.Group
This is your system — \(\ce{Li3YCl_{6-x}Br_x}\) halide electrolytes. Directly relevant to Yan Li and Mengke Li's work on halide electrolyte transport and degradation. The fine-tuning strategy is directly adoptable. Compare their CHGNet approach with MACE for the same system (Yanhao). Their structural enumeration protocol for disordered halides can feed into Mengke Li's transport studies. Potential collaboration opportunity — check if their ordered models capture the same physics as your DFT calculations.
4. Latent Space Design of Interatomic Potentials¶
Source: arXiv (physics.chem-ph), Mar 5, 2026 · 📅 2026-03-05 · ↗ Open paper
Construct latent space patterns using DFT theorems and analytic constraints, linking electronic and atomic length scales through electron density. Connects ground, excited, and charge-transfer states. Theoretical framework mapping DFT constraints to latent space components, building on ensemble charge-transfer potential formalism. Moves MLIP design from "fit large datasets" to "encode known physics as latent structure." Could address the combinatoric complexity and undiscovered bonding motif problems in current MLIPs.
Relevance to DENG.Group
Proposes a fundamentally different approach to MLIPs — physics-based latent space from DFT constraints rather than purely data-driven. Relevant to Yanhao's work if standard graph-network MLIPs hit accuracy limits for complex electrolyte systems. If the framework becomes implementable, it could improve MLIP accuracy for systems with mixed bonding character (e.g., electrolyte/electrode interfaces where charge transfer matters — Umang's project). Worth monitoring but likely not immediately applicable.
5. Discovery of Polymer Electrolytes with Bayesian Optimization and High-Throughput MD¶
Source: arXiv (cond-mat.mtrl-sci), Feb 19, 2026 · 📅 2026-02-19 · ↗ Open paper
Bayesian optimization-guided high-throughput MD screening of 1.7M hypothetical polymer electrolytes. Branched architectures and ketone functional groups enhance ion-hopping mechanisms. Classical MD simulations (1.7M chemical space), warm-started batch Bayesian optimization, evaluated 767 homopolymers iteratively. Open-source framework provided. The scale (1.7M candidates) and the mechanistic finding that branched + ketone architectures beat PEO. Also provides Li vs Na cation transport comparison in the same framework.
Relevance to DENG.Group
Directly relevant to Naibing Wu's solid polymer electrolyte project. They screened 1.7M polymer candidates and found architectures that outperform PEO/LiTFSI. Naibing should look at the top candidates and test with atomistic MD or MLIP-driven MD for more accurate transport predictions. Their open-source framework could be adapted for composite polymer electrolytes. The Li/Na comparison is relevant if Naibing wants to extend to Na systems.
6. Scaling Autoregressive Models for Lattice Thermodynamics¶
Source: arXiv (cond-mat.stat-mech), Mar 16, 2026 · 📅 2026-03-16 · ↗ Open paper
Any-order autoregressive models with marginalization can directly learn thermodynamic distributions on crystal lattices, avoiding critical slowing down of MCMC. Scales from small to larger supercells. Any-order ARMs + marginalization models (MAMs) with Transformer architectures and lattice-aware positional encodings. Validated on Ising model and CuAu alloys. Enables sampling of thermodynamic distributions on lattices without expensive MCMC. Any-order generation means you can condition on known subset of sites (useful for interfaces).
Relevance to DENG.Group
Lattice site disorder (cation/anion mixing, vacancy ordering) is central to solid electrolyte properties. This offers a new way to sample thermodynamically relevant disordered configurations. Generate thermodynamically realistic disordered configurations for halide electrolytes (e.g., \(\ce{Li3YCl_{6-x}Br_x}\) site disorder) without exhaustive enumeration. Could replace the enumeration approach in Paper 3 above. Also relevant for Cheng Peng's grain boundary work — generating realistic GB structures with proper site disorder.
7. Adaptive Uncertainty-Guided Surrogates for Phase Field Dendritic Solidification¶
Source: arXiv (physics.comp-ph), Feb 17, 2026 · 📅 2026-02-17 · ↗ Open paper
ML surrogates (XGBoost + CNN) with uncertainty-driven adaptive sampling to approximate phase field dendritic solidification with far fewer full simulations. Monte Carlo dropout (CNN) and bagging (XGBoost) for uncertainty estimation. Adaptive sampling within hyperspheres around high-uncertainty regions. Compared against OLHS-PSO. Self-supervised strategy for temporal instance selection in spatio-temporal surrogate modeling. Quantifies CO₂ emissions of compute alongside accuracy — a useful framing.
Relevance to DENG.Group
Relevant to Shoutong Jin's phase field dendrite growth work. If his simulations are computationally expensive (multi-physics coupling), surrogate models could accelerate parametric studies. Shoutong could train surrogates for his multi-physics (mechanical-thermal-electrochemical) dendrite model to rapidly explore parameter spaces (applied pressure, temperature, SEI properties). The adaptive sampling idea is generalizable to any expensive PDE solver.
8. 2026 Roadmap on Next-Generation Solid Electrolytes¶
Source: ChemRxiv · 📅 2026-03 · ↗ Open paper
Comprehensive roadmap covering sulfide, oxide, polymer, halide electrolytes with emphasis on ML, scalable processing, and high-throughput synthesis as key enablers for the next decade. Expert review / community consensus Identifies ML-driven discovery, multiscale modeling, and interface engineering as the three pillars for solid electrolyte advancement. Highlights gaps in scalable processing and interfacial stability.
Relevance to DENG.Group
Major community roadmap — useful for identifying where the field is heading and positioning your group's contributions. Use as a reference for grant proposals and review papers. The identified gaps (scalable processing, air stability, interface engineering) can guide project direction. Position your group's halide MLIP + interface work within this roadmap.