BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Lai Wei

Lai Wei contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine Learningeess.SYSystems and Controlcond-mat.mtrl-scimath.OCArtificial Intelligenceeess.SPInformation Theorymath.ITRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
13works
0followers
10topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

13 published item(s)

preprint2026arXiv

InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees

We study how large language models can be used to evolve inventory policies in online, non-stationary environments. Our work is motivated by recent advances in LLM-based evolutionary search, such as AlphaEvolve, which demonstrates strong performance for static and highly structured problems such as mathematical discovery, but is not directly suited to online dynamic inventory settings. To this end, we propose InvEvolve, an end-to-end inventory policy evolution and inference framework grounded in confidence-interval-based certification. Built on a large language model trained via reinforcement learning, InvEvolve can process demand data together with additional numerical and textual features, and generates white-box inventory policies with statistical safety guarantees for deployment in future periods. We further introduce a unified theoretical model that connects training, inference, and deployment. This allows us to drive a lower bound on the probability that InvEvolve evolves a statistically safe and improved policy, and to characterize the multi-period performance gap relative to the oracle-safe benchmark. Tested on both synthetic data and real-world retail data, InvEvolve outperforms classical inventory policies and deep learning based methods. In canonical inventory settings, it evolves new policies that improve upon existing benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

In context learning Foundation models for Materials Property Prediction with Small datasets

Foundation models (FMs) have recently shown remarkable in-context learning (ICL) capabilities across diverse scientific domains. In this work, we introduce a unified in-context learning foundation model (ICL-FM) framework for materials property prediction that integrates both composition-based and structure-aware representations. The proposed approach couples the pretrained TabPFN transformer with graph neural network (GNN)-derived embeddings and our novel MagpieEX descriptors. MagpieEX augments traditional features with cation-anion interaction data to explicitly measure bond ionicity and charge-transfer asymmetry, capturing interatomic bonding characteristics that influence vibrational and thermal transport properties. Comprehensive experiments on the MatBench benchmark suite and a standalone lattice thermal conductivity (LTC) dataset demonstrate that ICL-FM achieves competitive or superior performance to state-of-the-art (SOTA) models with significantly reduced training costs. Remarkably, the training-free ICL-FM outperformed sophisticated SOTA GNN models in five out of six representative composition-based tasks, including a significant 9.93\% improvement in phonon frequency prediction. On the LTC dataset, the FM effectively models complex phenomena such as phonon-phonon scattering and atomic mass contrast. t-SNE analysis reveals that the FM acts as a physics-aware feature refiner, transforming raw, disjoint feature clusters into continuous manifolds with gradual property transitions. This restructured latent space enhances interpolative prediction accuracy while aligning learned representations with underlying physical laws. This study establishes ICL-FM as a generalizable, data-efficient paradigm for materials informatics.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Contraction-constrained Model Predictive Control for Multi-timescale Nonlinear Processes

Many chemical processes exhibit diverse timescale dynamics with a strong coupling between timescale sensitive variables. Model predictive control with a non-uniformly spaced optimisation horizon is an effective approach to multi-timescale control and offers opportunities for reduced computational complexity. In such an approach the fast, moderate and slow dynamics can be included in the optimisation problem by implementing smaller time intervals earlier in the prediction horizon and increasingly larger intervals towards the end of the prediction. In this paper, a reference-flexible condition is developed based on the contraction theory to provide a stability guarantee for a nonlinear system under non-uniform prediction horizons.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Contraction-constrained Model Predictive Control for Nonlinear Processes using Disturbance Forecasts

Model predictive control (MPC) has become the most widely used advanced control method in process industry. In many cases, forecasts of the disturbances are available, e.g., predicted renewable power generation based on weather forecast. While the predictions of disturbances may not be accurate, utilizing the information can significantly improve the control performance in response to the disturbances. By exploiting process and disturbance models, future system behaviour can be predicted and used to optimise control actions via minimisation of an economical cost function which incorporates these predictions. However, stability guarantee of the resulting closed-loop system is often difficult in this approach when the processes are nonlinear. Proposed in the following article is a contraction-constrained predictive controller which optimises process economy whilst ensuring stabilisation to operating targets subject to disturbance measurements and forecasts.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Adaptive Contraction-based Control of Uncertain Nonlinear Processes using Neural Networks

Driven by the flexible manufacturing trend in the process control industry and the uncertain nature of chemical process models, this article aims to achieve offset-free tracking for a family of uncertain nonlinear systems (e.g., using process models with parametric uncertainties) with adaptable performance. The proposed adaptive control approach incorporates into the control loop an adaptive neural network embedded contraction-based controller (to ensure convergence to time-varying references) and an online parameter identification module coupled with reference generation (to ensure modelled parameters converge those of the physical system). The integrated learning and control approach involves training a state and parameter dependent neural network to learn a contraction metric parameterized by the uncertain parameter and a differential feedback gain. This neural network is then embedded in an adaptive contraction-based control law which is updated by parameter estimates online. As uncertain parameter estimates converge to the corresponding physical values, offset-free tracking, simultaneously with improved convergence rates, can be achieved, resulting in a flexible, efficient and less conservative approach to the reference tracking control of uncertain nonlinear processes. An illustrative example is included to demonstrate the overall approach. An illustrative example is included to demonstrate the overall approach.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Contraction Analysis and Control Synthesis for Discrete-time Nonlinear Processes

Shifting away from the traditional mass production approach, the process industry is moving towards more agile, cost-effective and dynamic process operation (next-generation smart plants). This warrants the development of control systems for nonlinear chemical processes to be capable of tracking time-varying setpoints to produce products with different specifications as per market demand and deal with variations in the raw materials and utility (e.g., energy). This article presents a systematic approach to the implementation of contraction-based control for discrete-time nonlinear processes. Through the differential dynamic system framework, the contraction conditions to ensure the exponential convergence to feasible time-varying references are derived. The discrete-time differential dissipativity condition is further developed, which can be used for control designs for disturbance rejection. Computationally tractable equivalent conditions are then derived and additionally transformed into an SOS programming problem, such that a discrete-time control contraction metric and stabilising feedback controller can be jointly obtained. Synthesis and implementation details are provided and demonstrated through a numerical case study.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materials

Self-supervised neural language models have recently achieved unprecedented success, from natural language processing to learning the languages of biological sequences and organic molecules. These models have demonstrated superior performance in the generation, structure classification, and functional predictions for proteins and molecules with learned representations. However, most of the masking-based pre-trained language models are not designed for generative design, and their black-box nature makes it difficult to interpret their design logic. Here we propose BLMM Crystal Transformer, a neural network based probabilistic generative model for generative and tinkering design of inorganic materials. Our model is built on the blank filling language model for text generation and has demonstrated unique advantages in learning the "materials grammars" together with high-quality generation, interpretability, and data efficiency. It can generate chemically valid materials compositions with as high as 89.7\% charge neutrality and 84.8\% balanced electronegativity, which are more than 4 and 8 times higher compared to a pseudo random sampling baseline. The probabilistic generation process of BLMM allows it to recommend tinkering operations based on learned materials chemistry and makes it useful for materials doping. Combined with the TCSP crysal structure prediction algorithm, We have applied our model to discover a set of new materials as validated using DFT calculations. Our work thus brings the unsupervised transformer language models based generative artificial intelligence to inorganic materials. A user-friendly web app has been developed for computational materials doping and can be accessed freely at \url{www.materialsatlas.org/blmtinker}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DeepXRD, a Deep Learning Model for Predicting of XRD spectrum from Materials Composition

One of the long-standing problems in materials science is how to predict a material's structure and then its properties given only its composition. Experimental characterization of crystal structures has been widely used for structure determination, which is however too expensive for high-throughput screening. At the same time, directly predicting crystal structures from compositions remains a challenging unsolved problem. Herein we propose a deep learning algorithm for predicting the XRD spectrum given only the composition of a material, which can then be used to infer key structural features for downstream structural analysis such as crystal system or space group classification or crystal lattice parameter determination or materials property predictions. Benchmark studies on two datasets show that our DeepXRD algorithm can achieve good performance for XRD prediction as evaluated over our test sets. It can thus be used in high-throughput screening in the huge materials composition space for new materials discovery.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning idempotent representation for subspace clustering

The critical point for the successes of spectral-type subspace clustering algorithms is to seek reconstruction coefficient matrices which can faithfully reveal the subspace structures of data sets. An ideal reconstruction coefficient matrix should have two properties: 1) it is block diagonal with each block indicating a subspace; 2) each block is fully connected. Though there are various spectral-type subspace clustering algorithms have been proposed, some defects still exist in the reconstruction coefficient matrices constructed by these algorithms. We find that a normalized membership matrix naturally satisfies the above two conditions. Therefore, in this paper, we devise an idempotent representation (IDR) algorithm to pursue reconstruction coefficient matrices approximating normalized membership matrices. IDR designs a new idempotent constraint for reconstruction coefficient matrices. And by combining the doubly stochastic constraints, the coefficient matrices which are closed to normalized membership matrices could be directly achieved. We present the optimization algorithm for solving IDR problem and analyze its computation burden as well as convergence. The comparisons between IDR and related algorithms show the superiority of IDR. Plentiful experiments conducted on both synthetic and real world datasets prove that IDR is an effective and efficient subspace clustering algorithm.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Materials Transformers Language Models for Generative Materials Design: a benchmark study

Pre-trained transformer language models on large unlabeled corpus have produced state-of-the-art results in natural language processing, organic molecule design, and protein sequence generation. However, no such models have been applied to learn the composition patterns of inorganic materials. Here we train a series of seven modern transformer language models (GPT, GPT-2, GPT-Neo, GPT-J, BLMM, BART, and RoBERTa) using the expanded formulas from material deposited in the ICSD, OQMD, and Materials Projects databases. Six different datasets with/out non-charge-neutral or balanced electronegativity samples are used to benchmark the performances and uncover the generation biases of modern transformer models for the generative design of materials compositions. Our extensive experiments showed that the causal language models based materials transformers can generate chemically valid materials compositions with as high as 97.54\% to be charge neutral and 91.40\% to be electronegativity balanced, which has more than 6 times higher enrichment compared to a baseline pseudo-random sampling algorithm. These models also demonstrate high novelty and their potential in new materials discovery has been proved by their capability to recover the leave-out materials. We also find that the properties of the generated samples can be tailored by training the models with selected training sets such as high-bandgap materials. Our experiments also showed that different models each have their own preference in terms of the properties of the generated samples and their running time complexity varies a lot. We have applied our materials transformer models to discover a set of new materials as validated using DFT calculations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Secrecy Performance Analysis of RIS-aided Communication System with Randomly Flying Eavesdroppers

In this letter, we analyze the secrecy performance of a reconfigurable intelligent surface (RIS)-aided communication system with spatially random unmanned aerial vehicles (UAVs) acting as eavesdroppers. We consider the scenarios where the base station (BS) is equipped with single and multiple antennas.The signal-to-noise ratios (SNRs) of the legitimate user and the eavesdroppers are derived analytically and approximated through a computationally effective method. The ergodic secrecy capacity is approximated and derived in closed-form expressions.Simulation results validate the accuracy of the analytical and approximate expressions and show the security-enhanced effect of the deployment of the RIS.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Nonstationary Stochastic Multiarmed Bandits: UCB Policies and Minimax Regret

We study the nonstationary stochastic Multi-Armed Bandit (MAB) problem in which the distribution of rewards associated with each arm are assumed to be time-varying and the total variation in the expected rewards is subject to a variation budget. The regret of a policy is defined by the difference in the expected cumulative rewards obtained using the policy and using an oracle that selects the arm with the maximum mean reward at each time. We characterize the performance of the proposed policies in terms of the worst-case regret, which is the supremum of the regret over the set of reward distribution sequences satisfying the variation budget. We extend Upper-Confidence Bound (UCB)-based policies with three different approaches, namely, periodic resetting, sliding observation window and discount factor and show that they are order-optimal with respect to the minimax regret, i.e., the minimum worst-case regret achieved by any policy. We also relax the sub-Gaussian assumption on reward distributions and develop robust versions the proposed polices that can handle heavy-tailed reward distributions and maintain their performance guarantees.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Expedited Multi-Target Search with Guaranteed Performance via Multi-fidelity Gaussian Processes

We consider a scenario in which an autonomous vehicle equipped with a downward facing camera operates in a 3D environment and is tasked with searching for an unknown number of stationary targets on the 2D floor of the environment. The key challenge is to minimize the search time while ensuring a high detection accuracy. We model the sensing field using a multi-fidelity Gaussian process that systematically describes the sensing information available at different altitudes from the floor. Based on the sensing model, we design a novel algorithm called Expedited Multi-Target Search (EMTS) that (i) addresses the coverage-accuracy trade-off: sampling at locations farther from the floor provides wider field of view but less accurate measurements, (ii) computes an occupancy map of the floor within a prescribed accuracy and quickly eliminates unoccupied regions from the search space, and (iii) travels efficiently to collect the required samples for target detection. We rigorously analyze the algorithm and establish formal guarantees on the target detection accuracy and the expected detection time. We illustrate the algorithm using a simulated multi-target search scenario.

0 citations0 reviewsNo code linkedOpen access