Fox News anchor Bret Baier has the latest on the Murdoch Children's Research Institute's partnership with the Gladstone Institutes for the "Decoding Broken Hearts" initiative on "Special Report." Imagine having a tireless guardian watching over you during your subway commute. New York City's subway system is testing artificial intelligence to boost security and reduce crime. Michael Kemper, a 33-year NYPD veteran and the chief security officer for the Metropolitan Transportation Authority (MTA), which is the largest transit agency in the United States, is leading the rollout of AI software designed to spot suspicious behavior as it happens. The MTA says this technology represents the future of subway surveillance and reassures riders that privacy concerns are being taken seriously.

Soft attention is a critical mechanism powering LLMs to locate relevant parts within a given context. However, individual attention weights are determined by the similarity of only a single query and key token vector. This "single token attention" bottlenecks the amount of information used in distinguishing a relevant part from the rest of the context. To address this issue, we propose a new attention method, Multi-Token Attention (MTA), which allows LLMs to condition their attention weights on multiple query and key vectors simultaneously. This is achieved by applying convolution operations over queries, keys and heads, allowing nearby queries and keys to affect each other's attention weights for more precise attention. As a result, our method can locate relevant context using richer, more nuanced information that can exceed a single vector's capacity. Through extensive evaluations, we demonstrate that MTA achieves enhanced performance on a range of popular benchmarks. Notably, it outperforms Transformer baseline models on standard language modeling tasks, and on tasks that require searching for information within long contexts, where our method's ability to leverage richer information proves particularly beneficial.

Anyone who has rode the New York City subway can tell you that it has a lot of problems, from strange noises to flammable debris on the tracks. Now, as is the solution for everything these days, the Metropolitan Transportation Authority (MTA) is testing how AI could improve the repair process with the help of six Google Pixel phones. In this case, the Google Pixel phones rode on four different subway cars between last September and January. The experiment, conducted in partnership with Google Public Sector, used the phone's accelerometers, magnetometers and microphones to pick up on any worrisome noises. This data was thn sent to cloud-based systems that generated predictive insights using machine learning algorithms.

Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense mechanisms have made notable progress, they fail to protect against adversaries that aim to induce targeted backdoors under different learning and attack configurations. To address this limitation, we introduce DROP (Distillation-based Reduction Of Poisoning), a novel defense mechanism that combines clustering and activity-tracking techniques with extraction of benign behavior from clients via knowledge distillation to tackle stealthy adversaries that manipulate low data poisoning rates and diverse malicious client ratios within the federation. Through extensive experimentation, our approach demonstrates superior robustness compared to existing defenses across a wide range of learning configurations. Finally, we evaluate existing defenses and our method under the challenging setting of non-IID client data distribution and highlight the challenges of designing a resilient FL defense in this setting.

Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment. However, existing approaches treat perception and captioning as separate tasks, focusing on the performance of only one of the tasks and overlooking the potential benefits of multimodal alignment. To bridge this gap between modalities, we introduce MTA, a novel multimodal task alignment framework that boosts both BEV perception and captioning. MTA consists of two key components: (1) BEV-Language Alignment (BLA), a contextual learning mechanism that aligns the BEV scene representations with ground-truth language representations, and (2) Detection-Captioning Alignment (DCA), a cross-modal prompting mechanism that aligns detection and captioning outputs. MTA integrates into state-of-the-art baselines during training, adding no extra computational complexity at runtime. Extensive experiments on the nuScenes and TOD3Cap datasets show that MTA significantly outperforms state-of-the-art baselines, achieving a 4.9% improvement in perception and a 9.2% improvement in captioning. These results underscore the effectiveness of unified alignment in reconciling BEV-based perception and captioning.

We present a multi-task learning approach to jointly estimate the means of multiple independent data sets. The proposed multi-task averaging (MTA) algorithm results in a convex combination of the single-task averages. We derive the optimal amount of regularization, and show that it can be effectively estimated. Simulations and real data experiments demonstrate that MTA outperforms both maximum likelihood and James-Stein estimators, and that our approach to estimating the amount of regularization rivals cross-validation in performance but is more computationally efficient.

The MTA plans to use artificial intelligence technology to help prevent buses from breaking down on the road. The agency has tested the tech -- from the company Preteckt -- for two years. He said it can flag serious equipment problems long in advance, enabling crews to be more proactive about bus maintenance. Sills said the technology prevents "progressive damage." "Where you have a small issue that can be fixed fairly inexpensively with little amount of time that, if you get ahead of, can prevent you from damaging a very expensive component," he said.

Assembling the compound targets is an open problem for achieving good learning performance in Reinforcement Learning (RL). TD(λ), which uses a single parameter controlled geometric sequence as the weights of the n-step returns, stands out from the sea of compound update methods for its efficient incremental updates and its interesting mathematical properties. Empirical studies show that different λ's yield different performance. Furthermore, it is expected that adapting λ appropriately during the learning boosts performance in terms of convergence speed and accuracy. The goal of this paper is to find a method that optimizes the overall target error for all the states. We first derive a new state meta-objective for optimizing the bias-variance tradeoff and show that the meta-objective proposed in an existing work [1] is actually a special case of the newly proposed objective. Then, we propose a trust-region style method to tackle the difficulties of optimizing the meta-objective and prove its equivalence to optimizing the overall target error, given appropriate assumptions. In experiments, we observe that the proposed method MTA has generally significantly improved empirical performance over the existing method and baselines.

Traffic crawls through the wind and snow on the RFK Bridge on Friday in the Queens borough of New York. So reports the Wall Street Journal which reviewed an internal email sent by the Metropolitan Transportation Authority, the state agency which manages all the traffic crossing the area's bridges and tunnels. The MTA email was sent to the office of New York Governor Andrew Cuomo. According to the email, the "initial period for the proof of concept testing at the (Robert F. Kennedy Bridge connecting Manhattan, the Bronx and Queens) for facial recognition has been completed and failed with no faces (0%) being detected within acceptable parameters." Besides the RFK Bridge, the MTA is testing the technology at the Throgs Neck and Whitestone bridges, as well as at the Midtown and Hugh L. Carey tunnels.

We present a multi-task learning approach to jointly estimate the means of multiple independent data sets. The proposed multi-task averaging (MTA) algorithm results in a convex combination of the single-task averages. We derive the optimal amount of regularization, and show that it can be effectively estimated. Simulations and real data experiments demonstrate that MTA both maximum likelihood and James-Stein estimators, and that our approach to estimating the amount of regularization rivals cross-validation in performance but is more computationally efficient.