Recent generative image editing methods adopt layered representations to mitigate the entangled nature of raster images and improve controllability, typically relying on object-based segmentation. However, such strategies may fail to capture the structural and stylized properties of human-created images, such as anime illustrations. To solve this issue, we propose a workflow-aware structured layer decomposition framework tailored to the illustration production of anime artwork. Inspired by the creation pipeline of anime production, our method decomposes the illustration into semantically meaningful production layers, including line art, flat color, shadow, and highlight. To decouple all these layers, we introduce lightweight layer semantic embeddings to provide specific task guidance for each layer. Furthermore, a set of layer-wise losses is incorporated to supervise the training process of individual layers. To overcome the lack of ground-truth layered data, we construct a high-quality illustration dataset that simulated the standard anime production workflow. Experiments demonstrate that the accurate and visually coherent layer decompositions were achieved by using our method. We believe that the resulting layered representation further enables downstream tasks such as recoloring and embedding texture, supporting content creation, and illustration editing. Code is available at: https://github.com/zty0304/Anime-layer-decomposition
Archaeological pottery documentation traditionally requires a time-consuming manual process of converting pencil sketches into publication-ready inked drawings. I present PyPotteryInk, an open-source automated pipeline that transforms archaeological pottery sketches into standardised publication-ready drawings using a one-step diffusion model. Built on a modified img2img-turbo architecture, the system processes drawings in a single forward pass while preserving crucial morphological details and maintaining archaeologic documentation standards and analytical value. The model employs an efficient patch-based approach with dynamic overlap, enabling high-resolution output regardless of input drawing size. I demonstrate the effectiveness of the approach on a dataset of Italian protohistoric pottery drawings, where it successfully captures both fine details like decorative patterns and structural elements like vessel profiles or handling elements. Expert evaluation confirms that the generated drawings meet publication standards while significantly reducing processing time from hours to seconds per drawing. The model can be fine-tuned to adapt to different archaeological contexts with minimal training data, making it versatile across various pottery documentation styles. The pre-trained models, the Python library and comprehensive documentation are provided to facilitate adoption within the archaeological research community.
As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods primarily approach multimodal reasoning in a straightforward, text-centric manner, where both reasoning and answer derivation are conducted purely through text, with the only difference being the presence of multimodal input. As a result, these methods often encounter fundamental limitations in spatial reasoning tasks that demand precise geometric understanding and continuous spatial tracking-capabilities that humans achieve through mental visualization and manipulation. To address the limitations, we propose drawing to reason in space, a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space. By equipping models with basic drawing operations, including annotating bounding boxes and drawing auxiliary lines, we empower them to express and analyze spatial relationships through direct visual manipulation, meanwhile avoiding the performance ceiling imposed by specialized perception tools in previous tool-integrated reasoning approaches. To cultivate this capability, we develop a three-stage training framework: cold-start training with synthetic data to establish basic drawing abilities, reflective rejection sampling to enhance self-reflection behaviors, and reinforcement learning to directly optimize for target rewards. Extensive experiments demonstrate that our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks, involving maze navigation, static spatial reasoning, video-based reasoning, and multi-view-based reasoning tasks, with an average improvement of 18.4%.
The use of robotic technology has drastically increased in manufacturing in the 21st century. But by utilizing their sensory cues, humans still outperform machines, especially in the micro scale manufacturing, which requires high-precision robot manipulators. These sensory cues naturally compensate for high level of uncertainties that exist in the manufacturing environment. Uncertainties in performing manufacturing tasks may come from measurement noise, model inaccuracy, joint compliance (e.g., elasticity) etc. Although advanced metrology sensors and high-precision microprocessors, which are utilized in nowadays robots, have compensated for many structural and dynamic errors in robot positioning, but a well-designed control algorithm still works as a comparable and cheaper alternative to reduce uncertainties in automated manufacturing. Our work illustrates that a multi-robot control system can reduce various uncertainties to a great amount.
Анотація. У цій статті проведено теоретичний аналіз можливості використання рециркульованих бетонних конструкцій у складі бетонних сумішей. Дана проблема вимагає особливої уваги, адже на сьогодні в Україні накопичилось вже майже 12 млн тонн будівельного брухту, яке зберігається на тимчасових звалищах і створює негативні екологічні ризики. Зважаючи на це в нашій країні вже досягли розуміння, що залишки від зруйнованих будівель належать до матеріальних ресурсів, які можна використовувати у будівельній галузі при виробництві матеріалів. Мета – теоретичний аналіз особливостей використання рециркульованих бетонних конструкцій у складі бетонних сумішей. Методологія дослідження передбачає дослідження впливу залишків органіки, продуктів горіння, тощо у складі рециркульованого заповнювача на властивості бетонної суміші та бетону на її основі. Результати. Реалізація впровадження технологій з використанням рециркульованих бетонних конструкцій у складі бетонних сумішей дозволить підвищити ефективність використання таких матеріалів для будівництва та відновлення промислових комплексів хімічної, оборонної, сільськогосподарської та харчової галузей економіки, а також при спорудженні інфраструктурних та спеціальних об’єктів. Наукова новизна. Визначення процесів зменшення дефектності структури рециркульованого заповнювача та бетону на його основі в цілому, ретельного підбору в’яжучої речовини при проєктуванні складу бетонної суміші з огляду на підвищену дефектність такого заповнювача як продукту переробки зруйнованих бетонних конструкцій, а також з огляду на можливу наявність в його складі залишків органічних сполук та продуктів горіння. Практична значущість. Практична цінність цього дослідження полягає в його потенціалі для розвитку будівельної галузі, який відкриє можливість утилізації великотоннажних відходів бойових дій, а також дозволить розширити варіативність отримання бетонів різного призначення.
Iván Capdevila Castellanos, José Manuel López Ujaque
La ciudad de Viena es una de las primeras que ha regulado la preservación de ecosistemas urbanos existentes, hasta dotar de entidad jurídica a algunos lugares abandonados por el ser humano —donde la naturaleza ha emergido libremente—, garantizando así la coexistencia con las especies que allí habitan. Este artículo explicita cómo este logro está motivado por el entrelazamiento entre experiencias espontáneas, creativas y afirmativas en algunos de estos lugares —como la estación del Norte— y el concurso de arquitectura Europan. Dicho concurso introduce, primero, el soporte teórico que pone en valor estas experiencias para después acabar institucionalizando en sus nuevas ediciones los aprendizajes sucedidos en ellas. Así, este texto retrata en tres actos al concurso Europan y a Viena como instituciones y laboratorios —de ideas y de prácticas simpoiéticas, respectivamente— que se piensan y diseñan de manera recíproca.
We introduce SketcherX, a novel robotic system for personalized portrait drawing through interactive human-robot engagement. Unlike traditional robotic art systems that rely on analog printing techniques, SketcherX captures and processes facial images to produce vectorized drawings in a distinctive, human-like artistic style. The system comprises two 6-axis robotic arms : a face robot, which is equipped with a head-mounted camera and Large Language Model (LLM) for real-time interaction, and a drawing robot, utilizing a fine-tuned Stable Diffusion model, ControlNet, and Vision-Language models for dynamic, stylized drawing. Our contributions include the development of a custom Vector Low Rank Adaptation model (LoRA), enabling seamless adaptation to various artistic styles, and integrating a pair-wise fine-tuning approach to enhance stroke quality and stylistic accuracy. Experimental results demonstrate the system's ability to produce high-quality, personalized portraits within two minutes, highlighting its potential as a new paradigm in robotic creativity. This work advances the field of robotic art by positioning robots as active participants in the creative process, paving the way for future explorations in interactive, human-robot artistic collaboration.
Amit Sharma, Teodor-Dumitru Ene, Kishor Kunal
et al.
This paper presents a comparative analysis of total cost of ownership (TCO) and performance between domain-adapted large language models (LLM) and state-of-the-art (SoTA) LLMs , with a particular emphasis on tasks related to coding assistance for chip design. We examine the TCO and performance metrics of a domain-adaptive LLM, ChipNeMo, against two leading LLMs, Claude 3 Opus and ChatGPT-4 Turbo, to assess their efficacy in chip design coding generation. Through a detailed evaluation of the accuracy of the model, training methodologies, and operational expenditures, this study aims to provide stakeholders with critical information to select the most economically viable and performance-efficient solutions for their specific needs. Our results underscore the benefits of employing domain-adapted models, such as ChipNeMo, that demonstrate improved performance at significantly reduced costs compared to their general-purpose counterparts. In particular, we reveal the potential of domain-adapted LLMs to decrease TCO by approximately 90%-95%, with the cost advantages becoming increasingly evident as the deployment scale expands. With expansion of deployment, the cost benefits of ChipNeMo become more pronounced, making domain-adaptive LLMs an attractive option for organizations with substantial coding needs supported by LLMs
This article aims to reassess the theoretical contribution of the group of psychopedagogues who, after Töpffer and his Essai de physiognomonie, would represent the second generation of theorists of graphic literature. The origins of this group can be traced back to a unique experiment which, between 1892 and 1910, invited boys and girls from all five continents to adapt into drawings the poem Hanns Guck-in-die-Luft, originally published in Dr. Heinrich Hoffmann’s book Struwwelpeter (1845). In this article, we focus on this first experiment, first proposed by the American Earl Barnes and—following Aby Warburg’s Hopi journey—pursued by Karl Lamprecht and Siegfried Levinstein in Germany.
Drawing. Design. Illustration, Literature (General)
The Divertor Tokamak Test (DTT) is a new experimental facility whose construction is starting in Frascati, Rome, Italy; its main goals are improving the understanding of plasma-wall interactions and supporting the development of ITER and DEMO. DTT will be equipped with a Neutral Beam Injector (NBI) based on negative deuterium ions, designed to inject 10 MW of power to the tokamak. A fundamental system for the good operations of the DTT NBI will be its Gas injection and Vacuum System (GVS). Indeed, the efficiency of the entire NBI strongly depends on the good performance of its GVS. The GVS for DTT NBI will be composed of two systems working in parallel: a grounded section connected to the main vacuum vessel, and a high voltage part connected to the ion source vessel and working at -510 kV voltage. The grounded part will feature a fore vacuum system (given by screw and roots pumps) plus a high vacuum system based on turbo-molecular pumps located on the side walls of the vessel and Non-Evaporable Getter (NEG) pumps located inside the vessel on the upper and lower surfaces. On the other hand, the high voltage part will feature a fore vacuum system (given by two compact screw pumps mounted on the external surface for the ion source vessel) plus a high vacuum system based on turbo-molecular pumps also located on the sidewalls of the ion source vessel. A dedicated deuterium gas injection will feed the process gas to the ion source and the neutralizer. This paper gives a description of the conceptual design of the GVS for DTT NBI, and of the procedure followed to optimize this system considering the operational requirements and the other constraints of the DTT NBI.
AbstractArt, architecture and urbanism practice Metis was founded by Professor Mark Dorrian, Forbes Chair in Architecture, and Adrian Hawker, MArch Programme Director, at the University of Edinburgh. Metis has a long history of proposing extraordinary architectures, whether in building form or as interventions in existing spaces. Architect and academic Peter Salter uses the lens of Francis Bacon's painting to view their creative tactics.
This paper considers the challenge of designing football group draw mechanisms which have the uniform distribution over all valid draw assignments, but are also entertaining, practical, and transparent. We explain how to simulate the FIFA Sequential Draw method, to compute the non-uniformity of its draws by comparison to a uniform Rejection Sampler. We then propose two practical methods of achieving the uniform distribution while still using balls and bowls in a way which is suitable for a televised draw. The solutions can also be tried interactively.
Yichao Liang, Joshua B. Tenenbaum, Tuan Anh Le
et al.
Learning general-purpose representations from perceptual inputs is a hallmark of human intelligence. For example, people can write out numbers or characters, or even draw doodles, by characterizing these tasks as different instantiations of the same generic underlying process -- compositional arrangements of different forms of pen strokes. Crucially, learning to do one task, say writing, implies reasonable competence at another, say drawing, on account of this shared process. We present Drawing out of Distribution (DooD), a neuro-symbolic generative model of stroke-based drawing that can learn such general-purpose representations. In contrast to prior work, DooD operates directly on images, requires no supervision or expensive test-time inference, and performs unsupervised amortised inference with a symbolic stroke model that better enables both interpretability and generalization. We evaluate DooD on its ability to generalise across both data and tasks. We first perform zero-shot transfer from one dataset (e.g. MNIST) to another (e.g. Quickdraw), across five different datasets, and show that DooD clearly outperforms different baselines. An analysis of the learnt representations further highlights the benefits of adopting a symbolic stroke model. We then adopt a subset of the Omniglot challenge tasks, and evaluate its ability to generate new exemplars (both unconditionally and conditionally), and perform one-shot classification, showing that DooD matches the state of the art. Taken together, we demonstrate that DooD does indeed capture general-purpose representations across both data and task, and takes a further step towards building general and robust concept-learning systems.
Jonathan Klawitter, Felix Klesen, Moritz Niederer
et al.
We consider the problem of drawing multiple gene trees inside a single species tree in order to visualize multispecies coalescent trees. Specifically, the drawing of the species tree fills a rectangle in which each of its edges is represented by a smaller rectangle, and the gene trees are drawn as rectangular cladograms (that is, orthogonally and downward, with one bend per edge) inside the drawing of the species tree. As an alternative, we also consider a style where the widths of the edges of the species tree are proportional to given effective population sizes. In order to obtain readable visualizations, our aim is to minimize the number of crossings between edges of the gene trees in such drawings. We show that planar instances can be recognized in linear time and that the general problem is NP-hard. Therefore, we introduce two heuristics and give an integer linear programming (ILP) formulation that provides us with exact solutions in exponential time. We use the ILP to measure the quality of the heuristics on real-world instances. The heuristics yield surprisingly good solutions, and the ILP runs surprisingly fast.
This paper analyses the advantages of using a stock spring selection tool that manages the uncertainty of designer requirements. Firstly, the manual search and its main drawbacks are described. Then a computer assisted stock spring selection tool is presented which performs all necessary calculations to extract the most suitable spring from within a database. The algorithm analyses data set with interval values using both multi-criteria analysis and fuzzy logic. Two examples, comparing manual and assisted search, are presented. They show not only that the results are significantly better using the assisted search but it helps designers to detail easily and precisely their specifications and thus increase design process flexibility.
Cultivating somatic sensibilities involves heightening our sensory appreciation as a path to devise meaningful multisensory experiences in interaction design. Immersed in an increasingly digitalized and data-centric world, research projects centering on the sensory, embodied, and material reality of our experience, might start losing momentum. On the other hand, the pandemic has also transferred our labs from the public nature of our workshop room to the intimacy of our homes, bringing unexpected benefits and challenges. The articles included in this issue center on the sensory and material experiences of designers, who work with design methods that foreground somatic modes of inquiry and show how these changes could open a door for new opportunities to emphasize the importance of embodied and somatic practices in design and HCI.
The extraordinary endeavour of William Kentridge is the testimony of an intense, many years and productive work that relates to the dynamics of a complexity located in the cultural and political context of belonging, so being able to interpret it means being confronted with a visual universe capable of reflecting a precise personal need, in privileging the medium of drawing and in the freedom to hybridize it with cinema and theatre (read more).