We present an integrated machine learning framework that transforms how manufacturing cost is estimated from 2D engineering drawings. Unlike traditional quotation workflows that require labor-intensive process planning, our approach about 200 geometric and statistical descriptors directly from 13,684 DWG drawings of automotive suspension and steering parts spanning 24 product groups. Gradient-boosted decision tree models (XGBoost, CatBoost, LightGBM) trained on these features achieve nearly 10% mean absolute percentage error across groups, demonstrating robust scalability beyond part-specific heuristics. By coupling cost prediction with explainability tools such as SHAP, the framework identifies geometric design drivers including rotated dimension maxima, arc statistics and divergence metrics, offering actionable insights for cost-aware design. This end-to-end CAD-to-cost pipeline shortens quotation lead times, ensures consistent and transparent cost assessments across part families and provides a deployable pathway toward real-time, ERP-integrated decision support in Industry 4.0 manufacturing environments.

We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of 14 open-source LMMs as well as the proprietary GPT-4V(ision) and Gemini highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V and Gemini Ultra only achieve accuracies of 56% and 59% respectively, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence.

Studies on manufacturing cost prediction based on deep learning have begun in recent years, but the cost prediction rationale cannot be explained because the models are still used as a black box. This study aims to propose a manufacturing cost prediction process for 3D computer-aided design (CAD) models using explainable artificial intelligence. The proposed process can visualize the machining features of the 3D CAD model that are influencing the increase in manufacturing costs. The proposed process consists of (1) data collection and pre-processing, (2) 3D deep learning architecture exploration, and (3) visualization to explain the prediction results. The proposed deep learning model shows high predictability of manufacturing cost for the computer numerical control (CNC) machined parts. In particular, using 3D gradient-weighted class activation mapping proves that the proposed model not only can detect the CNC machining features but also can differentiate the machining difficulty for the same feature. Using the proposed process, we can provide a design guidance to engineering designers in reducing manufacturing costs during the conceptual design phase. We can also provide real-time quotations and redesign proposals to online manufacturing platform customers.

The following paper, "Simba: Scaling Deep-Learning Inference with Chiplet-Based Architecture," by Shao et al. presents a scalable deep learning accelerator architecture that tackles issues ranging from chip integration technology to workload partitioning and non-uniform latency effects on deep neural network performance. Through a hardware prototype, they present a timely study of cross-layer issues that will inform next-generation deep learning hardware, software, and neural network architectures. Chip vendors face significant challenges with the continued slowing of Moore's Law causing the time between new technology nodes to increase, sky-rocketing manufacturing costs for silicon, and the end of Dennard scaling. In the absence of device scaling, domain specialization provides an opportunity for architects to deliver more performance and greater energy efficiency. However, domain specialization is an expensive proposition for chip manufacturers.

Today, chips can be manufactured with a wide range of semiconductor IP, ranging from central processing (CPUs) and graphics processing units (GPUs) to power management and other analog devices, arranged on a single slab of silicon like articles on the front page of a newspaper. Not only are SoCs taking longer and longer to design, adding to overall engineering costs, but the manufacturing costs are also mounting. Testing that the hardware and software are functioning correctly is also growing more expensive. Trying to change that is UltraSoC, which has announced a new debugging tool that can evaluate complete SoCs rather than just individual cores. UltraSoC said that the new UltraDevelop tool can trim development costs, save time and even enhance software running on multicore, multithreaded chips using a number of different architectures.

SHANGHAI – U.S. President Donald Trump often tweets from his iPhone about pressuring China to address its $375 billion trade surplus with the United States. But a closer look at the Apple smartphone reveals how the headline figure is distorted. The big trade imbalance -- at the heart of a potential trade war, with Trump expected to impose tariffs on Chinese imports this week -- exists in large part because of electrical goods and tech, the biggest U.S. import item from China. Apple Inc.'s iPhone, however, illustrates how a big portion of that imbalance is due to imports of American-branded products -- many of which use global suppliers for parts but are put together in China and shipped around the world. Take a look at the iPhone X. IHS Markit estimates its components cost a total of $370.25.

US President Donald Trump often tweets from his iPhone about pressuring China to address its $375bn trade surplus with the United States. But a closer look at the Apple smartphone reveals how the headline figure is distorted. The big trade imbalance - at the heart of a potential trade war, with Trump expected to impose tariffs on Chinese imports this week - exists in large part because of electrical goods and tech, the biggest US import item from China. Apple Inc's iPhone, however, illustrates how a big portion of that imbalance is due to imports of American-branded products - many of which use global suppliers for parts, but are put together in China and shipped around the world. Take a look at the iPhone X. IHS Markit estimates its components cost a total of $370.25.

Killer robots of the future will need more powerful chips to allow them to process vast amounts of data. The US military has now announced it is investing $900 million (£665 million) on advanced materials and technologies to make these processors a reality. It hope its efforts will enable the 50 years of growth in micro-processing power to continue over the coming century. This will allow for the creation of advanced AI systems, ranging from killing machines to cars, planes and other autonomous technology. Advanced AI systems of the future will need more powerful chips to allow them to process vast amounts of data.

Technology companies like to cite computer scientist Alan Kay's famous quote that "People who are really serious about software should make their own hardware." These days, Google's motto could be, "People who are really serious about AI should make their own hardware--and sell it at a premium." That appears to be the strategy behind the Pixel, the first Google-designed smartphone, which was released on October 20. Prior to the Pixel, Google offered a series of Nexus-branded smartphones that it developed with smartphone makers and sold online, at prices that essentially covered its costs. But while the Nexus phones supported the company's primary business of online advertising by getting more people to use Google services, the Pixel seems to be geared toward monetizing Google's AI initiatives, specifically its efforts to build a virtual assistant that will act as a user's "own personal Google" and provide a consistent experience across an entire line of Google-designed gadgets.