A screengrab from video of the drone and AI assisted search and rescue at Dead Horse Gap in Kosciuszko national park. A screengrab from video of the drone and AI assisted search and rescue at Dead Horse Gap in Kosciuszko national park. Two hikers who veered off a walking track in Kosciuszko national park have been found within five hours using a drone powered by artificial intelligence, a first-of-its-kind mission, Fire and Rescue NSW (FRNSW) has said. The two men, aged in their 20s, were reported missing at 7pm on Tuesday evening after they failed to return to a rendezvous point on time. FRNSW's remote air piloted system was put into the air, and was able to use thermal imaging to find the hikers who had been walking the Dead Horse Gap track, about 35km south-west of Jindabyne.

Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cross-client data heterogeneity naturally coexist, and the mismatch between local and global imbalances exacerbates the performance degradation of the aggregated model. The agnosticism of global class distribution poses significant challenges for data-level methods, especially under extreme conditions with severe class absence across clients. In this paper, we propose FedReLa, a novel data-level approach that tackles the coexistence of data heterogeneity and class imbalance in federated learning. By re-labeling samples with a feature-dependent label re-allocator, FedReLa corrects biased global decision boundaries without requiring knowledge of the global class distribution. This modular, model-agnostic approach can be integrated with algorithmic methods to deliver consistent improvements without additional communication overhead. Through extensive experiments, our method significantly improves the accuracy of minority classes and the overall accuracy on stepwise-imbalanced and long-tailed datasets, outperforming the previous state of the art.

Greens senator Sarah Hanson-Young says Australia can't allow tech firms to'drain our power and water'. Greens senator Sarah Hanson-Young says Australia can't allow tech firms to'drain our power and water'. Australia'sleepwalking' into AI crisis and'tech bro free-for-all', says Greens senator Sarah Hanson Young's warning comes as David Pocock urges government to prevent firms using Australian content to train AI models Tue 23 Jun 2026 06.21 EDTFirst published on Tue 23 Jun 2026 05.16 EDT His call came as the Greens senator Sarah Hanson-Young called for a moratorium on the building and approval of new datacentres in Australia until "we get the regulations right". She said the nation was "sleepwalking" into an AI crisis and could hand tech companies a greenlight "to drain our power and water". Pocock used Senate question time on Tuesday to ask the government about intense lobbying from AI proprietors over possible new rules and regulations for Australian-made content - including suggestions Labor would create a new "carve out" or extend existing licensing arrangements.

Cutting-edge artificial intelligence technology is poised to supercharge offensive hacking capabilities, and urgent action is needed to face up to the threat, US, UK, Canadian, Australian and New Zealand officials have said. "Frontier AI models are anticipated to exceed current industry expectations, fundamentally transforming both offensive and defensive cyber capabilities," the intelligence alliance commonly known as the Five Eyes said in a three-page statement on Monday. The statement was light on detail and mostly restated core cybersecurity advice, such as swiftly patching faulty software and not putting systems online unless necessary. The officials also urged defenders to use AI "to strengthen defence", for example by identifying weaknesses sooner or responding more quickly to incidents. The warning was another indication of officials' increasing concerns over models such as Anthropic's Mythos or OpenAI's GPT-5.5-Cyber, which are said to allow users to quickly execute complex - and potentially devastating - hacks.

Pseudo label based semi-supervised learning (SSL) for single-label and multilabel classification tasks has been extensively studied; however, semi-supervised label distribution learning (SSLDL) remains a largely unexplored area. Existing SSL methods fail in SSLDL because the pseudo-labels they generate only ensure overall similarity to the ground truth but do not preserve the ranking relationships between true labels, as they rely solely on KL divergence as the loss function during training. These skewed pseudo-labels lead the model to learn incorrect semantic relationships, resulting in reduced performance accuracy. To address these issues, we propose a novel SSLDL method called RankMatch. RankMatch fully considers the ranking relationships between different labels during the training phase with labeled data to generate higher-quality pseudo-labels. Furthermore, our key observation is that a flexible utilization of pseudo-labels can enhance SSLDL performance. Specifically, focusing solely on the ranking relationships between labels while disregarding their margins helps prevent model overfitting. Theoretically, we prove that incorporating ranking correlations enhances SSLDL performance and establish generalization error bounds for RankMatch.

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that the exemplar image-text pairs constitute two representations of an identical concept. However, recent research has revealed that real-world datasets often exhibit cross-modal misalignment. There are two distinct viewpoints on how to address this issue: one suggests mitigating the misalignment, and the other leveraging it. We seek here to reconcile these seemingly opposing perspectives, and to provide a practical guide for practitioners. Using latent variable models we thus formalize cross-modal misalignment by introducing two specific mechanisms: Selection bias, where some semantic variables are absent in the text, and perturbation bias, where semantic variables are altered--both leading to misalignment in data pairs. Our theoretical analysis demonstrates that, under mild assumptions, the representations learned by MMCL capture exactly the information related to the subset of the semantic variables invariant to selection and perturbation biases. This provides a unified perspective for understanding misalignment. Based on this, we further offer actionable insights into how misalignment should inform the design of real-world ML systems.

In the zero-shot policy transfer setting in reinforcement learning, the goal is to train an agent on a fixed set of training environments so that it can generalise to similar, but unseen, testing environments. Previous work has shown that policy distillation after training can sometimes produce a policy that outperforms the original in the testing environments. However, it is not yet entirely clear why that is, or what data should be used to distil the policy. In this paper, we prove, under certain assumptions, a generalisation bound for policy distillation after training. The theory provides two practical insights: for improved generalisation, you should 1) train an ensemble of distilled policies, and 2) distil it on as much data from the training environments as possible. We empirically verify that these insights hold in more general settings, when the assumptions required for the theory no longer hold. Finally, we demonstrate that an ensemble of policies distilled on a diverse dataset can generalise significantly better than the original agent.

Cybersecurity agencies from the Five Eyes alliance have issued a joint statement on AI after the US blocked Anthropic's much-hyped Fable. Cybersecurity agencies from the Five Eyes alliance have issued a joint statement on AI after the US blocked Anthropic's much-hyped Fable. Signal agencies in Australia, the US, the UK, New Zealand and Canada sound alarm after Trump blocks foreign nationals from Anthropic's Fable AI model Powerful AI models capable of devastating new cyber attacks on governments and businesses are mere months away, intelligence agencies for the Five Eyes have warned in a rare joint statement, urging leaders to "act now". The surprising public intervention by signals agencies for Australia, the US, the UK, New Zealand and Canada comes after the Trump administration earlier this month decided to block "foreign nationals" from using a much-hyped AI model built by tech company Anthropic, called Fable. The statement, issued late on Monday night, Sydney time, said while AI "would help us improve cyber defence over time, it also accelerates the speed, scale, and sophistication of cyber threats".

Where does'A man is walking in a Locate the moment where "A man For the query'A man recommends narrow alley, with street noise and Determine the precise timestamp in wearing a white mask is speaking visiting local areas in Tokyo, filming the conversations in the background.

There are about 160 datacentres operating in Australia, with another 90 proposed. There are about 160 datacentres operating in Australia, with another 90 proposed. They're a key part of the digital and AI economy, but they come at a high environmental cost and offer few operational jobs Sun 21 Jun 2026 11.00 EDTLast modified on Sun 21 Jun 2026 11.01 EDT On Mamre Road, in Sydney's outer western suburbs, there are plans to build a "hyperscale" datacentre that will be one of the biggest in the world. If approved, the 52-hectare site will include six four-storey buildings that stretch 40 metres high, alongside 936 cooling units and 852 diesel backup power generators. The Mamre Road project is part of an estimated $155bn investment pipeline over the coming decade, amid a worldwide rush to build the infrastructure enabling the artificial intelligence revolution.