arXiv subjects

Renzheng Zhang

Publications and source records attributed to Renzheng Zhang.

7 recordsLinked to original sources

arXiv2026

DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing

From a Bayesian perspective, score-based diffusion solves inverse problems through joint inference, embedding the likelihood with the prior to guide the sampling process. However, this formulation fails to explain its practical behavior: the prior offers limited guidance, while reconstruction is largely driven by the measurement-consistency term, leading to an inference process that is effectively decoupled from the diffusion dynamics. We show that the diffusion prior in these solvers functions primarily as a warm initializer that places estimates near the data manifold, while reconstruction is driven almost entirely by measurement consistency. Based on this observation, we introduce \textbf{DAPS++}, which fully decouples diffusion-based initialization from likelihood-driven refinement, allowing the likelihood term to guide inference more directly while maintaining numerical stability and providing insight into why unified diffusion trajectories remain effective in practice. By requiring fewer function evaluations (NFEs) and measurement-optimization steps, \textbf{DAPS++} achieves high computational efficiency and robust reconstruction performance across diverse image restoration tasks.

cs.AI↗

arXiv2026

Ultrasensitive Nanoplastics Detection Leveraging Shrinking Surface Plasmonic Bubble

Nanoplastics pose serious environmental and health risks due to their widespread presence in aquatic systems. Detecting trace amounts of nanoplastics is a challenging task, which currently requires sophisticated equipment and tedious sample preparation (e.g., ultrafiltration). In this work, we demonstrate an ultra-sensitive Shrinking Surface Bubble Deposition (SSBD) technique for nanoplastics detection. SSBD leverages plasmonic photothermal effects to generate a surface bubble and the resulting Marangoni flow to concentrate sparsely suspended nanoplastics onto the bubble surface. The collected nanoplastic particles are subsequently deposited on the substrate after the bubble shrinks and vanishes. To quantify the detection limit of SSBD for nanoplastics in water, core-shell gold plasmonic nanoparticles are mixed with the aqueous sample to enable photothermal bubble generation, while also supporting surface-enhanced Raman spectroscopy (SERS) for signal enhancement. Results show that the limits of detection are 10 ng/mL, 10-1 ng/mL and 10-3 ng/mL for polystyrene (PS) particles with diameters of 500 nm, 200 nm and 30 nm, respectively. We further used SSBD to detect plastics particles in real drinking water (e.g., bottled and fountain water) and found polyamides (PA) and polypropylene (PP) micro/nanoplastics, demonstrating the potential of the SSBD-SERS technique as a versatile and sensitive platform for detecting trace-level nanoplastic contamination and assessing human exposure risk.

physics.optics↗

arXiv2026

ADEPT-PolyGraphMT: Automated Molecular Simulation and Multi-Task Multi-Fidelity Machine Learning for Polymer Property Generation and Prediction

The discovery of polymers with targeted properties is challenged by the vast chemical design space and the limited availability of consistent, high-quality data across multiple properties. In this work, an integrated polymer informatics framework is presented that combines the Automated molecular Dynamics Engine for Polymer simulaTions (ADEPT) workflow with multi-task and multi-fidelity machine learning (PolyGraphMT). Polymer repeat units are represented as molecular graphs and processed using a graph neural network to learn structure-property relationships. Starting from SMILES representations for monomers, ADEPT automates the construction of atomistic models and the evaluation of their properties using molecular dynamics simulations and density functional theory calculations. The simulation data are combined with curated experimental data and group contribution theory estimates to construct a unified dataset of approximately 62,000 polymer property values spanning 28 properties. Using this dataset, inter-property correlations are analyzed, and multi-task learning strategies are evaluated for joint property prediction. The results show that multi-task models achieve performance comparable to single-task models in data-rich regimes and exhibit superior accuracy as training data become limited. In addition, fidelity-aware training improves predictive accuracy when combining experimental and computational data sources. The trained models are further applied to large-scale property prediction for polymers in the PolyInfo database and the PI1M virtual polymer library, producing physically consistent property distributions across a broad chemical space. Overall, the proposed framework provides a structured approach for scalable prediction and screening of polymer properties across multiple property types and data fidelity levels.

physics.chem-ph↗

arXiv2026

Active learning-enabled multi-objective design of thermally conductive and mechanically compliant polymers

Polymers are attractive in applications like flexible electronics and thermal interface materials due to their mechanical compliance and processability. However, conventional polymers have low thermal conductivity (TC), limiting their heat dissipation performance. Identifying polymers that simultaneously achieve high intrinsic TC and mechanical flexibility (i.e., low modulus) remains a challenge. Here, we develop an active learning (AL) framework based on multi-objective Bayesian optimization (MOBO) to discover polymers exhibiting both high TC and low bulk modulus. Initially, a high-throughput molecular dynamics (MD) pipeline generated an initial dataset, and independent Deep Kernel Learning (DKL) surrogate models were trained for TC and bulk modulus to predict properties and uncertainties. Using the parallel noisy expected hypervolume improvement (qNEHVI) acquisition function, the framework iteratively screens a larger unlabeled polymer database, systematically recommends new polymer candidates for MD evaluation, and updates the DKL models with newly acquired data. Ultimately, six candidates were identified on the Pareto front, representing optimal trade-offs between TC and modulus. Interpretability analysis further revealed molecular features associated with these trade-offs, and synthesizability assessment supported the practical relevance of the selected candidates. By combining MD simulations with AL-enabled MOBO, our workflow mitigates data scarcity, reduces development time, and provides actionable guidance for designing multifunctional polymers tailored for different applications.

cond-mat.mtrl-sci↗

arXiv2025

Open Polymer Challenge: Post-Competition Report

Machine learning (ML) offers a powerful path toward discovering sustainable polymer materials, but progress has been limited by the lack of large, high-quality, and openly accessible polymer datasets. The Open Polymer Challenge (OPC) addresses this gap by releasing the first community-developed benchmark for polymer informatics, featuring a dataset with 10K polymers and 5 properties: thermal conductivity, radius of gyration, density, fractional free volume, and glass transition temperature. The challenge centers on multi-task polymer property prediction, a core step in virtual screening pipelines for materials discovery. Participants developed models under realistic constraints that include small data, label imbalance, and heterogeneous simulation sources, using techniques such as feature-based augmentation, transfer learning, self-supervised pretraining, and targeted ensemble strategies. The competition also revealed important lessons about data preparation, distribution shifts, and cross-group simulation consistency, informing best practices for future large-scale polymer datasets. The resulting models, analysis, and released data create a new foundation for molecular AI in polymer science and are expected to accelerate the development of sustainable and energy-efficient materials. Along with the competition, we release the test dataset at https://www.kaggle.com/datasets/alexliu99/neurips-open-polymer-prediction-2025-test-data. We also release the data generation pipeline at https://github.com/sobinalosious/ADEPT, which simulates more than 25 properties, including thermal conductivity, radius of gyration, and density.

cs.LG↗

arXiv2025

Self-Driving Laboratory Optimizes the Lower Critical Solution Temperature of Thermoresponsive Polymers

To overcome the inherent inefficiencies of traditional trial-and-error materials discovery, the scientific community is increasingly developing autonomous laboratories that integrate data-driven decision-making into closed-loop experimental workflows. In this work, we realize this concept for thermoresponsive polymers by developing a low-cost, "frugal twin" platform for the optimization of the lower critical solution temperature (LCST) of poly(N-isopropylacrylamide) (PNIPAM). Our system integrates robotic fluid-handling, on-line sensors, and Bayesian optimization (BO) that navigates the multi-component salt solution spaces to achieve user-specified LCST targets. The platform demonstrates convergence to target properties within a minimal number of experiments. It strategically explores the parameter space, learns from informative "off-target" results, and self-corrects to achieve the final targets. By providing an accessible and adaptable blueprint, this work lowers the barrier to entry for autonomous experimentation and accelerates the design and discovery of functional polymers.

cond-mat.soft↗

arXiv2024

Superior Polymeric Gas Separation Membrane Designed by Explainable Graph Machine Learning

Gas separation using polymer membranes promises to dramatically drive down the energy, carbon, and water intensity of traditional thermally driven separation, but developing the membrane materials is challenging. Here, we demonstrate a novel graph machine learning (ML) strategy to guide the experimental discovery of synthesizable polymer membranes with performances simultaneously exceeding the empirical upper bounds in multiple industrially important gas separation tasks. Two predicted candidates are synthesized and experimentally validated to perform beyond the upper bounds for multiple gas pairs (O2/N2, H2/CH4, and H2/N2). Notably, the O2/N2 separation selectivity is 1.6-6.7 times higher than existing polymer membranes. The molecular origin of the high performance is revealed by combining the inherent interpretability of our ML model, experimental characterization, and molecule-level simulation. Our study presents a unique explainable ML-experiment combination to tackle challenging energy material design problems in general, and the discovered polymers are beneficial for industrial gas separation.

cond-mat.mtrl-sci↗