Who will control Africa's AI infrastructure, and at what cost? In April, African Union ministers gathered in Tangier, Morocco, to discuss artificial intelligence at a moment when governments across the continent are racing to develop AI strategies, attract investment and expand digital infrastructure. Beneath the enthusiasm, however, sits a more fundamental question. As foreign technology companies invest in data centres, cloud services and AI systems across Africa, how much control will African countries ultimately have over the infrastructure on which those technologies depend? The debate reflects a broader shift in how policymakers are thinking about AI.

We consider the problem of how many samples from a Gaussian multi-index model are required to weakly reconstruct the relevant index subspace. Despite its increasing popularity as a testbed for investigating the computational complexity of neural networks, results beyond the single-index setting remain elusive. In this work, we introduce spectral algorithms based on the linearization of a message passing scheme tailored to this problem. Our main contribution is to show that the proposed methods achieve the optimal reconstruction threshold. Leveraging a high-dimensional characterization of the algorithms, we show that above the critical threshold the leading eigenvector correlates with the relevant index subspace, a phenomenon reminiscent of the Baik-Ben Arous-Peche (BBP) transition in spiked models arising in random matrix theory.

Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during training and has been widely adopted in LLM development, potential security risks it may introduce remain uninvestigated. This paper systematically evaluates the resilience of synthetic-data-integrated training paradigm for LLMs against mainstream poisoning and backdoor attacks. We reveal that such a paradigm exhibits strong resistance to existing attacks, primarily thanks to the different distribution patterns between poisoning data and queries used to generate synthetic samples. To enhance the effectiveness of these attacks and further investigate the security risks introduced by synthetic data, we introduce a novel and universal attack framework, namely, Virus Infection Attack (VIA), which enables the propagation of current attacks through synthetic data even under purely clean queries. Inspired by the principles of virus design in cybersecurity, VIA conceals the poisoning payload within a protective "shell" and strategically searches for optimal hijacking points in benign samples to maximize the likelihood of generating malicious content. Extensive experiments on both data poisoning and backdoor attacks show that VIA significantly increases the presence of poisoning content in synthetic data and correspondingly raises the attack success rate (ASR) on downstream models to levels comparable to those observed in the poisoned upstream models.

The Restricted Boltzmann Machine (RBM) is one of the simplest generative neural networks capable of learning input distributions. Despite its simplicity, the analysis of its performance in learning from the training data is only well understood in cases that essentially reduce to singular value decomposition of the data. Here, we consider the limit of a large dimension of the input space and a constant number of hidden units. In this limit, we simplify the standard RBM training objective into a form that is equivalent to the multi-index model with non-separable regularization. This opens a path to analyze training of the RBM using methods that are established for multi-index models, such as Approximate Message Passing (AMP) and its state evolution, and the analysis of Gradient Descent (GD) via the dynamical mean-field theory. We then give rigorous asymptotics of the training dynamics of RBMs on data generated by the spiked covariance model as a prototype of a structure suitable for unsupervised learning. We show in particular that RBMs reach the optimal computational weak recovery threshold, aligning with the Baik-Ben Arous-Péché (BBP) transition, in the spiked covariance model.

We study the dynamics of stochastic gradient descent (SGD) for a class of sequence models termed Sequence Single-Index (SSI) models, where the target depends on a single direction in input space applied to a sequence of tokens. This setting generalizes classical single-index models to the sequential domain, encompassing simplified one-layer attention architectures. We derive a closed-form expression for the population loss in terms of a pair of sufficient statistics capturing semantic and positional alignment, and characterize the induced high-dimensional SGD dynamics for these coordinates. Our analysis reveals two distinct training phases: escape from uninformative initialization and alignment with the target subspace, and demonstrates how the sequence length and positional encoding influence convergence speed and learning trajectories. These results provide a rigorous and interpretable foundation for understanding how sequential structure in data can be beneficial for learning with attention-based models. Stochastic Gradient Descent (SGD) is the core optimization tool driving modern machine learning. Recent years have seen substantial progress in understanding its dynamics, particularly in two-layer networks [Saad and Solla, 1995, Mei et al., 2018, Chizat and Bach, 2018, Rotskoff and VandenEijnden, 2022, Sirignano and Spiliopoulos, 2020, Arnaboldi et al., 2023a]. While global convergence is qualitatively well-understood when the network is wide enough, quantitative results are scarcer. A particularly fruitful body of recent theoretical work addressing this gap has focused on deriving precise convergence rates for particular model classes on synthetic data, such as high-dimensional Gaussian single and multi-index models [Ben Arous et al., 2021, Abbe et al., 2022, 2023].

We consider the problem of how many samples from a Gaussian multi-index model are required to weakly reconstruct the relevant index subspace. Despite its increasing popularity as a testbed for investigating the computational complexity of neural networks, results beyond the single-index setting remain elusive. In this work, we introduce spectral algorithms based on the linearization of a message passing scheme tailored to this problem. Our main contribution is to show that the proposed methods achieve the optimal reconstruction threshold. Leveraging a high-dimensional characterization of the algorithms, we show that above the critical threshold the leading eigenvector correlates with the relevant index subspace, a phenomenon reminiscent of the Baik-Ben Arous-Peche (BBP) transition in spiked models arising in random matrix theory.

Pat McAfee wages war on Omaha's famous Jell-o shot bar after crew gets cold reception at College World Series NASCAR legend Tony Stewart calls mourning fans'a--holes' in tone-deaf rant about Kyle Busch Brewers' Jacob Misiorowski breaks brains and radar guns with hardest pitch ever by a starting pitcher US fans were out in full force ahead of the USMNT's first match of the 2026 FIFA World Cup MLB announces drive-in theater screenings of'The Sandlot' with live games and fireworks for July 4th California Democratic Party under fire for'you're not allowed to watch' World Cup post Victor Wembanyama isn't good or mature enough to be the face of the NBA -- at least not yet Trump praised for having'lots of energy' ahead of 80th birthday Trump calls Maine Democratic Senate candidate Graham Platner a'thug' Charter Space founder responds to critics' worries about SpaceX impact on market Rep. Byron Donalds shares his faith redemption story amid Florida gubernatorial run Iran's foreign minister says peace with US'has never been closer' GOP lawmaker says it's'really important' that US continues cartel crackdown Spencer Pratt's use of AI to boost campaign sparks debate FBI arrests first suspect on'most wanted fraudsters' list Brazil favored at -145 with the over at 2.5 +115, while Japan's tactical play could neutralize Haaland INSTANT REACTION FIFA World Cup Now reacts to USA's 4-1 dominant win over Paraguay Melissa Ortiz, Peter Crouch, Sacha Kljestan, Bob Bradley, Stu Holden, Brad Guzan and Mo Edu react to USA's 4-1 win over Paraguay. We are all jazzed up about the World Cup, right? I mean it is in our own backyard this year and the USA Men's National Team just won their first game with a dominant 4-1 victory over Paraguay. More importantly to me, we just won 1.35 units on the game because we took the over for it. I'm headed back to the pitch today for a couple of different plays.

NASCAR legend Tony Stewart calls mourning fans'a--holes' in tone-deaf rant about Kyle Busch Brewers' Jacob Misiorowski breaks brains and radar guns with hardest pitch ever by a starting pitcher US fans were out in full force ahead of the USMNT's first match of the 2026 FIFA World Cup MLB announces drive-in theater screenings of'The Sandlot' with live games and fireworks for July 4th California Democratic Party under fire for'you're not allowed to watch' World Cup post Victor Wembanyama isn't good or mature enough to be the face of the NBA -- at least not yet Rep. Byron Donalds shares his faith redemption story amid Florida gubernatorial run Iran's foreign minister says peace with US'has never been closer' GOP lawmaker says it's'really important' that US continues cartel crackdown Spencer Pratt's use of AI to boost campaign sparks debate FBI arrests first suspect on'most wanted fraudsters' list Accused Charlie Kirk killer's attorneys seek to BLOCK death penalty Kayleigh McEnany: Capitalism isn't the big evil Bernie Sanders would have you believe OutKick Sports Pat McAfee wages war on Omaha's famous Jell-o shot bar after crew gets cold reception at College World Series McAfee says the general manager was unhappy he didn't call ahead and mocked his ability to pay for shots Dan Dakich asks how ESPN's relevance has changed since adding Pat McAfee. We've got drama at the College World Series, and it has nothing to do with baseball. Pat McAfee has waged war with Rocco's -- the famous Omaha-based bar known for its Jell-O shot challenge during the 12-day tournament. And by war, I mean McAfee stuffed the GM in a locker during a heated segment on his ESPN and YouTube show Friday afternoon. It was nowhere near what I thought it was going to be like, McAfee said of the crew's experience at the bar earlier this week.

The Restricted Boltzmann Machine (RBM) is one of the simplest generative neural networks capable of learning input distributions. Despite its simplicity, the analysis of its performance in learning from the training data is only well understood in cases that essentially reduce to singular value decomposition of the data. Here, we consider the limit of a large dimension of the input space and a constant number of hidden units. In this limit, we simplify the standard RBM training objective into a form that is equivalent to the multi-index model with non-separable regularization. This opens a path to analyze training of the RBM using methods that are established for multi-index models, such as Approximate Message Passing (AMP) and its state evolution, and the analysis of Gradient Descent (GD) via the dynamical mean-field theory. We then give rigorous asymptotics of the training dynamics of RBMs on data generated by the spiked covariance model as a prototype of a structure suitable for unsupervised learning. We show in particular that RBMs reach the optimal computational weak recovery threshold, aligning with the Baik-Ben Arous-Péché (BBP) transition, in the spiked covariance model.

Fully autonomous drones with no human oversight have killed soldiers on the battlefield for the first time. This is according to a senior figure in the Ukrainian defence industry, marking a watershed moment in warfare. The one-off test involved 10 AI-controlled "Terminator" drones on the front line of the Ukraine war. "We tried it," says drone-maker Alexander Kokhanovskyy, who supplied the technology and spoke to at a press event hosted by the Ukrainian embassy. We never implemented it [more widely]." The test took place two years ago and involved quadcopter drones that were programmed to fly towards the front line, cover between 3 and 5 kilometres over around 10 minutes and then engage "Terminator mode", in which an AI model searches for and intercepts targets. "We just launch it and we know everything will be dead - everything that will be found there in this particular area will be dead," says Kokhanovskyy. "There is no connection to the drone at all, you cannot see the video, ...