[2507.21288] Learning Simulatable Models of Cloth with Spatially-varying Constitutive Properties

Published

1 month ago

August 1, 2025

Guanxiong Chen, Shashwat Suri, Yuhao Wu, Etienne Voulga, David I. W. Levin, Dinesh K. Pai

[Submitted on 28 Jul 2025 (v1), last revised 30 Jul 2025 (this version, v2)]

View a PDF of the paper titled Learning Simulatable Models of Cloth with Spatially-varying Constitutive Properties, by Guanxiong Chen and 5 other authors

View PDF
HTML (experimental)

Abstract:Materials used in real clothing exhibit remarkable complexity and spatial variation due to common processes such as stitching, hemming, dyeing, printing, padding, and bonding. Simulating these materials, for instance using finite element methods, is often computationally demanding and slow. Worse, such methods can suffer from numerical artifacts called “membrane locking” that makes cloth appear artificially stiff. Here we propose a general framework, called Mass-Spring Net, for learning a simple yet efficient surrogate model that captures the effects of these complex materials using only motion observations. The cloth is discretized into a mass-spring network with unknown material parameters that are learned directly from the motion data, using a novel force-and-impulse loss function. Our approach demonstrates the ability to accurately model spatially varying material properties from a variety of data sources, and immunity to membrane locking which plagues FEM-based simulations. Compared to graph-based networks and neural ODE-based architectures, our method achieves significantly faster training times, higher reconstruction accuracy, and improved generalization to novel dynamic scenarios.

Submission history

From: Guanxiong Chen [view email]
[v1]
Mon, 28 Jul 2025 19:21:04 UTC (11,629 KB)
[v2]
Wed, 30 Jul 2025 18:05:08 UTC (11,629 KB)

Source link

Artificial Intelligence Cheating | Nation

Published

54 minutes ago

September 12, 2025

Jae C. Hong - AP

Artificial Intelligence Cheating | Nation | hjnews.com

We recognize you are attempting to access this website from a country belonging to the European Economic Area (EEA) including the EU which
enforces the General Data Protection Regulation (GDPR) and therefore access cannot be granted at this time.

For any issues, call 435-752-2121.

Source link

AI Research

Artificial Intelligence in Healthcare Market : A Study of

Published

1 hour ago

September 12, 2025

The Editors

Global Artificial Intelligence in Healthcare Market size was valued at USD 27.07 Bn in 2024 and is expected to reach USD 347.28 Bn by 2032, at a CAGR of 37.57%

Artificial Intelligence (AI) in healthcare is reshaping the industry by enabling faster diagnosis, personalized treatment, and enhanced operational efficiency. AI-driven tools such as predictive analytics, natural language processing, and medical imaging analysis are empowering physicians with deeper insights and decision support, reducing human error and improving patient outcomes. Moreover, AI is revolutionizing drug discovery, clinical trial optimization, and remote patient monitoring, making healthcare more proactive and accessible in both developed and emerging markets.

The adoption of AI in healthcare is also being accelerated by the rising demand for telemedicine, wearable health devices, and real-time data-driven solutions. From virtual health assistants to robotic surgery, AI is driving innovation across patient care and hospital management. However, challenges such as data privacy, ethical considerations, and regulatory frameworks remain crucial in ensuring responsible deployment. As AI continues to integrate with IoT, cloud, and big data platforms, it is set to create a connected healthcare ecosystem that prioritizes precision medicine and patient-centric solutions.

Get a sample of the report https://www.maximizemarketresearch.com/request-sample/21261/

Major companies profiled in the market report include

BP Target Neutral . JPMorgan Chase & Co. . Gold Standard Carbon Clear . South Pole Group . 3Degrees . Shell. EcoAct.

Research objectives:

The latest research report has been formulated using industry-verified data. It provides a detailed understanding of the leading manufacturers and suppliers engaged in this market, their pricing analysis, product offerings, gross revenue, sales network & distribution channels, profit margins, and financial standing. The report’s insightful data is intended to enlighten the readers interested in this business sector about the lucrative growth opportunities in the Artificial Intelligence in Healthcare market.

Get access to the full description of the report @ https://www.maximizemarketresearch.com/market-report/global-artificial-intelligence-ai-healthcare-market/21261/

It has segmented the global Artificial Intelligence in Healthcare market

by Offering

Hardware

Software

Services

by Technology

Machine Learning

Natural Language Processing

Context-Aware Computing

Computer Vision

Key Objectives of the Global Artificial Intelligence in Healthcare Market Report:

The report conducts a comparative assessment of the leading market players participating in the globalArtificial Intelligence in Healthcare

The report marks the notable developments that have recently taken place in the Artificial Intelligence in Healthcare industry

It details on the strategic initiatives undertaken by the market competitors for business expansion.

It closely examines the micro- and macro-economic growth indicators, as well as the essential elements of theArtificial Intelligence in Healthcaremarket value chain.

The repot further jots down the major growth prospects for the emerging market players in the leading regions of the market

Explore More Related Report @

Engineering, Procurement, and Construction Management (EPCM) Market https://www.maximizemarketresearch.com/market-report/engineering-procurement-and-construction-management-epcm-market/73131/

Global Turbomolecular Pumps Market

https://www.maximizemarketresearch.com/market-report/global-turbomolecular-pumps-market/20730/

Contact Maximize Market Research:

3rd Floor, Navale IT Park, Phase 2

Pune Bangalore Highway, Narhe,

Pune, Maharashtra 411041, India

sales@maximizemarketresearch.com

+91 96071 95908, +91 9607365656

About Maximize Market Research:

Maximize Market Research is a multifaceted market research and consulting company with professionals from several industries. Some of the industries we cover include medical devices, pharmaceutical manufacturers, science and engineering, electronic components, industrial equipment, technology and communication, cars and automobiles, chemical products and substances, general merchandise, beverages, personal care, and automated systems. To mention a few, we provide market-verified industry estimations, technical trend analysis, crucial market research, strategic advice, competition analysis, production and demand analysis, and client impact studies

This release was published on openPR.

Source link

AI Research

A Unified Model for Robot Interaction, Reasoning and Planning

Published

3 hours ago

September 12, 2025

Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li

[Submitted on 1 Sep 2025 (v1), last revised 11 Sep 2025 (this version, v2)]

View a PDF of the paper titled Robix: A Unified Model for Robot Interaction, Reasoning and Planning, by Huang Fang and 8 other authors

View PDF

Abstract:We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.