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

Xian Zhang

Xian Zhang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer Visioneess.IVcond-mat.mtrl-sciArtificial IntelligenceComputation and Languagecond-mat.mes-hallCryptography and SecurityMachine LearningMultiagent Systemsphysics.app-phphysics.opticsRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
12topics
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

9 published item(s)

preprint2026arXiv

STAR-PólyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision

Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability issues: hallucination accumulation, memory fragmentation, and imbalanced reasoning-tool trade-offs. In this paper, we introduce STAR-PólyaMath, a multi-agent framework that systematically addresses these challenges through meta-level supervision and structured Reasoner-Verifier interaction. STAR-PólyaMath is structured as an orchestrated state machine with nested challenge-step-replan loops, governed by a reasoning-free Python orchestrator that separates control from inference and bounds error propagation through trace-back and re-planning. Our key innovation is a persistent Meta-Strategist that maintains cross-attempt memory and exercises meta-level control by issuing high-level strategic guidance or mandatory directives, so the system can escape unproductive loops rather than stagnate or over-rely on tools. STAR-PólyaMath achieves state-of-the-art results on all eight top-tier competition benchmarks: AIME 2025-2026, MathArena Apex Shortlist, MathArena Apex 2025, Putnam 2025, IMO 2025, HMMT February 2026, and USAMO 2026. It obtains perfect scores on AIMEs, Putnam, and HMMT, and shows its largest margin on Apex 2025, scoring 93.75% compared with 80.21% by the strongest baseline GPT-5.5. Ablation studies show that the gains arise from the framework's orchestration rather than from model-level diversity since removing key components or substituting in mixed backbones consistently weakens performance. Code is available at https://github.com/Julius-Woo/STAR-PolyaMath.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Decentralized Verifiable Mail-in Ballot Counting for Postal Voting

As computer vision is prevalently used for mail-in ballot processing and counting, it becomes a point of centralized trust in postal voting. We propose DVote, a prototype system of postal voting that provides decentralized trust in computer vision. With blockchain and layer-2 technologies, DVote decentralizes the computation and model training of computer vision to a group of scrutineers that hold the AnyTrust assumption, i.e., at least one member is honest. Consequently, the computational integrity is anchored to the trustworthiness of a large public blockchain such as Ethereum.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

EfficientGrasp: A Unified Data-Efficient Learning to Grasp Method for Multi-fingered Robot Hands

Autonomous grasping of novel objects that are previously unseen to a robot is an ongoing challenge in robotic manipulation. In the last decades, many approaches have been presented to address this problem for specific robot hands. The UniGrasp framework, introduced recently, has the ability to generalize to different types of robotic grippers; however, this method does not work on grippers with closed-loop constraints and is data-inefficient when applied to robot hands with multigrasp configurations. In this paper, we present EfficientGrasp, a generalized grasp synthesis and gripper control method that is independent of gripper model specifications. EfficientGrasp utilizes a gripper workspace feature rather than UniGrasp's gripper attribute inputs. This reduces memory use by 81.7% during training and makes it possible to generalize to more types of grippers, such as grippers with closed-loop constraints. The effectiveness of EfficientGrasp is evaluated by conducting object grasping experiments both in simulation and real-world; results show that the proposed method also outperforms UniGrasp when considering only grippers without closed-loop constraints. In these cases, EfficientGrasp shows 9.85% higher accuracy in generating contact points and 3.10% higher grasping success rate in simulation. The real-world experiments are conducted with a gripper with closed-loop constraints, which UniGrasp fails to handle while EfficientGrasp achieves a success rate of 83.3%. The main causes of grasping failures of the proposed method are analyzed, highlighting ways of enhancing grasp performance.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Identification and classification of exfoliated graphene flakes from microscopy images using a hierarchical deep convolutional neural network

Identification of the mechanically exfoliated graphene flakes and classification of the thickness is important in the nanomanufacturing of next-generation materials and devices that overcome the bottleneck of Moore's Law. Currently, identification and classification of exfoliated graphene flakes are conducted by human via inspecting the optical microscope images. The existing state-of-the-art automatic identification by machine learning is not able to accommodate images with different backgrounds while different backgrounds are unavoidable in experiments. This paper presents a deep learning method to automatically identify and classify the thickness of exfoliated graphene flakes on Si/SiO2 substrates from optical microscope images with various settings and background colors. The presented method uses a hierarchical deep convolutional neural network that is capable of learning new images while preserving the knowledge from previous images. The deep learning model was trained and used to classify exfoliated graphene flakes into monolayer (1L), bi-layer (2L), tri-layer (3L), four-to-six-layer (4-6L), seven-to-ten-layer (7-10L), and bulk categories. Compared with existing machine learning methods, the presented method possesses high accuracy and efficiency as well as robustness to the backgrounds and resolutions of images. The results indicated that our deep learning model has accuracy as high as 99% in identifying and classifying exfoliated graphene flakes. This research will shed light on scaled-up manufacturing and characterization of graphene for advanced materials and devices.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Thermal Conductivities and Interfacial Thermal Conductance of 1- to 3-Layer WSe$_2$

Atomically thin materials such as graphene and semiconducting transition metal dichalcogenides have attracted extensive interest in recent years, motivating investigation into multiple properties. In this work, we used the opto thermal Raman technique to measure the thermal transport properties of a popular TMDC material WSe$_2$, in single atomic layer, bilayer, and trilayer forms.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Very High Interfacial Thermal Conductance in Fully hBN-Encapsulated MoS2 van der Waals Heterostructure

We report experimental and computational studies of thermal transport properties in hexagonal boron nitride (hBN) encapsulated molybdenum disulfide (MoS2) structure using refined optothermal Raman techniques, and reveal very high interfacial thermal conductance between hBN and MoS2. By studying the Raman shift of hBN and MoS2 in suspended and substrate-supported thin films under varying laser power and temperature, we calibrate lateral (in-plane) thermal conductivity of hBN and MoS2 and the vertical interfacial thermal conductance in the hBN/MoS2/hBN heterostructure as well as the interfaces between heterostructure and substrate. Crucially, we have found that interfacial thermal conductance between hBN and encapsulated MoS2 is 74MW/m2K and 72MW/m2K in supported and suspended films, respectively, which are significantly higher than interfacial thermal conductance between MoS2 and other substrates. Molecular dynamics (MD) computations conducted in parallel have shown consistent results. This work provides clear evidence of significantly efficient heat dissipation in hBN/MoS2/hBN heterostructures and sheds light on building novel hBN encapsulated nanoelectronics with efficient thermal management.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting

Prior knowledge of face shape and structure plays an important role in face inpainting. However, traditional face inpainting methods mainly focus on the generated image resolution of the missing portion without consideration of the special particularities of the human face explicitly and generally produce discordant facial parts. To solve this problem, we present a domain embedded multi-model generative adversarial model for inpainting of face images with large cropped regions. We firstly represent only face regions using the latent variable as the domain knowledge and combine it with the non-face parts textures to generate high-quality face images with plausible contents. Two adversarial discriminators are finally used to judge whether the generated distribution is close to the real distribution or not. It can not only synthesize novel image structures but also explicitly utilize the embedded face domain knowledge to generate better predictions with consistency on structures and appearance. Experiments on both CelebA and CelebA-HQ face datasets demonstrate that our proposed approach achieved state-of-the-art performance and generates higher quality inpainting results than existing ones.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Training Multiscale-CNN for Large Microscopy Image Classification in One Hour

Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory capacity available on GPUs and emerging accelerators. These techniques often lead to longer time to convergence or time to train (TTT), and in some cases, lower model accuracy. CPUs, on the other hand, can leverage significant amounts of memory. While much work has been done on parallelizing neural network training on multiple CPUs, little attention has been given to tune neural network training with large images on CPUs. In this work, we train a multi-scale convolutional neural network (M-CNN) to classify large biomedical images for high content screening in one hour. The ability to leverage large memory capacity on CPUs enables us to scale to larger batch sizes without having to crop or down-sample the input images. In conjunction with large batch sizes, we find a generalized methodology of linearly scaling of learning rate and train M-CNN to state-of-the-art (SOTA) accuracy of 99% within one hour. We achieve fast time to convergence using 128 two socket Intel Xeon 6148 processor nodes with 192GB DDR4 memory connected with 100Gbps Intel Omnipath architecture.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

A Polarization-insensitive and High-speed Electro-optic Switch Based on a Hybrid Silicon and Lithium Niobate Platform

We propose and demonstrate a polarization-insensitive and high speed optical switch unit based on a silicon and lithium niobate hybrid integration platform. The presented device exhibits a sub nano-second switching time, low drive voltages of 4.97 V, and low power dissipation due to electrostatic operation. The measured polarization dependence loss was lower than 0.8 dB. The demonstrated optical switch could provide as a building block for polarization-insensitive and high-speed optical matrix switches.

0 citations0 reviewsNo code linkedOpen access