I own 20 axolotls - people need to know they're not easy to look after When Emma Honeyfield's daughter Amber asked for an axolotl for her birthday, Emma never imagined it would lead to a collection of 20. The 37-year-old bought her daughter's first axolotl, Stitch, in September and has since fallen in love with their calming nature. Emma said Amber, eight, had always been difficult to buy for, so when she asked for one for her birthday, she couldn't say no. And the family, from Tredegar, Blaenau Gwent, are far from alone in seeking out the amphibians, which are critically endangered and only found in lakes and wetlands in southern Mexico City . The animal's cute, smiling face and appearance in the hugely popular Minecraft and Roblox games has seen an increase in the number of people keeping them as pets.

A still from animated film La Sélection Mécanique, directed by Jules Blachier. A still from animated film La Sélection Mécanique, directed by Jules Blachier. While emerging technology is banned from the Palme d'Or, an upstart movement is gaining investment and attention I n Cannes' darkened screening rooms, the supposed future of cinema flickered into life this week and it was strange. The first edition of the World AI film festival (WAIFF) showcased visions of men with fish scales erupting from their necks and seaweed from their mouths, a heroine with a heart beating outside her body and so many massed armies of AI-generated tanned men sweeping across battlefields that David Lean would have blushed. Last week the Cannes film festival, entering its 76th year, banned the emerging technology from its Palme d'Or competition, insisting "AI imitates very well but it will never feel deep emotions".

The 31-year-old engineer and self-described indie game developer is suspected of firing shots at the annual event attended by President Donald Trump, high-profile media figures, and US government officials. US President Donald Trump listens as acting attorney general Todd Blanche speaks during a press briefing shortly after a shooting incident at the White House Correspondents' Dinner on April 25, 2026. A 31-year-old engineer and computer scientist was identified by media reports and President Donald Trump as the suspected shooter at the White House Correspondents Dinner on Saturday night. Cole Tomas Allen, of Torrance, California, was apprehended following the firing of shots at the Washington Hilton, where Trump was scheduled to deliver remarks to a ballroom full of journalists, cabinet officials, and Hilton staff. Allen's name surfaced in media reports shortly before Trump posted two photos of a suspect following his apprehension.

Artificial neural networks for motor control usually adopt generic architectures like fully connected MLPs. While general, these tabula rasa architectures rely on large amounts of experience to learn, are not easily transferable to new bodies, and have internal dynamics that are difficult to interpret. In nature, animals are born with highly structured connectivity in their nervous systems shaped by evolution; this innate circuitry acts synergistically with learning mechanisms to provide inductive biases that enable most animals to function well soon after birth and learn efficiently. Convolutional networks inspired by visual circuitry have encoded useful biases for vision. However, it is unknown the extent to which ANN architectures inspired by neural circuitry can yield useful biases for other AI domains. In this work, we ask what advantages biologically inspired ANN architecture can provide in the domain of motor control.

Linear sketches have been widely adopted to process fast data streams, and they can be used to accurately answer frequency estimation, approximate top K items, and summarize data distributions. When data are sensitive, it is desirable to provide privacy guarantees for linear sketches to preserve private information while delivering useful results with theoretical bounds. We show that linear sketches can ensure privacy and maintain their unique properties with a small amount of noise added at initialization. From the differentially private linear sketches, we showcase that the state-of-the-art quantile sketch in the turnstile model can also be private and maintain high performance. Experiments further demonstrate that our proposed differentially private sketches are quantitatively and qualitatively similar to noise-free sketches with high utilization on synthetic and real datasets.

Monocular 3D detection of vehicle and infrastructure sides are two important topics in autonomous driving. Due to diverse sensor installations and focal lengths, researchers are faced with the challenge of constructing algorithms for the two topics based on different prior knowledge. In this paper, by taking into account the diversity of pitch angles and focal lengths, we propose a unified optimization target named normalized depth, which realizes the unification of 3D detection problems for the two sides. Furthermore, to enhance the accuracy of monocular 3D detection, 3D normalized cube depth of obstacle is developed to promote the learning of depth information. We posit that the richness of depth clues is a pivotal factor impacting the detection performance on both the vehicle and infrastructure sides. A richer set of depth clues facilitates the model to learn better spatial knowledge, and the 3D normalized cube depth offers sufficient depth clues. Extensive experiments demonstrate the effectiveness of our approach. Without introducing any extra information, our method, named MonoUNI, achieves state-of-the-art performance on five widely used monocular 3D detection benchmarks, including Rope3D and DAIR-V2X-I for the infrastructure side, KITTI and Waymo for the vehicle side, and nuScenes for the cross-dataset evaluation.

Our main reconstruction loss is an MSE between the rendered color c and the corresponding pixel in the input image. This loss is then exponentially faded over 100,000 steps to a cosine weighted MSE: (x ωo n ˆxωo n)2. This weighting tends to achieve better BRDF fitting results [4] as harsh grazing highlights from the Fresnel effect are not factored as much as regular samples, as well as our approximated rendering model being the least accurate in the grazing angles. The reason for this fading loss scheme is that the normals nare not reliable in the early stages of the training.

Neural networks are known to be vulnerable to adversarial attacks - slight but carefully constructed perturbations of the inputs which can drastically impair the network's performance. Many defense methods have been proposed for improving robustness of deep networks by training them on adversarially perturbed inputs. However, these models often remain vulnerable to new types of attacks not seen during training, and even to slightly stronger versions of previously seen attacks. In this work, we propose a novel approach to adversarial robustness, which builds upon the insights from the domain adaptation field. Our method, called Adversarial Feature Desensitization (AFD), aims at learning features that are invariant towards adversarial perturbations of the inputs. This is achieved through a game where we learn features that are both predictive and robust (insensitive to adversarial attacks), i.e. cannot be used to discriminate between natural and adversarial data. Empirical results on several benchmarks demonstrate the effectiveness of the proposed approach against a wide range of attack types and attack strengths. Our code is available at https://github.com/BashivanLab/afd.