arXiv subjects

Zipeng Liu

Publications and source records attributed to Zipeng Liu.

12 recordsLinked to original sources

arXiv2026

MM-SVGEdit: A Multimodal-Driven SVG Editing for UI Design

In the field of UI design, Scalable Vector Graphics (SVG) is widely used as a design medium. However, traditional SVG editing techniques have high entry barriers and require cumbersome manual iteration, while LLM-based editing solutions suffer from low accuracy and poor user controllability. To address these issues, we propose MM-SVGEdit, a multimodal-driven SVG editing approach that integrates traditional SVG editing and LLM-based methods. We introduce a two-stage strategy in which visual grounding is followed by modification. Both stages support two interaction modalities: natural language instructions and direct manipulation (mouse and keyboard). We trained and evaluated MM-SVGEdit on a self-constructed dataset of 14,476 question-answer pairs generated from UIs, covering 11 types of editing operations on both single and multiple UI targets. The results show that MM-SVGEdit improves SVG editing accuracy, efficiency, and user-perceived control while reducing token consumption and response time.

cs.HC↗

arXiv2026

Visual Analysis of LLM-based Entity Resolution from Scientific Papers

This paper focuses on the visual analytics support for extracting domain-specific entity from extensive scientific literature, a task with inherent limitations using traditional named entity resolution methods. With the advent of large language models (LLMs) such as GPT-4, significant improvements over conventional machine learning approaches have been achieved due to LLM's capability on entity resolution integrate abilities such as understanding multiple types of text. This research introduces a new visual analysis pipeline that integrates these advanced LLMs with versatile visualization and interaction designs to support batch entity resolution. Specifically, we focus on a specific material science field of Metal-Organic Frameworks (MOFs) and a large data collection namely CSD-MOFs. Through collaboration with domain experts in material science, we obtain well-labeled synthesis paragraphs. We propose human-in-the-loop refinement over the entity resolution process using visual analytics techniques, which allows domain experts to interactively integrate insights into LLM intelligence, including error analysis and interpretation of the retrieval-augmented generation (RAG) algorithm. Our evaluation through the case study of example selection for RAG demonstrates that this human-machine collaborative approach improved single-document entity resolution accuracy by approximately 30%.

cs.IR↗

arXiv2026

Visualization of Machine Learning Models through Their Spatial and Temporal Listeners

Model visualization (ModelVis) has emerged as a major research direction, yet existing taxonomies are largely organized by data or tasks, making it difficult to treat models as first-class analysis objects. We present a model-centric two-stage framework that employs abstract listeners to capture spatial and temporal model behaviors, and then connects the translated model behavior data to the classical InfoVis pipeline. To apply the framework at scale, we build a retrieval-augmented human--large language model (LLM) extraction workflow and curate a corpus of 128 VIS/VAST ModelVis papers with 331 coded figures. Our analysis shows a dominant result-centric priority on visualizing model outcomes, quantitative/nominal data type, statistical charts, and performance evaluation. Citation-weighted trends further indicate that less frequent model-mechanism-oriented studies have disproportionately high impact while are less investigated recently. Overall, the framework is a general approach for comparing existing ModelVis systems and guiding possible future designs.

cs.LG↗

arXiv2025

Theoretical and experimental studies of energy modulation to demodulation in seeded free-electron lasers

Laser manipulation plays a critical role in precisely tailoring relativistic electron beams through energy modulation, enabling the generation of coherent, intense, and ultrashort radiation in accelerator-based light sources such as synchrotron radiation facilities and free-electron lasers (FELs). However, laser-induced energy modulation inevitably degrades electron beam quality by increasing the energy spread, thereby limiting high-repetition-rate operation. Here, we investigate energy modulation and demodulation in a seeded FEL using two modulators separated by a tunable phase shifter. Analytical analysis and three-dimensional simulations show that a $\pi$ phase delay can nearly reverse the laser-beam interaction and substantially suppress the residual modulation. Diagnostics based on coherent undulator radiation and time-resolved measurements are established to characterize weak residual modulation, and a dedicated demodulation undulator is designed for controlled studies. Preliminary experiments performed at the Shanghai soft X-ray FEL facility using the existing seeding beamline demonstrate laser-induced energy-modulation suppression. Together with the analytical and numerical studies, these results establish a practical framework for investigating the transition from energy modulation to demodulation in seeded FELs, with potential applications in high-repetition-rate, fully coherent X-ray sources with improved preservation of electron beam quality.

physics.acc-ph↗

arXiv2025

Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach

Graph unlearning is tailored for GNNs to handle widespread and various graph structure unlearning requests, which remain largely unexplored. The GIF (graph influence function) achieves validity under partial edge unlearning, but faces challenges in dealing with more disturbing node unlearning. To avoid the overhead of retraining and realize the model utility of unlearning, we proposed a novel node unlearning method to reverse the process of aggregation in GNN by embedding reconstruction and to adopt Range-Null Space Decomposition for the nodes' interaction learning. Experimental results on multiple representative datasets demonstrate the SOTA performance of our proposed approach.

cs.LG↗

arXiv2024

Space Charge-Induced Emittance Growth in the Downstream Section of ERL Injectors

The injector for ERL-FEL has been widely researched. Unlike traditional linacs, the bunch in the injector for ERLs requires additional deflection and matching section at lower energies. It makes the bunch more susceptible to the effects of the Space Charge. This will lead to a degradation in beam quality. In this paper, we comprehensively analyze the impact of space charge on ERL-injector and propose new design concepts to further maintain beam quality.

physics.acc-ph↗

arXiv2024

The design of high-brightness ERL-FEL injector based on VHF electron gun

In the past decade, the fourth-generation light source based on the combination of Energy Recovery Linac (ERL) and Free-Electron Laser (FEL) using superconducting linear accelerators has garnered significant attention. It holds immense potential, particularly in generating high-power Extreme Ultraviolet (EUV) light sources. This article primarily focuses on the physical design of an injector for ERL-FEL, based on a Very High Frequency (VHF) electron gun with a charge of 100 pC. The beam energy is accelerated to 10 MeV using 3-cell superconducting cavity. The optimization of beam parameters is conducted through employment of BMad and ASTRA simulations, incorporating the concept of Merger optimization. The beam emittance is less than 0.6 mm mrad, and the peak current at the injector exit exceeds 18 A. We present a new method to evaluate the Longitudinal Space Charge (LSC) effects in merger sections, which can be readily applied in design work. Furthermore, we introduce a novel type of merger. The performance of this new merger is comparable to the previously known optimum, the zigzag merger, offering a potential alternative solution for injectors in ERLs.

physics.acc-ph↗

arXiv2024

GeneticPrism: Multifaceted Visualization of Scientific Impact Evolutions

Understanding the evolution of scholarly impact is essential for many real-life decision-making processes in academia, such as research planning, frontier exploration, and award selection. Popular platforms like Google Scholar and Web of Science rely on numerical indicators that are too abstract to convey the context and content of scientific impact, while most existing visualization approaches on mapping science do not consider the presentation of individual scholars' impact evolution using curated self-citation data. This paper builds on our previous work and proposes an integrated pipeline to visualize a scholar's impact evolution from multiple topic facets. A novel 3D prism-shaped visual metaphor is introduced as the overview of a scholar's impact, whilst their scientific evolution on each topic is displayed in a more structured manner. Additional designs by topic chord diagram, streamgraph visualization, and inter-topic flow map, optimized by an elaborate layout algorithm, assist in perceiving the scholar's scientific evolution across topics. A new six-degree-impact glyph metaphor highlights key interdisciplinary works driving the evolution. The proposed visualization methods are evaluated through case studies analyzing the careers of prestigious Turing award laureates and a major visualization venue.

cs.DL↗

arXiv2024

LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations

The extraction of Metal-Organic Frameworks (MOFs) synthesis route from literature has been crucial for the logical MOFs design with desirable functionality. The recent advent of large language models (LLMs) provides disruptively new solution to this long-standing problem. While the latest researches mostly stick to primitive zero-shot LLMs lacking specialized material knowledge, we introduce in this work the few-shot LLM in-context learning paradigm. First, a human-AI interactive data curation approach is proposed to secure high-quality demonstrations. Second, an information retrieval algorithm is applied to pick and quantify few-shot demonstrations for each extraction. Over three datasets randomly sampled from nearly 90,000 well-defined MOFs, we conduct triple evaluations to validate our method. The synthesis extraction, structure inference, and material design performance of the proposed few-shot LLMs all significantly outplay zero-shot LLM and baseline methods. The lab-synthesized material guided by LLM surpasses 91.1% high-quality MOFs of the same class reported in the literature, on the key physical property of specific surface area.

cs.CL↗

arXiv2024

Multi-View Empowered Structural Graph Wordification for Language Models

Significant efforts have been dedicated to integrating the powerful Large Language Models (LLMs) with diverse modalities, particularly focusing on the fusion of language, vision and audio data. However, the graph-structured data, which is inherently rich in structural and domain-specific knowledge, has not yet been gracefully adapted to LLMs. Existing methods either describe the graph with raw text, suffering the loss of graph structural information, or feed Graph Neural Network (GNN) embeddings into LLMs at the cost of losing explainable prompt semantics. To bridge this gap, we introduce an end-to-end modality-aligning framework for LLM-graph alignment: Dual-Residual Vector Quantized-Variational AutoEncoder, namely Dr.E. Our approach is purposefully designed to facilitate token-level alignment with LLMs, enabling an effective translation of the intrinsic `language' of graphs into comprehensible natural language. We also manage to enhance LLMs' more robust structural understanding of graphs by incorporating multiple views of the central nodes based on their surrounding nodes at various distances. Our experimental evaluations on standard graph tasks demonstrate competitive performance against other state-of-the-art (SOTA) approaches. Additionally, our framework ensures certain visual interpretability, efficiency, and robustness, marking the promising successful endeavor to achieve token-level alignment between LLMs and GNNs. Our code is available at: https://github.com/Timothy914/Dr.E.

cs.CL↗

arXiv2021

Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding

Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links. GNN developers rely on quantitative metrics of the predictions to evaluate a GNN, but similar to many other neural networks, it is difficult for them to understand if the GNN truly learns characteristics of a graph as expected. We propose an approach to corresponding an input graph to its node embedding (aka latent space), a common component of GNNs that is later used for prediction. We abstract the data and tasks, and develop an interactive multi-view interface called CorGIE to instantiate the abstraction. As the key function in CorGIE, we propose the K-hop graph layout to show topological neighbors in hops and their clustering structure. To evaluate the functionality and usability of CorGIE, we present how to use CorGIE in two usage scenarios, and conduct a case study with five GNN experts.

cs.LG↗

arXiv2021

Numerical study of transverse position monitor and compensation for x-ray polarization diagnosis

Diagnosing free electron laser (FEL) polarization is critical for polarization-modulated research such as x-ray free electron laser (XFEL) diffraction imaging and probing material magnetism. In an electron time-of-flight (eTOF)\ polarimeter, the flight time and angular distribution of photoelectrons were designed based on x-ray polarimetry for on-site diagnosis. However, the transverse position of x-ray FEL pulses introduces error into the measured photoelectron angular distribution. This work thus proposes a method to monitor the transverse position using an eTOF polarimeter and explains how to compensate for the error due to transverse position. A comprehensive numerical model is developed to demonstrate the feasibility of the compensation method, and the results reveal that a spatial resolution of 20 $\mu$m and a polarity improved by 0.5\% is possible with fully polarized FEL pulses. The impact of FEL\ pulses and a method to calibrate their linearity is also discussed.

physics.ins-det↗