South Korea's top trade envoy Yeo Han-koo said Thursday that Samsung Electronics and SK Hynix will not be subject to 100% U.S. tariffs on chips. Yeo said on radio that among various countries, South Korea will face the most favorable U.S. tariff rates on chips under the trade deal between Washington and Seoul. U.S. President Donald Trump said Wednesday the United States will impose a tariff of about 100% on semiconductors imported from countries not producing in the U.S. or planning to do so. But it would not apply to companies that had made a commitment to manufacture in the U.S. or were in the process of doing so. Trump's comments were not a formal announcement and much remains unclear.

Russian artillery shelling on a car belonging to Ukraine's state emergency services killed three people, including an emergency worker, and injured four others in the southeastern Ukrainian town of Nikopol, the regional governor, Serhiy Lysak, said. Dozens of Russian drones attacked a gas pumping station in southern Ukraine, part of an LNG imports scheme from the United States and Azerbaijan, Ukraine's Ministry of Energy said. Russia struck a gas facility in Ukraine's southern Odesa region, Ukrainian President Volodymyr Zelenskyy said, as Ukraine's gas reserves are now at their lowest in 12 years, with storage facilities currently less than a third full, according to analysis firm ExPro. Russian artillery shelling on a car belonging to Ukraine's state emergency services killed three people, including an emergency worker, and injured four others in the southeastern Ukrainian town of Nikopol, the regional governor, Serhiy Lysak, said. Dozens of Russian drones attacked a gas pumping station in southern Ukraine, part of an LNG imports scheme from the United States and Azerbaijan, Ukraine's Ministry of Energy said.

Donald Trump on Wednesday celebrated a commitment by Apple to increase its investments in US manufacturing by an additional 100bn over the next four years. Apple's plan to up its domestic investment comes as it seeks to avoid Trump's threatened tariffs, which would increase the tech giant's costs as it relies on a complex international supply chain to produce its iPhones. Apple's CEO, Tim Cook, warned during an earnings call in May that the tariffs could cost the company up to 900m that fiscal quarter alone. After Cook gifted Trump a US-made souvenir with a 24-karat gold base at the Oval Office on Wednesday, the president praised the corporation, telling reporters: "Companies like Apple, they're coming home … This is a significant step toward the ultimate goal of ensuring that iPhones sold in America also are made in America." Cook said many components of the iPhones are already made domestically, including glass, semiconductors and face ID, but that final assembly of the devices would remain overseas "for a while".

KI) platform, a new benchmark designed to address the unique challenges of integrating medical knowledge into foundation models under privacy constraints.

In this paper, we propose new randomized algorithms for estimating the two-to-infinity and one-to-two norms in a matrix-free setting, using only matrix-vector multiplications. Our methods are based on appropriate modifications of Hutchinson's diagonal estimator and its Hutch++ version. We provide oracle complexity bounds for both modifications. We further illustrate the practical utility of our algorithms for Jacobian-based regularization in deep neural network training on image classification tasks. We also demonstrate that our methodology can be applied to mitigate the effect of adversarial attacks in the domain of recommender systems.

We implement a quantum generalization of a neural network on trapped-ion and IBM superconducting quantum computers to classify MNIST images, a common benchmark in computer vision. The network feedforward involves qubit rotations whose angles depend on the results of measurements in the previous layer. The network is trained via simulation, but inference is performed experimentally on quantum hardware. The classical-to-quantum correspondence is controlled by an interpolation parameter, $a$, which is zero in the classical limit. Increasing $a$ introduces quantum uncertainty into the measurements, which is shown to improve network performance at moderate values of the interpolation parameter. We then focus on particular images that fail to be classified by a classical neural network but are detected correctly in the quantum network. For such borderline cases, we observe strong deviations from the simulated behavior. We attribute this to physical noise, which causes the output to fluctuate between nearby minima of the classification energy landscape. Such strong sensitivity to physical noise is absent for clear images. We further benchmark physical noise by inserting additional single-qubit and two-qubit gate pairs into the neural network circuits. Our work provides a springboard toward more complex quantum neural networks on current devices: while the approach is rooted in standard classical machine learning, scaling up such networks may prove classically non-simulable and could offer a route to near-term quantum advantage.

Adversarial robustness of deep autoencoders (AEs) remains relatively unexplored, even though their non-invertible nature poses distinct challenges. Existing attack algorithms during the optimization of imperceptible, norm-bounded adversarial perturbations to maximize output damage in AEs, often stop at sub-optimal attacks. We observe that the adversarial loss gradient vanishes when backpropagated through ill-conditioned layers. This issue arises from near-zero singular values in the Jacobians of these layers, which weaken the gradient signal during optimization. We introduce GRILL, a technique that locally restores gradient signals in ill-conditioned layers, enabling more effective norm-bounded attacks. Through extensive experiments on different architectures of popular AEs, under both sample-specific and universal attack setups, and across standard and adaptive attack settings, we show that our method significantly increases the effectiveness of our adversarial attacks, enabling a more rigorous evaluation of AE robustness.

--Preliminary attempts at incorporating the critical role of astrocytes--cells that constitute more than 50% of human brain cells--in brain-inspired neuromorphic computing remain in infancy. This paper seeks to delve deeper into various key aspects of neuron-synapse-astrocyte interactions to mimic self-attention mechanisms in Transformers. The cross-layer perspective explored in this work involves bioplausible modeling of Hebbian and presynaptic plasticities in neuron-astrocyte networks, incorporating effects of non-linearities and feedback along with algorithmic formulations to map the neuron-astrocyte computations to self-attention mechanism and evaluating the impact of incorporating bio-realistic effects from the machine learning application side. Our analysis on sentiment and image classification tasks (IMDB and CIF AR10 datasets) highlights the advantages of Astromorphic Transformers, offering improved accuracy and learning speed. Furthermore, the model demonstrates strong natural language generation capabilities on the WikiT ext-2 dataset, achieving better perplexity compared to conventional models, thus showcasing enhanced generalization and stability across diverse machine learning tasks. STROCYTES, a type of glial cell, play a critical role in brain function, encompassing various processes such as homeostasis, metabolism, and synaptic regulation [1]. Astrocytes detect and regulate synaptic activity in the tripartite synapse through interactions with pre-and postsynaptic neurons. Investigating their impact on neural computation is currently an active research field in neuroscience and underscores the critical need to move beyond the neuro-synaptic perspective of current Artificial Intelligence (AI) systems. Recent experimental findings on neuron-astrocyte interactions and modulation have led to significant progress in computational neuroscience, enabling the development of models that incorporate neuron-astrocyte interactions within neural networks [2], [3]. Astrocytes have been found to modulate bursting in neural circuitry through the release of gliotransmitters, which have an impact on neuronal excitability and synaptic plasticity [4], [5]. Astrocytes possess the ability to encode information through calcium signaling and regulate information processing, thereby actively engaging in neural computation at the tripartite synapse level. Additionally, astrocytes possess inherent capacity as memory components [6], [7] and plasticity regulators that are capable of facilitating local sequential learning [8], [9].

Causal representation learning has attracted significant research interest during the past few years, as a means for improving model generalization and robustness. Causal representations of interventional image pairs (also called "actionable counterfactuals" in the literature), have the property that only variables corresponding to scene elements affected by the intervention / action are changed between the start state and the end state. While most work in this area has focused on identifying and representing the variables of the scene under a causal model, fewer efforts have focused on representations of the interventions themselves. In this work, we show that an effective strategy for improving out of distribution (OOD) robustness is to focus on the representation of actionable counterfactuals in the latent space. Specifically, we propose that an intervention can be represented by a Causal Delta Embedding that is invariant to the visual scene and sparse in terms of the causal variables it affects. Leveraging this insight, we propose a method for learning causal representations from image pairs, without any additional supervision. Experiments in the Causal Triplet challenge demonstrate that Causal Delta Embeddings are highly effective in OOD settings, significantly exceeding baseline performance in both synthetic and real-world benchmarks. Understanding how the world changes in response to actions and external interventions is fundamental for artificial intelligence agents, especially those operating in dynamic environments. Although deep learning models are highly successful at capturing complex patterns from data, they often fail to generalize to new situations where the underlying data distribution changes, which is a critical limitation for real world deployment Hendrycks et al. (2021); Geirhos et al. (2020). To overcome this, agents must recover the underlying mechanisms that generate and transform data, enabling causal reasoning and robust generalization (Pearl, 2009).

Mobile robot motion planners rely on theoretical models to predict how the robot will move through the world. However, when deployed on a physical robot, these models are subject to errors due to real-world physics and uncertainty in how the lower-level controller follows the planned trajectory. In this work, we address this problem by presenting three methods of incorporating stochastic controller behavior into the recombinant search space of the Kinodynamic Efficiently Adaptive State Lattice (KEASL) planner. To demonstrate this work, we analyze the results of experiments performed on a Clearpath Robotics Warthog Unmanned Ground Vehicle (UGV) in an off-road, unstructured environment using two different perception algorithms, and performed an ablation study using a full spectrum of simulated environment map complexities. Analysis of the data found that incorporating stochastic controller sampling into KEASL leads to more conservative trajectories that decrease predicted collision likelihood when compared to KEASL without sampling. When compared to baseline planning with expanded obstacle footprints, the predicted likelihood of collisions becomes more comparable, but reduces the planning success rate for baseline search.