Content-Controllable Summarization generates summaries focused on the given controlling signals. Due to the lack of large-scale training corpora for the task, we propose a plug-and-play module RelAttn to adapt any general summarizers to the content-controllable summarization task. RelAttn first identifies the relevant content in the source documents, and then makes the model attend to the right context by directly steering the attention weight. We further apply an unsupervised online adaptive parameter searching algorithm to determine the degree of control in the zero-shot setting, while such parameters are learned in the few-shot setting. By applying the module to three backbone summarization models, experiments show that our method effectively improves all the summarizers, and outperforms the prefix-based method and a widely used plug-and-play model in both zero- and few-shot settings. Tellingly, more benefit is observed in the scenarios when more control is needed.

The Self-Optimization (SO) model is a useful computational model for investigating self-organization in "soft" Artificial life (ALife) as it has been shown to be general enough to model various complex adaptive systems. So far, existing work has been done on relatively small network sizes, precluding the investigation of novel phenomena that might emerge from the complexity arising from large numbers of nodes interacting in interconnected networks. This work introduces a novel implementation of the SO model that scales as $\mathcal{O}\left(N^{2}\right)$ with respect to the number of nodes $N$, and demonstrates the applicability of the SO model to networks with system sizes several orders of magnitude higher than previously was investigated. Removing the prohibitive computational cost of the naive $\mathcal{O}\left(N^{3}\right)$ algorithm, our on-the-fly computation paves the way for investigating substantially larger system sizes, allowing for more variety and complexity in future studies.

Recent work has uncovered close links between between classical reinforcement learning algorithms, Bayesian filtering, and Active Inference which lets us understand value functions in terms of Bayesian posteriors. An alternative, but less explored, model-free RL algorithm is the successor representation, which expresses the value function in terms of a successor matrix of expected future state occupancies. In this paper, we derive the probabilistic interpretation of the successor representation in terms of Bayesian filtering and thus design a novel active inference agent architecture utilizing successor representations instead of model-based planning. We demonstrate that active inference successor representations have significant advantages over current active inference agents in terms of planning horizon and computational cost. Moreover, we demonstrate how the successor representation agent can generalize to changing reward functions such as variants of the expected free energy.

Australia will need to double the pace of its renewable energy uptake to meet the 2030 emissions target set by the Albanese government, even without any increase in demand, according to Bruce Mountain, head of the Victoria Energy Policy Centre. Labor's main energy policy, Rewiring the Nation, includes the creation of a special corporation to funnel $20bn into new transmission links to accelerate the uptake of more clean energy. The plan is part of Labor's pledge to cut Australia's 2005-level greenhouse gas emissions 43% by 2030, projecting renewables reach an 82% share of renewables in the National Electricity Market by then. Excluding hydro power, renewable energy has increased its share of the market 3% annually in the past five years, Mountain says. "Deducting 10% from hydro, the target is 72%," he says of Labor's goal.

Thousands of historical images from across Ireland are being brought to life in color for the first time, thanks to a new AI-led photo project. Combining digital technology with painstaking historical research, professors John Breslin and Sarah-Anne Buckley at the National University of Ireland, Galway, have been able to turn photos, originally shot in black in white, into rich color images. It includes portraits of key figures like Oscar Wilde and poet W.B. Yeats, as well as defining moments in history, like the Titanic setting sail from the Belfast shipyard where it was constructed. Yet, some of the most compelling photos depict everyday scenes -- people herding pigs, spinning wool or packed onto the back of horse-drawn carts. And while poverty is evident in pictures of barefoot villagers crowding around for a photo, or of Dublin's working-class tenement buildings, there are also well-to-do family shots and depictions of upper-class pastimes like fox hunting.

Active Inference (AIF) is an emerging framework in the brain sciences which suggests that biological agents act to minimise a variational bound on model evidence. Control-as-Inference (CAI) is a framework within reinforcement learning which casts decision making as a variational inference problem. While these frameworks both consider action selection through the lens of variational inference, their relationship remains unclear. Here, we provide a formal comparison between them and demonstrate that the primary difference arises from how value is incorporated into their respective generative models. In the context of this comparison, we highlight several ways in which these frameworks can inform one another.

Tristram Buckley says the benches in the Forbidden Journey ride gave him "shaken adult syndrome." It's safe to say Tristram Buckley wasn't swept up in the magic of the Wizarding World of Harry Potter. Buckley, a former visitor to the Universal Studios Hollywood location of the Potter-themed park, claims in a new lawsuit that one of the rides -- Harry Potter and the Forbidden Journey -- left him in pain after causing severe injury to his spine, TMZ reported Monday. According to the suit, Buckley took a seat on the ride's Enchanted Bench, which is suspended from a mechanical arm that moves along a track. The seats also pivot and sway to give riders the sensation of flying through the scenarios presented on a wrap-around screen.

MIT CSAIL Director Daniela Rus says the goal of the STL initiative is "to create a new generation of AI tools that are deeply rooted in systems." From self-driving cars to the Internet of Things, artificial intelligence (AI) has reached new levels of sophistication in recent years. With that in mind, this week MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) launched an industry collaboration focused on using machine learning to create functional human-like systems. Nearly 40 senior researchers will participate in the new "SystemsThatLearn@CSAIL" (STL) initiative alongside a range of organizations that include founding members BT, Microsoft, Nokia Bell Labs, Salesforce, and Schlumberger. Member companies will work with CSAIL scientists to suggest new lines of research and develop real-world applications.

Whirring engines, hairpin turns and the occasional crash -- but today, instead of top performance cars with millions of dollars of research behind them, it's tiny drones crossing the finish line. "There's really nothing like it," said Tom Buckley, who founded the Boston Multi Rotor Club. "You're in the driver's seat, you are the pilot, you're going around these courses at very fast speeds." Today, Buckley and a couple dozen others will fire up their drones, connect their remote controllers and zoom around a track as fast as they can at BMRC's latest race. The races are often scored based on how many laps each drone can fly in two minutes.