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

Michael Xu

Michael Xu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
cond-mat.mtrl-sciArtificial IntelligenceComputer VisionMachine Learningphysics.ins-detRobotics

Trust snapshot

Quick read

Trust 19 - UnverifiedVerification L1Unclaimed author
5works
0followers
6topics
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

5 published item(s)

preprint2026arXiv

MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents

We present MineNPC-Task, a user-authored benchmark and evaluation harness for testing memory-aware, mixed-initiative LLM agents in open-world Minecraft. Rather than relying on synthetic prompts, tasks are elicited through formative and summative co-play with expert players, then normalized into parametric templates with explicit preconditions and dependency structure. These tasks are paired with machine-checkable validators under a bounded-knowledge policy that forbids out-of-world shortcuts. The harness captures plan, action, and memory events, including plan previews, targeted clarifications, memory reads and writes, precondition checks, and repair attempts, and reports outcomes relative to the total number of attempted subtasks using only in-world evidence. As an initial snapshot, we instantiate the framework with GPT-4o and evaluate 216 subtasks across 8 experienced players. We observe recurring breakdown patterns in code execution, inventory and tool handling, referencing, and navigation, alongside successful recoveries supported by mixed-initiative clarifications and lightweight memory use. Participants rated interaction quality and interface usability positively, while noting the need for stronger memory persistence across tasks. We release the complete task suite, validators, logs, and evaluation harness to support transparent and reproducible evaluation of future memory-aware embodied agents.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Sonar-GPS Fusion for Seabed Mapping in Turbid Shallow Waters with an Autonomous Surface Vehicle

Accurate seabed mapping is essential for habitat monitoring and infrastructure inspection. In turbid, shallow coastal waters, such as shellfish aquaculture farms, the effectiveness of traditional optical methods is limited. Autonomous surface vehicles (ASVs) equipped with forward-looking sonar (FLS) offer a promising alternative. However, existing sonar-based systems face challenges in achieving fine resolution mapping over long trajectories due to low-resolution positioning measurements and accumulated drift over long trajectories. In this paper, we present a drift-resilient seabed mapping framework that integrates local FLS frame alignment using the Fourier-Mellin transform (FMT) with global trajectory optimization based on an extended Kalman filter (EKF) that fuses global positioning system (GPS), inertial measurement unit (IMU), and compass data. A variance-based image blending strategy is used to further reduce visual artifacts in overlapping regions. Field trials on a structured oyster farm site show that our framework helps reduce drift in RMSE by 9.5% relative to the FMT-only baseline. This framework also enables sub-meter reconstruction accuracy and preservation of high-resolution textures needed for oyster inventory estimation within the mapped areas.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A new semiconducting perovskite alloy system made possible by gas-source molecular beam epitaxy

Optoelectronic technologies are based on families of semiconductor alloys. It is rare that a new semiconductor alloy family is developed to the point where epitaxial growth is possible; since the 1950s, this has happened approximately once per decade. Here we demonstrate epitaxial thin film growth of semiconducting chalcogenide perovskite alloys in the Ba-Zr-S-Se system by gas-source molecular beam epitaxy (MBE). We stabilize the full range y = 0 ... 3 of compositions BaZrS$_{(3-y)}$Se$_y$ in the perovskite structure, up to and including BaZrSe$_3$, by growing on BaZrS$_3$ epitaxial templates. The resulting films are environmentally stable and the direct band gap ($E_g$) varies strongly with Se content, as predicted by theory, covering the range $E_g$ = 1.9 ... 1.4 eV for $y$ = 0 ... 3. This creates possibilities for visible and near-infrared (VIS-NIR) optoelectronics, solid state lighting, and solar cells using chalcogenide perovskites.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Correlating Local Chemical and Structural Order Using Geographic Information Systems-Based Spatial Statistics

Analysis of nanoscale short-range chemical and/or structural order via (scanning) transmission electron microscopy (S/TEM) imaging is fundamentally limited by projection of the three dimensional sample, which averages informational along the beam direction. Extracting statistically significant spatial correlations between the structure and chemistry determined from these two-dimensional datasets thus remains challenging. Here, we apply methods commonly used in Geographic Information Systems (GIS) to determine the spatial correlation between measures of local chemistry and structure from atomic-resolution STEM imaging of a compositionally complex relaxor, Pb(Mg$_{1/3}$Nb$_{2/3}$)O$_{3}$ (PMN). The approach is used to determine the type of ordering present and to quantify the spatial variation of chemical order, oxygen octahedral distortions, and oxygen octahedral tilts. The extent of autocorrelation and inter-feature correlation among these short-range ordered regions are then evaluated through a spatial covariance analysis, showing correlation as a function of distance. The results demonstrate that integrating GIS tools for analyzing microscopy datasets can serve to unravel subtle relationships among chemical and structural features in complex materials that can be hidden when ignoring their spatial distributions.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Augmented Microscopy with Reinforcement Learning-Enhanced Workflows

Here, we report a case study implementation of reinforcement learning (RL) to automate operations in the scanning transmission electron microscopy (STEM) workflow. To do so, we design a virtual, prototypical RL environment to test and develop a network to autonomously align the electron beam without prior knowledge. Using this simulator, we evaluate the impact of environment design and algorithm hyperparameters on alignment accuracy and learning convergence, showing robust convergence across a wide hyperparameter space. Additionally, we deploy a successful model on the microscope to validate the approach and demonstrate the value of designing appropriate virtual environments. Consistent with simulated results, the on-microscope RL model achieves convergence to the goal alignment after minimal training. Overall, the results highlight that by taking advantage of RL, microscope operations can be automated without the need for extensive algorithm design, taking another step towards augmenting electron microscopy with machine learning methods.

0 citations0 reviewsNo code linkedOpen access