arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 667 records · Page 37Linked to original sources

arXiv2025

Graphene-like nanoribbons connected by four-/five- membered rings on pentacene/picene precursors, Au(110) surface

The rapid development of fabrication of functional high-quality graphene-like nanoribbons has increasingly reliant on integration of diverse nanofabrication platforms. The demand for innovative techniques to enable the exploration and precise manipulation of graphene-like nanoribbons. Herein, we present an on-surface synthesis approach for graphene-like nanoribbons, achieved through the self-assembly and annealing of pentacene/picene monomers on an one-dimensional(1D) Au(110) substrate. Scanning tunneling microscope(STM) analysis reveals that the formation of four- and eight- membered rings between adjacent molecules. Furthermore, we demonstrate a technique for manipulating pentacene dimer without breaking structural integrity by STM tip manipulation. Our results exhibit a potential platform for the development of next-generation graphene-based quantum computing architectures, as well as a technique for fabricating functional graphene-like nanoribbons with exceptional precision.

cond-mat.mes-hall↗

arXiv2025

Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey

Retrieval-Augmented Generation (RAG) is an advanced technique designed to address the challenges of Artificial Intelligence-Generated Content (AIGC). By integrating context retrieval into content generation, RAG provides reliable and up-to-date external knowledge, reduces hallucinations, and ensures relevant context across a wide range of tasks. However, despite RAG's success and potential, recent studies have shown that the RAG paradigm also introduces new risks, including robustness issues, privacy concerns, adversarial attacks, and accountability issues. Addressing these risks is critical for future applications of RAG systems, as they directly impact their trustworthiness. Although various methods have been developed to improve the trustworthiness of RAG methods, there is a lack of a unified perspective and framework for research in this topic. Thus, in this paper, we aim to address this gap by providing a comprehensive roadmap for developing trustworthy RAG systems. We place our discussion around five key perspectives: reliability, privacy, safety, fairness, explainability, and accountability. For each perspective, we present a general framework and taxonomy, offering a structured approach to understanding the current challenges, evaluating existing solutions, and identifying promising future research directions. To encourage broader adoption and innovation, we also highlight the downstream applications where trustworthy RAG systems have a significant impact.

cs.CL↗

arXiv2025

GLAM: Glomeruli Segmentation for Human Pathological Lesions using Adapted Mouse Model

Moving from animal models to human applications in preclinical research encompasses a broad spectrum of disciplines in medical science. A fundamental element in the development of new drugs, treatments, diagnostic methods, and in deepening our understanding of disease processes is the accurate measurement of kidney tissues. Past studies have demonstrated the viability of translating glomeruli segmentation techniques from mouse models to human applications. Yet, these investigations tend to neglect the complexities involved in segmenting pathological glomeruli affected by different lesions. Such lesions present a wider range of morphological variations compared to healthy glomerular tissue, which are arguably more valuable than normal glomeruli in clinical practice. Furthermore, data on lesions from animal models can be more readily scaled up from disease models and whole kidney biopsies. This brings up a question: ``\textit{Can a pathological segmentation model trained on mouse models be effectively applied to human patients?}" To answer this question, we introduced GLAM, a deep learning study for fine-grained segmentation of human kidney lesions using a mouse model, addressing mouse-to-human transfer learning, by evaluating different learning strategies for segmenting human pathological lesions using zero-shot transfer learning and hybrid learning by leveraging mouse samples. From the results, the hybrid learning model achieved superior performance.

eess.IV↗

arXiv2025

Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology

Cell nuclei instance segmentation is a crucial task in digital kidney pathology. Traditional automatic segmentation methods often lack generalizability when applied to unseen datasets. Recently, the success of foundation models (FMs) has provided a more generalizable solution, potentially enabling the segmentation of any cell type. In this study, we perform a large-scale evaluation of three widely used state-of-the-art (SOTA) cell nuclei foundation models (Cellpose, StarDist, and CellViT). Specifically, we created a highly diverse evaluation dataset consisting of 2,542 kidney whole slide images (WSIs) collected from both human and rodent sources, encompassing various tissue types, sizes, and staining methods. To our knowledge, this is the largest-scale evaluation of its kind to date. Our quantitative analysis of the prediction distribution reveals a persistent performance gap in kidney pathology. Among the evaluated models, CellViT demonstrated superior performance in segmenting nuclei in kidney pathology. However, none of the foundation models are perfect; a performance gap remains in general nuclei segmentation for kidney pathology.

eess.IV↗

arXiv2025

Reflections on "Can AI Understand Our Universe?"

This article briefly discusses the philosophical and technical aspects of AI. It focuses on two concepts of understanding: intuition and causality, and highlights three AI technologies: Transformers, chain-of-thought reasoning, and multimodal processing. We anticipate that in principle AI could form understanding, with these technologies representing promising advancements.

cs.AI↗

arXiv2025

Two measurement bases are asymptotically informationally complete for any pure state tomography

One of the fundamental questions in quantum information theory is to find how many measurement bases are required to obtain the full information of a quantum state. While a minimum of four measurement bases is typically required to determine an arbitrary pure state, we prove that for any states generated by finite-depth Clifford + T circuits, just two measurement bases are sufficient. More generally, we prove that two measurement bases are informationally complete for determining algebraic pure states whose state-vector elements represented in the computational basis are algebraic numbers. Since any pure state can be asymptotically approximated by a sequence of algebraic states with arbitrarily high precision, our scheme is referred to as asymptotically informationally complete for pure state tomography. Furthermore, existing works mostly construct the measurements using entangled bases. So far, the best result requires $O(n)$ local measurement bases for $n$-qubit pure-state tomography. Here, we show that two measurement bases that involve polynomial elementary gates are sufficient for uniquely determining sparse algebraic states. Moreover, we prove that two local measurement bases, involving single-qubit local operations only, are informationally complete for certain algebraic states, such as GHZ-like and W-like states. Besides, our two-measurement-bases scheme remains valid for mixed states with certain types of noises. We numerically test the uniqueness of the reconstructed states under two (local) measurement bases with and without measurement and depolarising types of noise. Our scheme provides a theoretical guarantee for pure state tomography in the fault-tolerant quantum computing regime.

quant-ph↗

arXiv2025

YingLong-weather: AI-Based Limited Area Models for Forecasting of Non-precipitation Surface Meteorological Variables

Recently, artificial intelligence-based (AI-based) models for forecasting of global weather have been rapidly developed. Most of the global models are trained on reanalysis datasets with a spatial resolution of 0.25°*0.25°. However, research on AI-based high spatial resolution limited area weather forecasting models remains limited. In this study, YingLong, an AI-based limited area weather forecasting model with a spatial resolution of 3 km * 3 km is developed. YingLong employs a parallel structure of global and local blocks to capture multiscale meteorological features and operates much faster than the dynamical limited area model WRF-ARW. In two selected limited areas (one relatively flat and the other featuring significant mountain ranges), YingLong (with lateral boundary condition imposed by the global AI-based model Pangu-weather) demonstrates superior skill in forecasting surface wind speed compared to WRF-ARW. Additionally, it shows comparable skill in forecasting surface temperature and pressure. The accuracy of surface temperature and humidity forecasts can be further improved by applying better boundary conditions. YingLong also addresses issues related to the lateral boundary conditions of AI-based limited area models, such as selecting the width of the lateral boundary region and combining finer and coarser resolution predictions in this region. Therefore, YingLong has a great potential to generate cost-effective multiyear high-resolution synthetic wind speed that maintain meteorological realism both spatially and temporally, aiding in the planning and operations for wind power generation companies.

physics.ao-ph↗

arXiv2025

Disentangled Condensation for Large-scale Graphs

Graph condensation has emerged as an intriguing technique to save the expensive training costs of Graph Neural Networks (GNNs) by substituting a condensed small graph with the original graph. Despite the promising results achieved, previous methods usually employ an entangled paradigm of redundant parameters (nodes, edges, GNNs), which incurs complex joint optimization during condensation. This paradigm has considerably impeded the scalability of graph condensation, making it challenging to condense extremely large-scale graphs and generate high-fidelity condensed graphs. Therefore, we propose to disentangle the condensation process into a two-stage GNN-free paradigm, independently condensing nodes and generating edges while eliminating the need to optimize GNNs at the same time. The node condensation module avoids the complexity of GNNs by focusing on node feature alignment with anchors of the original graph, while the edge translation module constructs the edges of the condensed nodes by transferring the original structure knowledge with neighborhood anchors. This simple yet effective approach achieves at least 10 times faster than state-of-the-art methods with comparable accuracy on medium-scale graphs. Moreover, the proposed DisCo can successfully scale up to the Ogbn-papers100M graph containing over 100 million nodes with flexible reduction rates and improves performance on the second-largest Ogbn-products dataset by over 5%. Extensive downstream tasks and ablation study on five common datasets further demonstrate the effectiveness of the proposed DisCo framework. Our code is available at https://github.com/BangHonor/DisCo.

cs.SI↗

arXiv2025

WanJuanSiLu: A High-Quality Open-Source Webtext Dataset for Low-Resource Languages

This paper introduces the open-source dataset WanJuanSiLu, designed to provide high-quality training corpora for low-resource languages, thereby advancing the research and development of multilingual models. To achieve this, we have developed a systematic data processing framework tailored for low-resource languages. This framework encompasses key stages such as data extraction, corpus cleaning, content deduplication, security filtering, quality evaluation, and theme classification. Through the implementation of this framework, we have significantly improved both the quality and security of the dataset, while maintaining its linguistic diversity. As of now, data for all five languages have been fully open-sourced. The dataset can be accessed at https://opendatalab.com/applyMultilingualCorpus, and GitHub repository is available at https://github.com/opendatalab/WanJuan3.0

cs.CL↗

arXiv2025

Manipulating nonadiabatic dynamics by plasmonic nanocavity

In recent years, plasmonic nanocavities have emerged as powerful tools for controlling and enhancing light-matter interactions at the nanoscale. This study explores the role of plasmonic nanocavities in manipulating nonadiabatic dynamics, particularly in systems where fast electronic transitions are crucial. By coupling molecular states to the plasmonic resonances of metallic nanocavities, we demonstrate that the local electromagnetic fields generated by plasmons can significantly influence the rates and pathways of nonadiabatic transitions, including electron transfer and excitation relaxation processes. Using the Floquet quantum master equation (FQME) and Floquet surface hopping (FSH) methods that we previously developed, we find that plasmonic nanocavities can enhance nonadiabatic effects by tuning the plasmonic coupling strength, the molecule-metal interaction strength, and the material properties. These approaches offer a new perspective for predicting molecular dynamics in ultrafast processes. Our findings pave the way for designing novel plasmonic devices capable of controlling electron and energy transfer in chemical reactions, optoelectronic applications, and quantum information processing.

physics.optics↗

arXiv2025

Towards LifeSpan Cognitive Systems

Building a human-like system that continuously interacts with complex environments -- whether simulated digital worlds or human society -- presents several key challenges. Central to this is enabling continuous, high-frequency interactions, where the interactions are termed experiences. We refer to this envisioned system as the LifeSpan Cognitive System (LSCS). A critical feature of LSCS is its ability to engage in incremental and rapid updates while retaining and accurately recalling past experiences. In this paper we focus on the domain of Large Language Models (LLMs), where we identify two major challenges: (1) Abstraction and Experience Merging, and (2) Long-term Retention with Accurate Recall. These properties are essential for storing new experiences, organizing past experiences, and responding to the environment in ways that leverage relevant historical data. Unlike language models with continual learning, which typically rely on large corpora for fine-tuning and focus on improving performance within specific domains or tasks, LSCS must rapidly and incrementally update with new information from its environment at a high frequency. Existing technologies with the potential of solving the above two major challenges can be classified into four classes based on a conceptual metric called Storage Complexity, which measures the relative space required to store past experiences. Each of these four classes of technologies has its own strengths and limitations while we argue none of them alone can achieve LSCS alone. To this end, we propose a potential instantiation for LSCS that can integrate all four classes of technologies. The new instantiation, serving as a conjecture, operates through two core processes: Absorbing Experiences and Generating Responses.

cs.CL↗

arXiv2025

Observation of condensed moire exciton polaritons in twisted photonic lattices at room temperature

Moire lattices attract significant attention in double-layer graphene and TMD layer heterostructures as well as in photonic crystals due to the interesting exotic physics that emerges within these structures. However, direct measurement of the moiré ground, excited states and Bloch bands in twisted photonic lattices is still illusive. In this work we report strong coupling between excitons in CsPbBr3 microplates and moire photonic modes at room temperature. Depending on the coupling strength between the nearest potential sites, we observe staggered moire polariton ground states, excited states and moire polariton bands. Phase locked moire zero (in-phase) states and moire pi (antiphase) states with different spatial distributions are measured. The moire polariton distribution can be tuned into the shape of a parallelogram by controlling the depth and width of the potential in one photonic lattice with another superimposed one fixed. In addition, moire polaritons in twisted 2D honeycomb lattices are also observed. Increasing the pumping density, we realize exciton polariton condensation in the moire potential sites of the 1D/2D twisted lattices with the coherence time of around 1.4 ps. Our work lays the foundation to study coherent moire polariton condensation in twisted photonic lattices at room temperature.

physics.optics↗

arXiv2025

Beyond-Hubbard pairing in a cuprate ladder

The Hubbard model is believed to capture the essential physics of cuprate superconductors. However, recent theoretical studies suggest that it fails to reproduce a robust and homogeneous superconducting ground state. Here, using resonant inelastic x-ray scattering and density matrix renormalization group calculations, we show that magnetic excitations in the prototypical cuprate ladder Sr$_{14}$Cu$_{24}$O$_{41}$ are inconsistent with those of a simple Hubbard model. The magnetic response of hole carriers, contributing to an emergent branch of spin excitations, is strongly suppressed. This effect is the consequence of d-wave-like pairing, enhanced by nearly an order of magnitude through a large nearest-neighbor attractive interaction. The similarity between cuprate ladders and the two-dimensional compounds suggests that such an enhanced hole pairing may be a universal feature of superconducting cuprates.

cond-mat.str-el↗

arXiv2025

Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap

Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations. Due to the diversification of internet platforms and the exponential growth of users and items, the importance of cold-start recommendation (CSR) is becoming increasingly evident. At the same time, large language models (LLMs) have achieved tremendous success and possess strong capabilities in modeling user and item information, providing new potential for cold-start recommendations. However, the research community on CSR still lacks a comprehensive review and reflection in this field. Based on this, in this paper, we stand in the context of the era of large language models and provide a comprehensive review and discussion on the roadmap, related literature, and future directions of CSR. Specifically, we have conducted an exploration of the development path of how existing CSR utilizes information, from content features, graph relations, and domain information, to the world knowledge possessed by large language models, aiming to provide new insights for both the research and industrial communities on CSR. Related resources of cold-start recommendations are collected and continuously updated for the community in https://github.com/YuanchenBei/Awesome-Cold-Start-Recommendation.

cs.IR↗

arXiv2025

Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We provide a comprehensive analysis of SSCL and demonstrate that unreliable distributions of unlabeled data lead to unstable training and refinement of the progressing stages. This problem severely impacts the performance of SSCL. To address the limitations, we propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning, which leverages both semantic and structural information to achieve more stable knowledge distillation on unlabeled data and exhibit robustness against distribution bias. Firstly, we formalize a general model of structural distillation and design a dynamic graph construction for the continual learning progress. Next, we define a structure distillation vector and design a dynamic sub-graph distillation algorithm, which enables end-to-end training and adaptability to scale up tasks. The entire proposed method is adaptable to various CL methods and supervision settings. Finally, experiments conducted on three datasets CIFAR10, CIFAR100, and ImageNet-100, with varying supervision ratios, demonstrate the effectiveness of our proposed approach in mitigating the catastrophic forgetting problem in semi-supervised continual learning scenarios.

cs.LG↗

arXiv2025

Study the quantum resolution sizes and atomic bonding states of two-dimensional tin monoxide

Understanding the interatomic bonding and electronic properties of two-dimensional (2D) materials is crucial for preparing high-performance 2D semiconductor materials. We have calculated the band structure, electronic properties, and bonding characteristics of SnO in 2D materials by using density functional theory (DFT) and combining bond energy and bond charge models. Atomic bonding analysis enables us to deeply and meticulously analyze the interatomic bonding and charge transfer in the layered structure of SnO. This study greatly enhances our understanding of the local bonding state on the surface of 2D structural materials. In addition, we use the renormalization method to operate energy to determine the wave function at different quantum resolutions. This is of great significance for describing the size and phase transition of nanomaterials.

cond-mat.mtrl-sci↗

arXiv2025

PySpatial: A High-Speed Whole Slide Image Pathomics Toolkit

Whole Slide Image (WSI) analysis plays a crucial role in modern digital pathology, enabling large-scale feature extraction from tissue samples. However, traditional feature extraction pipelines based on tools like CellProfiler often involve lengthy workflows, requiring WSI segmentation into patches, feature extraction at the patch level, and subsequent mapping back to the original WSI. To address these challenges, we present PySpatial, a high-speed pathomics toolkit specifically designed for WSI-level analysis. PySpatial streamlines the conventional pipeline by directly operating on computational regions of interest, reducing redundant processing steps. Utilizing rtree-based spatial indexing and matrix-based computation, PySpatial efficiently maps and processes computational regions, significantly accelerating feature extraction while maintaining high accuracy. Our experiments on two datasets-Perivascular Epithelioid Cell (PEC) and data from the Kidney Precision Medicine Project (KPMP)-demonstrate substantial performance improvements. For smaller and sparse objects in PEC datasets, PySpatial achieves nearly a 10-fold speedup compared to standard CellProfiler pipelines. For larger objects, such as glomeruli and arteries in KPMP datasets, PySpatial achieves a 2-fold speedup. These results highlight PySpatial's potential to handle large-scale WSI analysis with enhanced efficiency and accuracy, paving the way for broader applications in digital pathology.

eess.IV↗

arXiv2025

BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs

Biomedical data is inherently multimodal, comprising physical measurements and natural language narratives. A generalist biomedical AI model needs to simultaneously process different modalities of data, including text and images. Therefore, training an effective generalist biomedical model requires high-quality multimodal data, such as parallel image-text pairs. Here, we present PMC-15M, a novel dataset that is two orders of magnitude larger than existing biomedical multimodal datasets such as MIMIC-CXR, and spans a diverse range of biomedical image types. PMC-15M contains 15 million biomedical image-text pairs collected from 4.4 million scientific articles. Based on PMC-15M, we have pretrained BiomedCLIP, a multimodal foundation model, with domain-specific adaptations tailored to biomedical vision-language processing. We conducted extensive experiments and ablation studies on standard biomedical imaging tasks from retrieval to classification to visual question-answering (VQA). BiomedCLIP achieved new state-of-the-art results in a wide range of standard datasets, substantially outperforming prior approaches. Intriguingly, by large-scale pretraining on diverse biomedical image types, BiomedCLIP even outperforms state-of-the-art radiology-specific models such as BioViL in radiology-specific tasks such as RSNA pneumonia detection. In summary, BiomedCLIP is a fully open-access foundation model that achieves state-of-the-art performance on various biomedical tasks, paving the way for transformative multimodal biomedical discovery and applications. We release our models at https://aka.ms/biomedclip to facilitate future research in multimodal biomedical AI.

cs.CV↗