Fluid–structure interaction (FSI) systems involve distinct physical domains, fluid and solid, governed by different partial differential equations and coupled at a dynamic interface. While learning-based solvers offer a promising alternative to costly numerical simulations, existing methods struggle to capture the heterogeneous dynamics of FSI within a unified framework. This challenge is further exacerbated by inconsistencies in response across domains due to interface coupling and by disparities in learning difficulty across fluid and solid regions, leading to instability during prediction. To address these challenges, we propose the Heterogeneous Graph Attention Solver (HGATSolver). HGATSolver encodes the system as a heterogeneous graph, embedding physical structure directly into the model via distinct node and edge types for fluid, solid, and interface regions. This enables specialized message-passing mechanisms tailored to each physical domain. To stabilize explicit time stepping, we introduce a novel physics-conditioned gating mechanism that serves as a learnable, adaptive relaxation factor. Furthermore, an Inter-domain Gradient-Balancing Loss dynamically balances the optimization objectives across domains based on predictive uncertainty. Extensive experiments on two constructed FSI benchmarks and a public dataset demonstrate that HGATSolver achieves state-of-the-art performance, establishing an effective framework for surrogate modeling of coupled multi-physics systems.

Transcatheter tricuspid valve replacement (TTVR) has emerged as a promising minimally invasive procedure for treating severe tricuspid regurgitation (TR). However, accurate catheter delivery remains a significant challenge, primarily due to the reliance on 2D vision feedback, complex catheter kinematics, camera-to-robot pose calibration, which are difficult to generalize across patients. To address these issues, this paper presents a model-free robotic catheter delivery strategy for TTVR using Data-Enabled Predictive Control (DeePC). This approach leverages data-driven control to optimize catheter positioning without the need for prior knowledge of the system’s dynamics, eliminating the need for complex kinematic models or camera calibration. The proposed method incorporates environmental constraints to ensure the safety of the procedure, delivering the catheter to the desired location with high accuracy across varying catheters and camera poses. Experimental results demonstrate the effectiveness and versatility of the approach, suggesting its potential for broader applications in robotic-assisted surgeries. This work presents a new perspective for vision based robotic TTVR, as well as other clinical interventions involving robotic catheter control.

The expressive power of Chinese calligraphy lies in its gestural dynamics, such as rhythm and velocity, which are implicitly captured in the final 2D form. This paper introduces Generative Strokes, a novel parametric framework that translates these implicit dynamics into explicit and controllable three-dimensional geometry. Our approach models a stroke from its boundary contours, constructing a volumetric representation through a multi-stage generative pipeline. The framework establishes an internal structural scaffold, computes a depth profile for the boundaries based on the integral of their local angular changes, and generates a continuous internal surface by enforcing a geometric orthogonality constraint. This process encodes gestural flow directly into the stroke’s 3D form. Key parameters for depth intensity, flow smoothing, and surface curvature provide direct control over the geometric expression of gestural qualities. This framework offers a new methodology for digital cultural heritage, enabling (1) the quantitative analysis of calligraphic styles, (2) the generation of novel 3D calligraphic sculptures rooted in traditional aesthetics, and (3) new possibilities for interactive educational tools that make the intangible aspects of calligraphy more accessible.

Emerging multimodal large language models (MLLMs) exhibit great potential for chart question answering (CQA). Recent efforts primarily focus on scaling up training datasets (i.e., charts, data tables, and question-answer (QA) pairs) through data collection and synthesis. However, our empirical study on existing MLLMs and CQA datasets reveals notable gaps. First, current data collection and synthesis focus on data volume and lack consideration of fine-grained visual encodings and QA tasks, resulting in unbalanced data distribution divergent from practical CQA scenarios. Second, existing work follows the training recipe of the base MLLMs initially designed for natural images, under-exploring the adaptation to unique chart characteristics, such as rich text elements. To fill the gap, we propose a visualization-referenced instruction tuning approach to guide the training dataset enhancement and model development. Specifically, we propose a novel data engine to effectively filter diverse and high-quality data from existing datasets and subsequently refine and augment the data using LLM-based generation techniques to better align with practical QA tasks and visual encodings. Then, to facilitate the adaptation to chart characteristics, we utilize the enriched data to train an MLLM by unfreezing the vision encoder and incorporating a mixture-of-resolution adaptation strategy for enhanced fine-grained recognition. Experimental results validate the effectiveness of our approach. Even with fewer training examples, our model consistently outperforms state-of-the-art CQA models on established benchmarks. We also contribute a dataset split as a benchmark for future research. Source codes and datasets of this paper are available at https://github.com/zengxingchen/ChartQA-MLLM.

Landscape renderings are realistic images of landscape sites, allowing stakeholders to perceive better and evaluate design ideas. While recent advances in Generative Artificial Intelligence (GAI (generative artificial intelligence)) enable automated generation of landscape renderings, the End to End (endtoend) methods are not compatible with common design processes, leading to insufficient alignment with design idealizations and limited cohesion of iterative landscape design. Informed by a formative study for comprehending design requirements, we present PlantoGraphy, an iterative design system that allows for interactive configuration of generative artificial intelligence models to accommodate human-centered design practice. A two-stage pipeline is incorporated: first, the concretization module transforms conceptual ideas into concrete scene layouts with a domain-oriented large language model; and second, the illustration module converts scene layouts into realistic landscape renderings with a layout-guided diffusion model Fine-tune (finetune)ed through Low-Rank Adaptation (LoRA) (lora). PlantoGraphy has undergone a series of performance evaluations and user studies, demonstrating its effectiveness in landscape rendering generation and the high recognition of its interactive functionality.

"Boundary awareness" has become increasingly prominent in the social sciences, highlighting the critical role of personal space in interpersonal behavior. Globalization and digitalization, however, have intensified human interconnectedness, blurring boundaries between individuals and sparking interpersonal conflicts. The delineation of public and private spaces, as well as the understanding of others’ boundaries, is primarily shaped by individuals’ cognitive models. Based on the theoretical framework of cognitive differences, we take as our starting point a research question: "How can installation design be used to raise public awareness of unconscious boundary violations caused by cognitive differences, and inspire reflection on achieving balance in interpersonal interactions?" This study provides insights into the relationship between cognitive differences and unconscious boundary violations through an on-site experiment in specific contexts and with target groups. By utilizing artistic installations as intervention tools, we aim to find ways to help the public break away from self-centered cognitive perspectives and seek balance in social interactions. This approach explores the conflicts and integration of subjectivity and objectivity between individuals, offering new perspectives for analyzing interpersonal conflicts. © 2024 Copyright held by the owner/author(s).

Chinese calligraphy, a cherished aspect of Chinese and global culture, employs Chinese characters as its medium, while ink and brush serve as instrumental tools, resulting in a distinctive aesthetic allure. Calligraphy comprises intricate imagery that not only captures the abstract forms of characters but also conveys the essence of natural landscapes, thereby stimulating viewers’ imagination. This research aims to explore a methodology for materializing calligraphic imagery, by utilizing AI generative models to produce corresponding images based on the form, meaning, and contextual aspects of calligraphy. The generated result present an artistic style that seamlessly integrates Chinese calligraphy and Chinese painting. Further, the comparison between different style of generated result shows that Chinese painting has stronger generalization ability.