This work introduces a novel and efficient Bayesian federated learning algorithm, namely, the Federated Averaging stochastic Hamiltonian Monte Carlo (FA-HMC), for parameter estimation and uncertainty quantification. We establish rigorous convergence guarantees of FA-HMC on non-iid distributed data sets, under the strong convexity and Hessian smoothness assumptions. Our analysis investigates the effects of parameter space dimension, noise on gradients and momentum, and the frequency of communication (between the central node and local nodes) on the convergence and communication costs of FA-HMC. Beyond that, we establish the tightness of our analysis by showing that the convergence rate cannot be improved even for continuous FA-HMC process. Moreover, extensive empirical studies demonstrate that FA-HMC outperforms the existing Federated Averaging-Langevin Monte Carlo (FA-LD) algorithm.

Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr), a new multi-purpose architecture for high-energy physics. L-GATr represents high-energy data in a geometric algebra over four-dimensional space-time and is equivariant under Lorentz transformations, the symmetry group of relativistic kinematics. At the same time, the architecture is a Transformer, which makes it versatile and scalable to large systems. L-GATr is first demonstrated on regression and classification tasks from particle physics. We then construct the first Lorentz-equivariant generative model: a continuous normalizing flow based on an L-GATr network, trained with Riemannian flow matching. Across our experiments, L-GATr is on par with or outperforms strong domain-specific baselines.

A large majority of American voters are skeptical of the argument that the U.S. should race ahead to build ever more powerful artificial intelligence, unconstrained by domestic regulations, in an effort to compete with China, according to new polling shared exclusively with TIME. The findings indicate that American voters disagree with a common narrative levied by the tech industry, in which CEOs and lobbyists have repeatedly argued the U.S. must tread carefully with AI regulation in order to not hand the advantage to their geopolitical rival. And they reveal a startling level of bipartisan consensus on AI policy, with both Republicans and Democrats in support of the government placing some limits on AI development in favor of safety and national security. According to the poll, 75% of Democrats and 75% of Republicans believe that "taking a careful controlled approach" to AI--by preventing the release of tools that terrorists and foreign adversaries could use against the U.S.--is preferable to "moving forward on AI as fast as possible to be the first country to get extremely powerful AI." A majority of voters support more stringent security practices at AI companies, and are worried about the risk of China stealing their most powerful models, the poll shows.

On an evening in December 2023, 43-year-old small business owner Sarah Rosenkranz collapsed in her home in Granbury, Texas and was rushed to the emergency room. Her heart pounded 200 beats per minute; her blood pressure spiked into hypertensive crisis; her skull throbbed. "It felt like my head was in a pressure vise being crushed," she says. "That pain was worse than childbirth." Rosenkranz's migraine lasted for five days. Doctors gave her several rounds of IV medication and painkiller shots, but nothing seemed to knock down the pain, she says. This was odd, especially because local doctors were similarly vexed when Indigo, Rosenkranz's 5-year-old daughter, was taken to urgent care earlier that year, screaming that she felt a "red beam behind her eardrums." It didn't occur to Sarah that these symptoms could be linked. But in January 2024, she walked into a town hall in Granbury and found a room full of people worn thin from strange, debilitating illnesses.

Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For such liquid-metal dealloying (LMD) process, phase field models have been developed. However, the governing equations often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, stiffness in the PDEs requires an extremely small time steps (e.g. $10^{-12}$ or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose U-Shaped Adaptive Fourier Neural Operators (U-AFNO), a machine learning (ML) model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g. the deformation of the liquid-metal interface) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in-spite of the chaotic nature of LMD. Our model reproduces the key micro-structure statistics and QoIs with a level of accuracy on-par with the high-fidelity numerical solver. We also investigate the opportunity of using hybrid simulations, in which we alternate forward leap in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.

The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its security risks. The generated videos may contain illegal or unethical content, and there is a lack of comprehensive quantitative understanding of their safety, posing a challenge to their reliability and practical deployment. Previous evaluations primarily focus on the quality of video generation. While some evaluations of text-to-image models have considered safety, they cover fewer aspects and do not address the unique temporal risk inherent in video generation. To bridge this research gap, we introduce T2VSafetyBench, a new benchmark designed for conducting safety-critical assessments of text-to-video models. We define 12 critical aspects of video generation safety and construct a malicious prompt dataset using LLMs and jailbreaking prompt attacks. Based on our evaluation results, we draw several important findings, including: 1) no single model excels in all aspects, with different models showing various strengths; 2) the correlation between GPT-4 assessments and manual reviews is generally high; 3) there is a trade-off between the usability and safety of text-to-video generative models. This indicates that as the field of video generation rapidly advances, safety risks are set to surge, highlighting the urgency of prioritizing video safety. We hope that T2VSafetyBench can provide insights for better understanding the safety of video generation in the era of generative AI.

Large language models (LLMs) currently dominate the field of natural language processing (NLP), representing the state-of-the-art across a diverse array of tasks. Developing a model of this nature, from training to inference, requires making numerous decisions which define a combinatorial search problem. For example, selecting the optimal pre-trained LLM, prompt, or hyperparameters to attain the best performance for a task often requires evaluating multiple candidates on an entire test set. This exhaustive evaluation can be time-consuming and costly, as both inference and metric computation with LLMs are resource-intensive. In this paper, we address the challenge of identifying the best method within a limited budget for evaluating methods on test examples. By leveraging the well-studied multi-armed bandit framework, which sequentially selects the next method-example pair to evaluate, our approach, combining multi-armed bandit algorithms with low-rank factorization, significantly reduces the required resources. Experiments show that our algorithms can identify the top-performing method using only 5-15\% of the typically needed resources, resulting in an 85-95\% reduction in cost.

In the era of space exploration, coronal holes on the sun play a significant role due to their impact on satellites and aircraft through their open magnetic fields and increased solar wind emissions. This study employs computer vision techniques to detect coronal hole regions and estimate their sizes using imagery from the Solar Dynamics Observatory (SDO). Additionally, we utilize deep learning methods, specifically Long Short-Term Memory (LSTM) networks, to analyze trends in the area of coronal holes and predict their areas across various solar regions over a span of seven days. By examining time series data, we aim to identify patterns in coronal hole behavior and understand their potential effects on space weather. This research enhances our ability to anticipate and prepare for space weather events that could affect Earth's technological systems.

At face value, this essay is about understanding a fairly esoteric governance tool called compute thresholds. However, in order to grapple with whether these thresholds will achieve anything, we must first understand how they came to be. This requires engaging with a decades-old debate at the heart of computer science progress, namely, is bigger always better? Hence, this essay may be of interest not only to policymakers and the wider public but also to computer scientists interested in understanding the role of compute in unlocking breakthroughs. Does a certain inflection point of compute result in changes to the risk profile of a model? This discussion is increasingly urgent given the wide adoption of governance approaches that suggest greater compute equates with higher propensity for harm. Several leading frontier AI companies have released responsible scaling policies. Both the White House Executive Orders on AI Safety (EO) and the EU AI Act encode the use of FLOP or floating-point operations as a way to identify more powerful systems. What is striking about the choice of compute thresholds to-date is that no models currently deployed in the wild fulfill the current criteria set by the EO. This implies that the emphasis is often not on auditing the risks and harms incurred by currently deployed models - but rather is based upon the belief that future levels of compute will introduce unforeseen new risks. A key conclusion of this essay is that compute thresholds as currently implemented are shortsighted and likely to fail to mitigate risk. Governance that is overly reliant on compute fails to understand that the relationship between compute and risk is highly uncertain and rapidly changing. It also overestimates our ability to predict what abilities emerge at different scales. This essay ends with recommendations for a better way forward.

This paper presents three batch estimation methods that use noisy ground velocity and heading measurements from a vehicle executing a circular orbit (or similar large heading change maneuver) to estimate the speed and direction of a steady, uniform, flow-field. The methods are based on a simple kinematic model of the vehicle's motion and use curve-fitting or nonlinear least-square optimization. A Monte Carlo simulation with randomized flow conditions is used to evaluate the batch estimation methods while varying the measurement noise of the data and the interval of unique heading traversed during the maneuver. The methods are also compared using experimental data obtained with a Bluefin-21 unmanned underwater vehicle performing a series of circular orbit maneuvers over a five hour period in a tide-driven flow.