arXiv subjects

Zhida Sun

Publications and source records attributed to Zhida Sun.

12 recordsLinked to original sources

arXiv2026

Semantic-Structural Alignment for Generative Pictorial Charts

Traditional statistical graphics are precise but often lack the visual appeal, memorability, and engagement of pictorial charts. We present a generative framework for the automated synthesis of pictorial charts that bridges the gap between semantic expression and structural faithfulness. Rather than treating charts merely as images to be stylized, we frame the problem as a dual-conditioned generation task guided by two parallel external control signals: a text prompt capturing the semantic context of the editing intent, and a context image providing the abstract statistical chart's global structure. To reinforce these controls within a Multi-Modal Diffusion Transformer, we introduce two complementary feature-level mechanisms: structural alignment to anchor spatial layouts to the input chart, and semantic alignment to transfer expressive textures from reference images. Generalizing across major visual channels (i.e., length, area, angle, and position) and diverse semantic domains, our method produces pictorial charts that are both artistically compelling and structurally consistent. Extensive quantitative evaluations and perceptual user studies demonstrate that our framework outperforms traditional controllable generation and image editing baselines, providing a foundation for high-fidelity, data-driven generative modeling in expressive visual storytelling. Project page: https://ssalign.github.io/.

cs.GR↗

arXiv2026

SkillDroid: Compile Once, Reuse Forever

LLM-based mobile GUI agents treat every task invocation as an independent reasoning episode, requiring a full LLM inference call at each action step. This per-step dependence makes them stateless: a task completed successfully yesterday is re-derived from scratch today, with no improvement in reliability or speed. We present SkillDroid, a three-layer skill agent that compiles successful LLM-guided GUI trajectories into parameterized skill templates (sequences of UI actions with weighted element locators and typed parameter slots) and replays them on future invocations without any LLM calls. A matching cascade (regex patterns, embedding similarity, and app filtering) routes incoming instructions to stored skills, while a failure-learning layer triggers recompilation when skill reliability degrades. Over a 150-round longitudinal evaluation with systematic instruction variation and controlled perturbations, SkillDroid achieves an 85.3% success rate (23 percentage points above a stateless LLM baseline) while using 49% fewer LLM calls. The skill replay mechanism achieves a perfect 1000% success rate across 79 replay rounds at 2.4 times the speed of full LLM execution. Most critically, the system improves with use: its success rate converges upward from 87% to 91%, while the baseline degrades from 80% to 44%.

cs.HC↗

arXiv2026

BadminSense: Enabling Fine-Grained Badminton Stroke Evaluation on a Single Smartwatch

Evaluating badminton performance often requires expert coaching, which is rarely accessible for amateur players. We present BadminSense, a smartwatch-based system for fine-grained badminton performance analysis using wearable sensing. Through interviews with experienced badminton players, we identified four system design requirements with three implementation insights that guide the development of BadminSense. We then collected a badminton strokes dataset on 12 experienced badminton amateurs and annotated it with fine-grained labels, including stroke type, expert-assessed stroke rating, and shuttle impact location. Built on this dataset, BadminSense segments and classifies strokes, predicts stroke quality, and estimates shuttle impact location using vibration signal from an off-the-shelf smartwatch. Our evaluations show that BadminSense achieves a stroke classification accuracy of 91.43%, an average quality rating error of 0.438, and an average impact location estimation error of 12.9%. A real-world usability study further demonstrates BadminSense's potential to provide reliable and meaningful support for daily badminton practice.

cs.HC↗

arXiv2026

Cycle-Consistent Tuning for Layered Image Decomposition

Disentangling visual layers in real-world images is a persistent challenge in vision and graphics, as such layers often involve non-linear and globally coupled interactions, including shading, reflection, and perspective distortion. In this work, we present an in-context image decomposition framework that leverages large diffusion foundation models for layered separation. We focus on the challenging case of logo-object decomposition, where the goal is to disentangle a logo from the surface on which it appears while faithfully preserving both layers. Our method fine-tunes a pretrained diffusion model via lightweight LoRA adaptation and introduces a cycle-consistent tuning strategy that jointly trains decomposition and composition models, enforcing reconstruction consistency between decomposed and recomposed images. This bidirectional supervision substantially enhances robustness in cases where the layers exhibit complex interactions. Furthermore, we introduce a progressive self-improving process, which iteratively augments the training set with high-quality model-generated examples to refine performance. Extensive experiments demonstrate that our approach achieves accurate and coherent decompositions and also generalizes effectively across other decomposition types, suggesting its potential as a unified framework for layered image decomposition.

cs.CV↗

arXiv2026

Iconix: Controlling Semantics and Style in Progressive Icon Grids Generation

Visual communication often needs stylistically consistent icons that span concrete and abstract meanings, for use in diverse contexts. We present Iconix, a human-AI co-creative system that organizes icon generation along two axes: semantic richness (what is depicted) and visual complexity (how much detail). Given a user-specified concept, Iconix constructs a semantic scaffold of related analytical perspectives and employs chained, image-conditioned generation to produce a coherent style of exemplars. Each exemplar is then automatically distilled into a progressive sequence, from detailed and elaborate to abstract and simple. The resulting two-dimensional grid exposes a navigable space, helping designers reason jointly about figurative content and visual abstraction. A within-subjects study (N = 32) found that compared to a baseline workflow, participants produced icon grids more creatively, reported lower workload, and explored a coherent range of design variations. We discuss implications for human-machine co-creative approaches that couple semantic scaffolding with progressive simplification to support visual abstraction.

cs.HC↗

arXiv2025

Creative Blends of Visual Concepts

Visual blends combine elements from two distinct visual concepts into a single, integrated image, with the goal of conveying ideas through imaginative and often thought-provoking visuals. Communicating abstract concepts through visual blends poses a series of conceptual and technical challenges. To address these challenges, we introduce Creative Blends, an AI-assisted design system that leverages metaphors to visually symbolize abstract concepts by blending disparate objects. Our method harnesses commonsense knowledge bases and large language models to align designers' conceptual intent with expressive concrete objects. Additionally, we employ generative text-to-image techniques to blend visual elements through their overlapping attributes. A user study (N=24) demonstrated that our approach reduces participants' cognitive load, fosters creativity, and enhances the metaphorical richness of visual blend ideation. We explore the potential of our method to expand visual blends to include multiple object blending and discuss the insights gained from designing with generative AI.

cs.HC↗

arXiv2024

AdaMotif: Graph Simplification via Adaptive Motif Design

With the increase of graph size, it becomes difficult or even impossible to visualize graph structures clearly within the limited screen space. Consequently, it is crucial to design effective visual representations for large graphs. In this paper, we propose AdaMotif, a novel approach that can capture the essential structure patterns of large graphs and effectively reveal the overall structures via adaptive motif designs. Specifically, our approach involves partitioning a given large graph into multiple subgraphs, then clustering similar subgraphs and extracting similar structural information within each cluster. Subsequently, adaptive motifs representing each cluster are generated and utilized to replace the corresponding subgraphs, leading to a simplified visualization. Our approach aims to preserve as much information as possible from the subgraphs while simplifying the graph efficiently. Notably, our approach successfully visualizes crucial community information within a large graph. We conduct case studies and a user study using real-world graphs to validate the effectiveness of our proposed approach. The results demonstrate the capability of our approach in simplifying graphs while retaining important structural and community information.

cs.SI↗

arXiv2024

Layered Image Vectorization via Semantic Simplification

This work presents a progressive image vectorization technique that reconstructs the raster image as layer-wise vectors from semantic-aligned macro structures to finer details. Our approach introduces a new image simplification method leveraging the feature-average effect in the Score Distillation Sampling mechanism, achieving effective visual abstraction from the detailed to coarse. Guided by the sequence of progressive simplified images, we propose a two-stage vectorization process of structural buildup and visual refinement, constructing the vectors in an organized and manageable manner. The resulting vectors are layered and well-aligned with the target image's explicit and implicit semantic structures. Our method demonstrates high performance across a wide range of images. Comparative analysis with existing vectorization methods highlights our technique's superiority in creating vectors with high visual fidelity, and more importantly, achieving higher semantic alignment and more compact layered representation. The project homepage is https://szuviz.github.io/layered_vectorization/.

cs.CV↗

arXiv2024

Beyond Numbers: Creating Analogies to Enhance Data Comprehension and Communication with Generative AI

Unfamiliar measurements usually hinder readers from grasping the scale of the numerical data, understanding the content, and feeling engaged with the context. To enhance data comprehension and communication, we leverage analogies to bridge the gap between abstract data and familiar measurements. In this work, we first conduct semi-structured interviews with design experts to identify design problems and summarize design considerations. Then, we collect an analogy dataset of 138 cases from various online sources. Based on the collected dataset, we characterize a design space for creating data analogies. Next, we build a prototype system, AnalogyMate, that automatically suggests data analogies, their corresponding design solutions, and generated visual representations powered by generative AI. The study results show the usefulness of AnalogyMate in aiding the creation process of data analogies and the effectiveness of data analogy in enhancing data comprehension and communication.

cs.HC↗

arXiv2024

EL-VIT: Probing Vision Transformer with Interactive Visualization

Nowadays, Vision Transformer (ViT) is widely utilized in various computer vision tasks, owing to its unique self-attention mechanism. However, the model architecture of ViT is complex and often challenging to comprehend, leading to a steep learning curve. ViT developers and users frequently encounter difficulties in interpreting its inner workings. Therefore, a visualization system is needed to assist ViT users in understanding its functionality. This paper introduces EL-VIT, an interactive visual analytics system designed to probe the Vision Transformer and facilitate a better understanding of its operations. The system consists of four layers of visualization views. The first three layers include model overview, knowledge background graph, and model detail view. These three layers elucidate the operation process of ViT from three perspectives: the overall model architecture, detailed explanation, and mathematical operations, enabling users to understand the underlying principles and the transition process between layers. The fourth interpretation view helps ViT users and experts gain a deeper understanding by calculating the cosine similarity between patches. Our two usage scenarios demonstrate the effectiveness and usability of EL-VIT in helping ViT users understand the working mechanism of ViT.

cs.AI↗

arXiv2023

Amplifying the Music Listening Experience through Song Comments on Music Streaming Platforms

Music streaming services are increasingly popular among younger generations who seek social experiences through personal expression and sharing of subjective feelings in comments. However, such emotional aspects are often ignored by current platforms, which affects the listeners' ability to find music that triggers specific personal feelings. To address this gap, this study proposes a novel approach that leverages deep learning methods to capture contextual keywords, sentiments, and induced mechanisms from song comments. The study augments a current music app with two features, including the presentation of tags that best represent song comments and a novel map metaphor that reorganizes song comments based on chronological order, content, and sentiment. The effectiveness of the proposed approach is validated through a usage scenario and a user study that demonstrate its capability to improve the user experience of exploring songs and browsing comments of interest. This study contributes to the advancement of music streaming services by providing a more personalized and emotionally rich music experience for younger generations.

cs.HC↗

arXiv2020

VoiceCoach: Interactive Evidence-based Training for Voice Modulation Skills in Public Speaking

The modulation of voice properties, such as pitch, volume, and speed, is crucial for delivering a successful public speech. However, it is challenging to master different voice modulation skills. Though many guidelines are available, they are often not practical enough to be applied in different public speaking situations, especially for novice speakers. We present VoiceCoach, an interactive evidence-based approach to facilitate the effective training of voice modulation skills. Specifically, we have analyzed the voice modulation skills from 2623 high-quality speeches (i.e., TED Talks) and use them as the benchmark dataset. Given a voice input, VoiceCoach automatically recommends good voice modulation examples from the dataset based on the similarity of both sentence structures and voice modulation skills. Immediate and quantitative visual feedback is provided to guide further improvement. The expert interviews and the user study provide support for the effectiveness and usability of VoiceCoach.

cs.HC↗