US President Donald Trump has announced that he will allow AI chip giant Nvidia to sell its advanced H200 chips to approved customers in China. We will protect National Security, create American Jobs, and keep America's lead in AI, Trump said on social media on Monday. The decision will apply to other US chip companies like AMD and comes after extensive lobbying by Nvidia boss Jensen Huang, who visited Washington last week to drum up support. Nvidia - both the world's leading chip firm and most valuable company - has found itself at the centre of a geopolitical tug-of-war between the US and China in recent months, and had been banned from selling its most advanced chips to Beijing. Trump reversed the chip-selling ban in July, but demanded that Nvidia pay 15% of its Chinese revenues to the US government. Beijing then reportedly ordered its tech companies to stop buying Nvidia chips manufactured for use in the Chinese market.

Cultural infrastructures, such as libraries, museums, theaters, and galleries, support learning, civic life, health, and local economies, yet access is uneven across cities. We present a novel, scalable, and open-data framework to measure spatial equity in cultural access. We map cultural infrastructures and compute a metric called Cultural Infrastructure Accessibility Score (CIAS) using exponential distance decay at fine spatial resolution, then aggregate the score per capita and integrate socio-demographic indicators. Interpretable tree-ensemble models with SHapley Additive exPlanation (SHAP) are used to explain associations between accessibility, income, density, and tract-level racial/ethnic composition. Results show a pronounced core-periphery gradient, where non-library cultural infrastructures cluster near urban cores, while libraries track density and provide broader coverage. Non-library accessibility is modestly higher in higher-income tracts, and library accessibility is slightly higher in denser, lower-income areas.

Abstract--Time series are high-dimensional and complex data objects, making their efficient search and indexing a longstanding challenge in data mining. Building on a recently introduced similarity measure, namely Multiscale Dubuc Distance (MDD), this paper investigates its comparative strengths and limitations relative to the widely used Dynamic Time Warping (DTW). MDD is novel in two key ways: it evaluates time series similarity across multiple temporal scales and avoids point-to-point alignment. We demonstrate that in many scenarios where MDD outperforms DTW, the gains are substantial, and we provide a detailed analysis of the specific performance gaps it addresses. We provide simulations, in addition to the 95 datasets from the UCR archive, to test our hypotheses. Finally, we apply both methods to a challenging real-world classification task and show that MDD yields a significant improvement over DTW, underscoring its practical utility. Time series, or more generally, ordered high-dimensional data types, have become increasingly prevalent with the rise of powerful computational tools and machine learning techniques. In this study, we adopt the term time series as an umbrella label for all such sequential data. A central challenge in analyzing time series lies in defining and measuring similarity. Similarity is inherently subjective, shaped by the specific goals and nuances of a given application. The existing literature has produced a rich landscape of similarity measures, each tailored to specific assumptions and use cases.

Composite optimization problems involve minimizing the composition of a smooth map with a convex function. Such objectives arise in numerous data science and signal processing applications, including phase retrieval, blind deconvolution, and collaborative filtering. The subgradient method achieves local linear convergence when the composite loss is well-conditioned. However, if the smooth map is, in a certain sense, ill-conditioned or overparameterized, the subgradient method exhibits much slower sublinear convergence even when the convex function is well-conditioned. To overcome this limitation, we introduce a Levenberg-Morrison-Marquardt subgradient method that converges linearly under mild regularity conditions at a rate determined solely by the convex function. Further, we demonstrate that these regularity conditions hold for several problems of practical interest, including square-variable formulations, matrix sensing, and tensor factorization. Numerical experiments illustrate the benefits of our method.

Workshop version accepted at KDD 2025 (AI4SupplyChain). Connecting an ever-expanding catalogue of products with suitable manufacturers and suppliers is critical for resilient, efficient global supply chains, yet traditional methods struggle to capture complex capabilities, certifications, geographic constraints, and rich multimodal data of real-world manufacturer profiles. To address these gaps, we introduce PMGraph, a public benchmark of bipartite and heterogeneous multimodal supply-chain graphs linking 8,888 manufacturers, over 70k products, more than 110k manufacturer-product edges, and over 29k product images. Building on this benchmark, we propose the Cascade Multimodal Attributed Graph C-MAG, a two-stage architecture that first aligns and aggregates textual and visual attributes into intermediate group embeddings, then propagates them through a manufacturer-product hetero-graph via multiscale message passing to enhance link prediction accuracy. C-MAG also provides practical guidelines for modality-aware fusion, preserving predictive performance in noisy, real-world settings.

--Understanding human motion is of critical importance for health monitoring and control of assistive robots, yet many human kinematic variables cannot be directly or accurately measured by wearable sensors. In recent years, invariant extended Kalman filtering (InEKF) has shown a great potential in nonlinear state estimation, but its applications to human poses new challenges, including imperfect placement of wearable sensors and inaccurate measurement models. T o address these challenges, this paper proposes an augmented InEKF design which considers the misalignment of the inertial sensor at the trunk as part of the states and preserves the group affine property for the process model. Personalized lower-extremity forward kinematic models are built and employed as the measurement model for the augmented InEKF . Observability analysis for the new InEKF design is presented. The filter is evaluated with three subjects in squatting, rolling-foot walking, and ladder-climbing motions. Experimental results validate the superior performance of the proposed InEKF over the state-of-the-art InEKF . Improved accuracy and faster convergence in estimating the velocity and orientation of human, in all three motions, are achieved despite the significant initial estimation errors and the uncertainties associated with the forward kinematic measurement model. Wearable robots have gained growing interests over the past decades as they demonstrated great potentials in facilitating neurorehabiltiation, assisting in daily activities, and reducing work-related injuries [1]-[3]. Wearable robots have been designed with different actuation mechanisms (e.g., cable-driven and pneumatic-driven) and materials (e.g., carbon fibers and fabrics), and they have been applied to various human joints. Since wearable robots physically interact with humans, it is critical to develop control systems that can understand the human's intent and physical states to adaptively exert an This work was supported by the National Science Foundation under Grants IIS-1756031, IIS-1955979, CMMI-1944833, and CMMI-2046562.

This paper introduces a new invariant extended Kalman filter design that produces real-time state estimates and rapid error convergence for the estimation of the human body movement even in the presence of sensor misalignment and initial state estimation errors. The filter fuses the data returned by an inertial measurement unit (IMU) attached to the body (e.g., pelvis or chest) and a virtual measurement of zero stance-foot velocity (i.e., leg odometry). The key novelty of the proposed filter lies in that its process model meets the group affine property while the filter explicitly addresses the IMU placement error by formulating its stochastic process model as Brownian motions and incorporating the error in the leg odometry. Although the measurement model is imperfect (i.e., it does not possess an invariant observation form) and thus its linearization relies on the state estimate, experimental results demonstrate fast convergence of the proposed filter (within 0.2 seconds) during squatting motions even under significant IMU placement inaccuracy and initial estimation errors.

-- This paper explores successor features for knowledge transfer in zero-sum, complete-information, and turn-based games. Prior research in single-agent systems has shown that successor features can provide a "jump start" for agents when facing new tasks with varying reward structures. However, knowledge transfer in games typically relies on value and equilibrium transfers, which heavily depends on the similarity between tasks. This reliance can lead to failures when the tasks differ significantly. T o address this issue, this paper presents an application of successor features to games and presents a novel algorithm called Game Generalized Policy Improvement (GGPI), designed to address Markov games in multi-agent reinforcement learning. The proposed algorithm enables the transfer of learning values and policies across games. An upper bound of the errors for transfer is derived as a function the similarity of the task. Through experiments with a turn-based pursuer-evader game, we demonstrate that the GGPI algorithm can generate high-reward interactions and one-shot policy transfer . When further tested in a wider set of initial conditions, the GGPI algorithm achieves higher success rates with improved path efficiency compared to those of the baseline algorithms.

--Under-actuated compliant robotic systems offer a promising approach to mitigating actuation and control challenges by harnessing pre-designed, embodied dynamic behaviors. This paper presents Flix-Walker, a novel, untethered, centimeter-scale quadrupedal robot inspired by compliant under-actuated mechanisms. Flix-Walker employs flexible, helix-shaped beams as legs, which are actuated by vibrations from just two motors to achieve three distinct mobility modes. We analyze the actuation parameters required to generate various locomotion modes through both simulation and prototype experiments. The effects of system and environmental variations on locomotion performance are examined, and we propose a generic metric for selecting control parameters that produce robust and functional motions. Under-actuated, compliant systems exploit structural dynamics to produce complex robotic motions for locomotion and manipulation, while reducing actuation demands. Leveraging these dynamic behaviors diminishes the need for active actuation, lowers controller complexity, reduces actuator count, and simplifies fabrication [1], [2]. Legged robots offer superior maneuverability in cluttered terrain compared to wheeled or tracked platforms [3], [4].

Laser powder bed fusion (L-PBF) is a widely recognized additive manufacturing technology for producing intricate metal components with exceptional accuracy. A key challenge in L-PBF is the formation of complex microstructures affecting product quality. We propose a physics-guided, machine-learning approach to optimize scan paths for desired microstructure outcomes, such as equiaxed grains. We utilized a phase-field method (PFM) to model crystalline grain structure evolution. To reduce computational costs, we trained a surrogate machine learning model, a 3D U-Net convolutional neural network, using single-track phase-field simulations with various laser powers to predict crystalline grain orientations based on initial microstructure and thermal history. We investigated three scanning strategies across various hatch spacings within a square domain, achieving a two-orders-of-magnitude speedup using the surrogate model. To reduce trial and error in designing laser scan toolpaths, we used deep reinforcement learning (DRL) to generate optimized scan paths for target microstructure. Results from three cases demonstrate the DRL approach's effectiveness. We integrated the surrogate 3D U-Net model into our DRL environment to accelerate the reinforcement learning training process. The reward function minimizes both aspect ratio and grain volume of the predicted microstructure from the agent's scan path. The reinforcement learning algorithm was benchmarked against conventional zigzag approach for smaller and larger domains, showing machine learning methods' potential to enhance microstructure control and computational efficiency in L-PBF optimization.