Jayanaka L. Dantanarayana, Savini Kashmira, Thakee Nathees
et al.
AI-Integrated programming is emerging as a foundational paradigm for building intelligent systems with large language models (LLMs). Recent approaches such as Meaning Typed Programming (MTP) automate prompt generation by leveraging the semantics already present in code. However, many real-world applications depend on contextual cues, developer intent, and domain-specific reasoning that extend beyond what static code semantics alone can express. To address this limitation, we introduce Semantic Engineering, a lightweight method for enriching program semantics so that LLM-based systems can more accurately reflect developer intent without requiring full manual prompt design. We present Semantic Context Annotations (SemTexts), a language-level mechanism that allows developers to embed natural-language context directly into program constructs. Integrated into the Jac programming language, Semantic Engineering extends MTP to incorporate these enriched semantics during prompt generation. We further introduce a benchmark suite designed to reflect realistic AI-Integrated application scenarios. Our evaluation shows that Semantic Engineering substantially improves prompt fidelity, achieving performance comparable to Prompt Engineering while requiring significantly less developer effort.
Lorenzo De Rebotti, Emanuele Giacomini, Giorgio Grisetti
et al.
Efficient and scalable 3D surface reconstruction from range data remains a core challenge in computer graphics and vision, particularly in real-time and resource-constrained scenarios. Traditional volumetric methods based on fixed-resolution voxel grids or hierarchical structures like octrees often suffer from memory inefficiency, computational overhead, and a lack of GPU support. We propose a novel variance-adaptive, multi-resolution voxel grid that dynamically adjusts voxel size based on the local variance of signed distance field (SDF) observations. Unlike prior multi-resolution approaches that rely on recursive octree structures, our method leverages a flat spatial hash table to store all voxel blocks, supporting constant-time access and full GPU parallelism. This design enables high memory efficiency and real-time scalability. We further demonstrate how our representation supports GPU-accelerated rendering through a parallel quad-tree structure for Gaussian Splatting, enabling effective control over splat density. Our open-source CUDA/C++ implementation achieves up to 13x speedup and 4x lower memory usage compared to fixed-resolution baselines, while maintaining on par results in terms of reconstruction accuracy, offering a practical and extensible solution for high-performance 3D reconstruction.
We introduce the \textit{crossing profile} of a drawing of a graph. This is a sequence of integers whose $(k+1)^{\text{th}}$ entry counts the number of edges in the drawing which are involved in exactly $k$ crossings. The first and second entries of this sequence (which count uncrossed edges and edges with one crossing, respectively) have been studied by multiple authors. However, to the best of our knowledge, we are the first to consider the entire sequence. Most of our results concern crossing profiles of rectilinear drawings of the complete graph $K_n$. We show that for any $k\leq (n-2)^2/4$ there is such a drawing for which the $k^{\text{th}}$ entry of the crossing profile is of magnitude $Ω(n)$. On the other hand, we prove that for any $k \geq 1$ and any sufficiently large $n$, the $k^{\text{th}}$ entry can also be made to be $0$. As our main result, we essentially characterize the asymptotic behavior of both the maximum and minimum values that the sum of the first $k$ entries of the crossing profile might achieve. Our proofs are elementary and rely mostly on geometric constructions and classical results from discrete geometry and geometric graph theory.
In this paper, we propose a novel approach for air drawing that uses image processing techniques to draw on the screen by moving fingers in the air. This approach benefits a wide range of applications such as sign language, in-air drawing, and 'writing' in the air as a new way of input. The approach starts with preparing ROI (Region of Interest) background images by taking a running average in initial camera frames and later subtracting it from the live camera frames to get a binary mask image. We calculate the pointer's position as the top of the contour on the binary image. When drawing a circle on the canvas in that position, it simulates the drawing. Furthermore, we combine the pre-trained Tesseract model for OCR purposes. To address the false contours, we perform hand detection based on the haar cascade before performing the background subtraction. In an experimental setup, we achieved a latency of only 100ms in air drawing. The code used to this research are available in GitHub as https://github.com/q-viper/Contour-Based-Writing
Inverse graphics -- the task of inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics. Successfully disentangling an image into its constituent elements, such as the shape, color, and material properties of the objects of the 3D scene that produced it, requires a comprehensive understanding of the environment. This complexity limits the ability of existing carefully engineered approaches to generalize across domains. Inspired by the zero-shot ability of large language models (LLMs) to generalize to novel contexts, we investigate the possibility of leveraging the broad world knowledge encoded in such models to solve inverse-graphics problems. To this end, we propose the Inverse-Graphics Large Language Model (IG-LLM), an inverse-graphics framework centered around an LLM, that autoregressively decodes a visual embedding into a structured, compositional 3D-scene representation. We incorporate a frozen pre-trained visual encoder and a continuous numeric head to enable end-to-end training. Through our investigation, we demonstrate the potential of LLMs to facilitate inverse graphics through next-token prediction, without the application of image-space supervision. Our analysis enables new possibilities for precise spatial reasoning about images that exploit the visual knowledge of LLMs. We release our code and data at https://ig-llm.is.tue.mpg.de/ to ensure the reproducibility of our investigation and to facilitate future research.
Large Language Models (LLMs) have significantly advanced software engineering (SE) tasks, with prompt engineering techniques enhancing their performance in code-related areas. However, the rapid development of foundational LLMs such as the non-reasoning model GPT-4o and the reasoning model o1 raises questions about the continued effectiveness of these prompt engineering techniques. This paper presents an extensive empirical study that reevaluates various prompt engineering techniques within the context of these advanced LLMs. Focusing on three representative SE tasks, i.e., code generation, code translation, and code summarization, we assess whether prompt engineering techniques still yield improvements with advanced models, the actual effectiveness of reasoning models compared to non-reasoning models, and whether the benefits of using these advanced models justify their increased costs. Our findings reveal that prompt engineering techniques developed for earlier LLMs may provide diminished benefits or even hinder performance when applied to advanced models. In reasoning LLMs, the ability of sophisticated built-in reasoning reduces the impact of complex prompts, sometimes making simple zero-shot prompting more effective. Furthermore, while reasoning models outperform non-reasoning models in tasks requiring complex reasoning, they offer minimal advantages in tasks that do not need reasoning and may incur unnecessary costs. Based on our study, we provide practical guidance for practitioners on selecting appropriate prompt engineering techniques and foundational LLMs, considering factors such as task requirements, operational costs, and environmental impact. Our work contributes to a deeper understanding of effectively harnessing advanced LLMs in SE tasks, informing future research and application development.
Active Learning (AL) is a well-known teaching method in engineering because it allows to foster learning and critical thinking of the students by employing debate, hands-on activities, and experimentation. However, most educational results of this instructional method have been achieved in face-to-face educational settings and less has been said about how to promote AL and experimentation for online engineering education. Then, the main aim of this study was to create an AL methodology to learn electronics, physical computing (PhyC), programming, and basic robotics in engineering through hands-on activities and active experimentation in online environments. N=56 students of two engineering programs (Technology in Electronics and Industrial Engineering) participated in the methodology that was conceived using the guidelines of the Integrated Course Design Model (ICDM) and in some courses combining mobile and online learning with an Android app. The methodology gathered three main components: (1) In-home laboratories performed through low-cost hardware devices, (2) Student-created videos and blogs to evidence the development of skills, and (3) Teacher support and feedback. Data in the courses were collected through surveys, evaluation rubrics, semi-structured interviews, and students grades and were analyzed through a mixed approach. The outcomes indicate a good perception of the PhyC and programming activities by the students and suggest that these influence motivation, self-efficacy, reduction of anxiety, and improvement of academic performance in the courses. The methodology and previous results can be useful for researchers and practitioners interested in developing AL methodologies or strategies in engineering with online, mobile, or blended learning modalities.
Online research platforms, such as Prolific, offer rapid access to diverse participant pools but also pose unique challenges in participant qualification and skill verification. Previous studies reported mixed outcomes and challenges in leveraging online platforms for the recruitment of qualified software engineers. Drawing from our experience in conducting three different studies using Prolific, we propose best practices for recruiting and screening participants to enhance the quality and relevance of both qualitative and quantitative software engineering (SE) research samples. We propose refined best practices for recruitment in SE research on Prolific. (1) Iterative and controlled prescreening, enabling focused and manageable assessment of submissions (2) task-oriented and targeted questions that assess technical skills, knowledge of basic SE concepts, and professional engagement. (3) AI detection to verify the authenticity of free-text responses. (4) Qualitative and manual assessment of responses, ensuring authenticity and relevance in participant answers (5) Additional layers of prescreening are necessary when necessary to collect data relevant to the topic of the study. (6) Fair or generous compensation post-qualification to incentivize genuine participation. By sharing our experiences and lessons learned, we contribute to the development of effective and rigorous methods for SE empirical research. particularly the ongoing effort to establish guidelines to ensure reliable data collection. These practices have the potential to transferability to other participant recruitment platforms.
In this paper, we investigate the problem of automatically controllable artistic character line drawing generation from photographs by proposing a Vector Flow Aware and Line Controllable Image-to-Image Translation architecture, which can be viewed as an appealing intersection between Artificial Intelligence and Arts. Specifically, we first present an Image-to-Flow network (I2FNet) to efficiently and robustly create the vector flow field in a learning-based manner, which can provide a direction guide for drawing lines. Then, we introduce our well-designed Double Flow Generator (DFG) framework to fuse features from learned vector flow and input image flow guaranteeing the spatial coherence of lines. Meanwhile, in order to allow for controllable character line drawing generation, we integrate a Line Control Matrix (LCM) into DFG and train a Line Control Regressor (LCR) to synthesize drawings with different styles by elaborately controlling the level of details, such as thickness, smoothness, and continuity, of lines. Finally, we design a Fourier Transformation Loss to further constrain the character line generation from the frequency domain view of the point. Quantitative and qualitative experiments demonstrate that our approach can obtain superior performance in producing high-resolution character line-drawing images with perceptually realistic characteristics.
Quantum software engineering (QSE) is receiving increasing attention, as evidenced by increasing publications on topics, e.g., quantum software modeling, testing, and debugging. However, in the literature, quantum software requirements engineering (QSRE) is still a software engineering area that is relatively less investigated. To this end, in this paper, we provide an initial set of thoughts about how requirements engineering for quantum software might differ from that for classical software after making an effort to map classical requirements classifications (e.g., functional and extra-functional requirements) into the context of quantum software. Moreover, we provide discussions on various aspects of QSRE that deserve attention from the quantum software engineering community.
Olga Movilla Miangolarra, Amirhossein Taghvaei, Yongxin Chen
et al.
The purpose of this work is to present the concept of an autonomous Stirling-like engine powered by anisotropy of thermodynamic fluctuations. Specifically, simultaneous contact of a thermodynamic system with two heat baths along coupled degrees of freedom generates torque and circulatory currents -- an arrangement referred to as a Brownian gyrator. The embodiment that constitutes the engine includes an inertial wheel to sustain rotary motion and average out the generated fluctuating torque, ultimately delivering power to an external load. We detail an electrical model for such an engine that consists of two resistors in different temperatures and three reactive elements in the form of variable capacitors. The resistors generate Johnson-Nyquist current fluctuations that power the engine, while the capacitors generate driving forces via a coupling of their dielectric material with the inertial wheel. A proof-of-concept is established via stability analysis to ensure the existence of a stable periodic orbit generating sustained power output. We conclude by drawing a connection to the dynamics of a damped pendulum with constant torque and to those of a macroscopic Stirling engine. The sought insights aim at nano-engines and biological processes that are similarly powered by anisotropy in temperature and chemical potentials.
The paper presents a new efficient and robust method for rare event probability estimation for computational models of an engineering product or a process returning categorical information only, for example, either success or failure. For such models, most of the methods designed for the estimation of failure probability, which use the numerical value of the outcome to compute gradients or to estimate the proximity to the failure surface, cannot be applied. Even if the performance function provides more than just binary output, the state of the system may be a non-smooth or even a discontinuous function defined in the domain of continuous input variables. In these cases, the classical gradient-based methods usually fail. We propose a simple yet efficient algorithm, which performs a sequential adaptive selection of points from the input domain of random variables to extend and refine a simple distance-based surrogate model. Two different tasks can be accomplished at any stage of sequential sampling: (i) estimation of the failure probability, and (ii) selection of the best possible candidate for the subsequent model evaluation if further improvement is necessary. The proposed criterion for selecting the next point for model evaluation maximizes the expected probability classified by using the candidate. Therefore, the perfect balance between global exploration and local exploitation is maintained automatically. The method can estimate the probabilities of multiple failure types. Moreover, when the numerical value of model evaluation can be used to build a smooth surrogate, the algorithm can accommodate this information to increase the accuracy of the estimated probabilities. Lastly, we define a new simple yet general geometrical measure of the global sensitivity of the rare-event probability to individual variables, which is obtained as a by-product of the proposed algorithm.
This paper represents preliminary work in identifying the foundation for the discipline of Software Engineering and discovering the links between the domains of Software Engineering and Information Technology (IT). Our research utilized IEEE Transactions on Software Engineering (IEEE-TSE), ACM Transactions on Software Engineering and Methodology (ACM-TOSEM), Automated Software Engineering (ASE), the International Conference on Software Engineering(ICSE), and other related journal publication in the software engineering domain to address our research questions. We explored existing frameworks and described the need for software engineering as an academic discipline. We went further to clarify the distinction difference between Software Engineering and Computer Science. Through this efforts we contribute to an understanding of how evidence from IT research can be used to improve Software Engineering as a discipline.
In industry as well as education as well as academics we see a growing need for knowledge on how to apply machine learning in software applications. With the educational programme ICT & AI at Fontys UAS we had to find an answer to the question: "How should we educate software engineers to become AI engineers?" This paper describes our educational programme, the open source tools we use, and the literature it is based on. After three years of experience, we present our lessons learned for both educational institutions and software engineers in practice.