Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task.This is challenging since it requires the identification of reward structures that are not sparse and that avoid inadvertently inducing undesirable behaviors. Naively modifying the reward structure to offer denser and more frequent feedback can lead to unintended outcomes and promote behaviors that are not aligned with the designer's intended goal. Although potential-based reward shaping is often suggested as a remedy, we systematically investigate settings where deploying it often significantly impairs performance. To address these issues, we introduce a new framework that uses a bi-level objective to learn \emph{behavior alignment reward functions}. These functions integrate auxiliary rewards reflecting a designer's heuristics and domain knowledge with the environment's primary rewards.

The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained models to downstream tasks in an efficient manner has become a prominent research area. Existing solutions primarily concentrate on designing lightweight adapters and their interaction with pre-trained models, with the goal of minimizing the number of parameters requiring updates. In this study, we propose a novel Adapter Re-Composing (ARC) strategy that addresses efficient pre-trained model adaptation from a fresh perspective. Our approach considers the reusability of adaptation parameters and introduces a parameter-sharing scheme. Specifically, we leverage symmetric down-/up-projections to construct bottleneck operations, which are shared across layers.

This year, hype around AI really exploded, and so did concerns about AI's environmental footprint. We also saw some surprising biotech developments. It's been a busy and productive year here at . We published magazine issues on power, creativity, innovation, bodies, relationships, and security . We hosted 14 exclusive virtual conversations with our editors and outside experts in our subscriber-only series, Roundtables, and held two events on MIT's campus. And we published hundreds of articles online, following new developments in computing, climate tech, robotics, and more.

We consider the problem of traffic accident analysis on a road network based on road network connections and traffic volume. Previous works have designed various deep-learning methods using historical records to predict traffic accident occurrences. However, there is a lack of consensus on how accurate existing methods are, and a fundamental issue is the lack of public accident datasets for comprehensive evaluations. This paper constructs a large-scale, unified dataset of traffic accident records from official reports of various states in the US, totaling 9 million records, accompanied by road networks and traffic volume reports. Using this new dataset, we evaluate existing deep-learning methods for predicting the occurrence of accidents on road networks. Our main finding is that graph neural networks such as GraphSAGE can accurately predict the number of accidents on roads with less than 22% mean absolute error (relative to the actual count) and whether an accident will occur or not with over 87% AUROC, averaged over states. We achieve these results by using multitask learning to account for cross-state variabilities (e.g., availability of accident labels) and transfer learning to combine traffic volume with accident prediction. Ablation studies highlight the importance of road graph-structural features, amongst other features. Lastly, we discuss the implications of the analysis and develop a package for easily using our new dataset.

Savvy countries will discover there's a way to mitigate the harm incurred by Trump's tariffs--and it'll boost their own economies while making goods cheaper too. In 2026, the leaders of America's (former) trading partners are going to have to grapple with the political consequences of tit-for-tat tariffs. A tariff is a tax paid by consumers, and if there's one thing the past four years have taught us, it's that the public will not forgive a politician who presides over a period of rising prices, no matter what the cause. Luckily for the political fortunes of the world's leaders, there is a better way to respond to tariffs. Tit-for-tat tariffs are a 19th-century tactic, and we live in a 21st-century world--a world where the most profitable lines of business of the most profitable US companies are all vulnerable to a simple legal change that will make things cheaper for billions of people, all over the world, including in the US, at the expense of the companies whose CEOs posed with Trump on the inaugural dais.

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .

'We Ain't Seen Nothing Yet'--Trump's Mass Deportations Will Only Grow From Here Militias and far-right extremists believed they would be central to Trump's mass deportation plans. When Donald Trump won a second term as US president a year ago, members of violent militias and far-right extremist groups who had spent years boosting the lie that the 2020 election was rigged were ready to assist the president with delivering on one of his main campaign promises: mass deportations. "I'm willing to help," Richard Mack, a former sheriff who founded the far-right Constitutional Sheriffs and Peace Officers Association, told WIRED at the time, claiming he was in touch with Tom Homan, the man Trump installed as his "border czar." Tim Foley, head of the Arizona Border Recon, which describes itself as a "non-government organization," also told WIRED he was in contact with administration officials. William Teer, then head of the far-right Texas Three Percenters militia, wrote a letter to Trump offering his help.

Modern generative models exhibit unprecedented capabilities to generate extremely realistic data. However, given the inherent compositionality of the real world, reliable use of these models in practical applications requires that they exhibit the capability to compose a novel set of concepts to generate outputs not seen in the training data set. Prior work demonstrates that recent diffusion models do exhibit intriguing compositional generalization abilities, but also fail unpredictably. Motivated by this, we perform a controlled study for understanding compositional generalization in conditional diffusion models in a synthetic setting, varying different attributes of the training data and measuring the model's ability to generate samples out-of-distribution. Our results show: (i) the order in which the ability to generate samples from a concept and compose them emerges is governed by the structure of the underlying data-generating process; (ii) performance on compositional tasks exhibits a sudden emergence due to multiplicative reliance on the performance of constituent tasks, partially explaining emergent phenomena seen in generative models; and (iii) composing concepts with lower frequency in the training data to generate out-of-distribution samples requires considerably more optimization steps compared to generating in-distribution samples. Overall, our study lays a foundation for understanding emergent capabilities and compositionality in generative models from a data-centric perspective.

Is the A.I. Bubble Bursting? An "A.I. hater" makes the case. Please enable javascript to get your Slate Plus feeds. If you can't access your feeds, please contact customer support. Check your phone for a link to finish setting up your feed.

'The game I wish I'd played more' Blue Prince. 'The game I wish I'd played more' Blue Prince. There was no shortage of fun and video games in the Diamond household in the last 12 months. Which ones did we play so much our thumbs hurt? And which one saved my soul?