Zhida Sun

Qijia Chen, Andrea Bellucci, Zhida Sun et al.

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%.

Taizhou Chen, Kai Chen, Xingyu Liu et al.

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.

Zheng Gu, Min Lu, Zhida Sun et al.

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.

Hong Zhou, Rui Zhang, Peifeng Lai et al.

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.

Zhenyu Wang, Jianxi Huang, Zhida Sun et al.

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/.

Xingbo Wang, Haipeng Zeng, Yong Wang et al.

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.