A robotic shark hungry for plastic is to snap up waste in the River Thames as part of efforts to tackle water pollution. WasteShark is the first marine robot to take London's river by storm, with the ability to'eat' up to 1,100lbs of waste everyday - equivalent to 22,700 plastic bottles. The electric shark has been released in Canary Wharf where it can travel through 3.1 miles (5km) of water before needing a recharge. It comes at a time when plastic waste has almost doubled globally since 2000, with only nine per cent of this successfully recycled, according to an Organisation for Economic Co-operation and Development report. But Britvic-owned Aqua Libra, which is launching the shark, hope to combat this by recycling the collected rubbish wherever possible.

Francis Fukuyama famously said in his 1992 book, The End of History and the Last Man, that history had come to an end circa 1989 with the fall of the Berlin Wall. It announced the end of the Cold War, the collapse of Soviet Russia and, generally, of communism as an economic system, and, correlatively, the unopposed global spread of liberal democracy. One hundred and eighty years before Fukuyama, Hegel had said something similar when he saw Napoleon on horseback riding into the town of Jena in 1806. Napoleon was, for many in those early days, the symbol of the spread of freedom through Europe and against the tyranny of monarchy. There is today the suspicion coming from both Marxists and conservatives alike that the imminent transformation of the labour process, its complete automation through robotics and artificial intelligence (AI), will bring about the end of history.

Youssef Jira, a fresh-faced 18-year-old in a hoodie with a bandana around his head, has big ambitions in a Libyan society where dictatorship and violence has dominated, rather than youthful creativity. Jira is one of a group of young tech fanatics who took part in the Libya Regional Championship for robotics in a suburb of Tripoli this month. Some 20 teams of 12-to-18-year-olds competed in the inclusive event. He wants to encourage other young people to use hi-tech to help modernise the divided and conflict-scarred country. "We want to send a message to the whole of society, because what we've learned has changed us a lot," Jira said, adding that he has gained new skills and learned about teamwork in pursuit of a common goal.

This work proposes a model for continual learning on tasks involving temporal sequences, specifically, human motions. It improves on a recently proposed brain-inspired replay model (BI-R) by building a biologically-inspired conditional temporal variational autoencoder (BI-CTVAE), which instantiates a latent mixture-of-Gaussians for class representation. We investigate a novel continual-learning-to-generate (CL2Gen) scenario where the model generates motion sequences of different classes. The generative accuracy of the model is tested over a set of tasks. The final classification accuracy of BI-CTVAE on a human motion dataset after sequentially learning all action classes is 78%, which is 63% higher than using no-replay, and only 5.4% lower than a state-of-the-art offline trained GRU model.

In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of both combinatorial and continuous parameters. We demonstrate that previous evolutionary algorithms which rely on mutation-based approaches, while flexible over combinatorial spaces, suffer from a curse of dimensionality in high dimensional continuous spaces both theoretically and empirically, which thus limits their scope over hybrid search spaces as well. In order to combat this curse, we propose ES-ENAS, a simple and modular joint optimization procedure combining the class of sample-efficient smoothed gradient techniques, commonly known as Evolutionary Strategies (ES), with combinatorial optimizers in a highly scalable and intuitive way, inspired by the one-shot or supernet paradigm introduced in Efficient Neural Architecture Search (ENAS). By doing so, we achieve significantly more sample efficiency, which we empirically demonstrate over synthetic benchmarks, and are further able to apply ES-ENAS for architecture search over popular RL benchmarks.

InfoMap is a popular approach for detecting densely connected "communities" of nodes in networks. To detect such communities, InfoMap uses random walks and ideas from information theory. Motivated by the dynamics of disease spread on networks, whose nodes may have heterogeneous disease-removal rates, we adapt InfoMap to absorbing random walks. To do this, we use absorption-scaled graphs, in which the edge weights are scaled according to absorption rates, along with Markov time sweeping. One of our adaptations of InfoMap converges to the standard version of InfoMap in the limit in which the node-absorption rates approach $0$. The community structure that we obtain using our adaptations of InfoMap can differ markedly from the community structure that one detects using methods that do not take node-absorption rates into account. Additionally, we demonstrate that the community structure that is induced by local dynamics can have important implications for susceptible-infected-recovered (SIR) dynamics on ring-lattice networks. For example, we find situations in which the outbreak duration is maximized when a moderate number of nodes have large node-absorption rates.

Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion process by gradients from a time-dependent classifier. While the idea is theoretically sound, deep learning-based classifiers are infamously susceptible to gradient-based adversarial attacks. Therefore, while traditional classifiers may achieve good accuracy scores, their gradients are possibly unreliable and might hinder the improvement of the generation results. Recent work discovered that adversarially robust classifiers exhibit gradients that are aligned with human perception, and these could better guide a generative process towards semantically meaningful images. We utilize this observation by defining and training a time-dependent adversarially robust classifier and use it as guidance for a generative diffusion model. In experiments on the highly challenging and diverse ImageNet dataset, our scheme introduces significantly more intelligible intermediate gradients, better alignment with theoretical findings, as well as improved generation results under several evaluation metrics. Furthermore, we conduct an opinion survey whose findings indicate that human raters prefer our method's results.

Automatic radiology report summarization is a crucial clinical task, whose key challenge is to maintain factual accuracy between produced summaries and ground truth radiology findings. Existing research adopts reinforcement learning to directly optimize factual consistency metrics such as CheXBert or RadGraph score. However, their decoding method using greedy search or beam search considers no factual consistency when picking the optimal candidate, leading to limited factual consistency improvement. To address it, we propose a novel second-stage summarizing approach FactReranker, the first attempt that learns to choose the best summary from all candidates based on their estimated factual consistency score. We propose to extract medical facts of the input medical report, its gold summary, and candidate summaries based on the RadGraph schema and design the fact-guided reranker to efficiently incorporate the extracted medical facts for selecting the optimal summary. We decompose the fact-guided reranker into the factual knowledge graph generation and the factual scorer, which allows the reranker to model the mapping between the medical facts of the input text and its gold summary, thus can select the optimal summary even the gold summary can't be observed during inference. We also present a fact-based ranking metric (RadMRR) for measuring the ability of the reranker on selecting factual consistent candidates. Experimental results on two benchmark datasets demonstrate the superiority of our method in generating summaries with higher factual consistency scores when compared with existing methods.

The object perception capabilities of humans are impressive, and this becomes even more evident when trying to develop solutions with a similar proficiency in autonomous robots. While there have been notable advancements in the technologies for artificial vision and touch, the effective integration of these two sensory modalities in robotic applications still needs to be improved, and several open challenges exist. Taking inspiration from how humans combine visual and haptic perception to perceive object properties and drive the execution of manual tasks, this article summarises the current state of the art of visuo-haptic object perception in robots. Firstly, the biological basis of human multimodal object perception is outlined. Then, the latest advances in sensing technologies and data collection strategies for robots are discussed. Next, an overview of the main computational techniques is presented, highlighting the main challenges of multimodal machine learning and presenting a few representative articles in the areas of robotic object recognition, peripersonal space representation and manipulation. Finally, informed by the latest advancements and open challenges, this article outlines promising new research directions.

Generative AI, i.e., the group of technologies that automatically generate visual or written content based on text prompts, has undergone a leap in complexity and become widely available within just a few years. Such technologies potentially introduce a massive disruption to creative fields. This paper presents the results of a qualitative survey ($N$ = 23) investigating how creative professionals think about generative AI. The results show that the advancement of these AI models prompts important reflections on what defines creativity and how creatives imagine using AI to support their workflows. Based on these reflections, we discuss how we might design \textit{participatory AI} in the domain of creative expertise with the goal of empowering creative professionals in their present and future coexistence with AI.