Researcher profile

Ziyu Zhou

Ziyu Zhou contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computer Vision Artificial Intelligence cond-mat.mes-hall cond-mat.mtrl-sci cond-mat.quant-gas Machine Learning quant-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

6works

0followers

7topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

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

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

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.

preprint2026arXiv

KEPIL: Knowledge-Enhanced Prompt-Image Learning for Prompt-Robust Disease Detection

Vision--language models (VLMs) show promise for clinical decision support in radiology because they enable joint reasoning over radiological images and clinical text, thereby leveraging complementary clinical information. However, radiological findings are long-tailed in practice, leaving some conditions underrepresented and making zero-shot inference essential. Yet current CLIP-style medical VLMs are sensitive to prompt variations and often lack trustworthy external knowledge at inference time, which hinders reliable clinical deployment. We present \textit{KEPIL}, a prompt-robust framework that integrates curated medical knowledge to stabilize zero-shot generalization. KEPIL comprises: (i) \emph{dynamic prompt enrichment} using ontologies with LLM assistance, (ii) a \emph{semantic-aware contrastive loss} aligning embeddings of equivalent prompt variants via a dual-embedding objective, and (iii) \emph{entity-centric report standardization} to yield ontology-aligned representations. Across seven benchmarks, KEPIL achieves state-of-the-art zero-shot inference performance; under prompt-variation tests, it improves AUC by $6.37\%$ on \textit{CheXpert} and by $4.11\%$ on average. These results suggest that structured knowledge and robust prompt design are key to clinically reliable radiology-facing VLMs. Code will be released at https://github.com/Roypic/KEPIL.

preprint2026arXiv

Lamps: Learning Anatomy from Multiple Perspectives via Self-supervision in Chest Radiographs

Foundation models have been successful in natural language processing and computer vision because they are capable of capturing the underlying structures (foundation) of natural languages. However, in medical imaging, the key foundation lies in human anatomy, as these images directly represent the internal structures of the body, reflecting the consistency, coherence, and hierarchy of human anatomy. Yet, existing self-supervised learning (SSL) methods often overlook these perspectives, limiting their ability to effectively learn anatomical features. To overcome the limitation, we built Lamps (learning anatomy from multiple perspectives via self-supervision) pre-trained on large-scale chest radiographs by harmoniously utilizing the consistency, coherence, and hierarchy of human anatomy as the supervision signal. Extensive experiments across 10 datasets evaluated through fine-tuning and emergent property analysis demonstrate Lamps' superior robustness, transferability, and clinical potential when compared to 10 baseline models. By learning from multiple perspectives, Lamps presents a unique opportunity for foundation models to develop meaningful, robust representations that are aligned with the structure of human anatomy.

preprint2026arXiv

Strain Engineering of Intrinsic Anomalous Hall and Nernst Effects in Altermagnetic MnTe at Realistic Doping Levels

Hexagonal MnTe has emerged as a prototypical g-wave altermagnet, hosting time-reversal symmetry breaking in momentum space despite a vanishing net magnetization. While this symmetry breaking theoretically allows for an intrinsic anomalous Hall effect, experimentally observed signals have remained weak. In this work, we investigate the origin of this suppression and demonstrate a strategy to amplify anomalous transport responses within the experimentally accessible doping regime. Using a $\bm{k}\cdot\bm{p}$ effective model, we reveal that near the valence band maximum, which corresponds to the energy window relevant for typical hole doping ($\sim10^{19}cm^{-3}$), the intrinsic Hall effect is suppressed due to a symmetry-enforced cancellation of opposing Berry curvature contributions. We propose that breaking the crystalline symmetry via volume-conserving biaxial strain lifts this cancellation, resulting in a significant enhancement of the anomalous Hall conductivity by orders of magnitude. This strain-induced Fermi surface distortion also amplifies the anomalous Nernst effect. Furthermore, the analysis of the spin texture confirms that these strain-enabled anomalous transport signatures emerge while preserving the zero net magnetization.

preprint2025arXiv

RAST: A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction

Traffic prediction is a cornerstone of modern intelligent transportation systems and a critical task in spatio-temporal forecasting. Although advanced Spatio-temporal Graph Neural Networks (STGNNs) and pre-trained models have achieved significant progress in traffic prediction, two key challenges remain: (i) limited contextual capacity when modeling complex spatio-temporal dependencies, and (ii) low predictability at fine-grained spatio-temporal points due to heterogeneous patterns. Inspired by Retrieval-Augmented Generation (RAG), we propose RAST, a universal framework that integrates retrieval-augmented mechanisms with spatio-temporal modeling to address these challenges. Our framework consists of three key designs: 1) Decoupled Encoder and Query Generator to capture decoupled spatial and temporal features and construct a fusion query via residual fusion; 2) Spatio-temporal Retrieval Store and Retrievers to maintain and retrieve vectorized fine-grained patterns; and 3) Universal Backbone Predictor that flexibly accommodates pre-trained STGNNs or simple MLP predictors. Extensive experiments on six real-world traffic networks, including large-scale datasets, demonstrate that RAST achieves superior performance while maintaining computational efficiency.

preprint2022arXiv

Coarse Retinal Lesion Annotations Refinement via Prototypical Learning

Deep-learning-based approaches for retinal lesion segmentation often require an abundant amount of precise pixel-wise annotated data. However, coarse annotations such as circles or ellipses for outlining the lesion area can be six times more efficient than pixel-level annotation. Therefore, this paper proposes an annotation refinement network to convert a coarse annotation into a pixel-level segmentation mask. Our main novelty is the application of the prototype learning paradigm to enhance the generalization ability across different datasets or types of lesions. We also introduce a prototype weighing module to handle challenging cases where the lesion is overly small. The proposed method was trained on the publicly available IDRiD dataset and then generalized to the public DDR and our real-world private datasets. Experiments show that our approach substantially improved the initial coarse mask and outperformed the non-prototypical baseline by a large margin. Moreover, we demonstrate the usefulness of the prototype weighing module in both cross-dataset and cross-class settings.

preprint2022arXiv

Gain/loss effects on spin-orbit coupled ultracold atoms in two-dimensional optical lattices

Due to the fundamental position of spin-orbit coupled ultracold atoms in the simulation of topological insulators, the gain/loss effects on these systems should be evaluated when considering the measurement or the coupling to the environment. Here, incorporating the mature gain/loss techniques into the experimentally realized spin-orbit coupled ultracold atoms in two-dimensional optical lattices, we investigate the corresponding non-Hermitian tight-binding model and evaluate the gain/loss effects on various properties of the system, revealing the interplay of the non-Hermiticity and the spin-orbit coupling. Under periodic boundary conditions, we analytically obtain the topological phase diagram, which undergoes a non-Hermitian gapless interval instead of a point that the Hermitian counterpart encounters for a topological phase transition. We also unveil that the band inversion is just a necessary but not sufficient condition for a topological phase in two-level spin-orbit coupled non-Hermitian systems. Because the nodal loops of the upper or lower two dressed bands of the Hermitian counterpart can be split into exceptional loops in this non-Hermitian model, a gauge-independent Wilson-loop method is developed for numerically calculating the Chern number of multiple degenerate complex bands. Under open boundary conditions, we find that the conventional bulk-boundary correspondence does not break down with only on-site gain/loss due to the lack of non-Hermitian skin effect, but the dissipation of chiral edge states depends on the boundary selection, which may be used in the control of edge-state dynamics. Given the technical accessibility of state-dependent atom loss, this model could be realized in current cold-atom experiments.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint