The special Galilean group, usually denoted SGal(3), is a 10-dimensional Lie group whose important subgroups include the special orthogonal group, the special Euclidean group, and the group of extended poses. We briefly describe SGal(3) and its Lie algebra and show how the group structure supports a unified representation of uncertainty in space and time. Our aim is to highlight the potential usefulness of this group for several robotics problems.

In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model internal information or have limitations when exploring the unsafe behavior of the victim model, limiting their reducing their general applicability. In this paper, we introduce PathSeeker, a novel black-box jailbreak method, which is inspired by the game of rats escaping a maze. We think that each LLM has its unique "security maze", and attackers attempt to find the exit learning from the received feedback and their accumulated experience to compromise the target LLM's security defences. Our approach leverages multi-agent reinforcement learning, where smaller models collaborate to guide the main LLM in performing mutation operations to achieve the attack objectives. By progressively modifying inputs based on the model's feedback, our system induces richer, harmful responses. During our manual attempts to perform jailbreak attacks, we found that the vocabulary of the response of the target model gradually became richer and eventually produced harmful responses. Based on the observation, we also introduce a reward mechanism that exploits the expansion of vocabulary richness in LLM responses to weaken security constraints. Our method outperforms five state-of-the-art attack techniques when tested across 13 commercial and open-source LLMs, achieving high attack success rates, especially in strongly aligned commercial models like GPT-4o-mini, Claude-3.5, and GLM-4-air with strong safety alignment. This study aims to improve the understanding of LLM security vulnerabilities and we hope that this sturdy can contribute to the development of more robust defenses.

Prevailing batch Bayesian optimisation methods allow all control variables to be freely altered at each iteration. Real-world experiments, however, often have physical limitations making it time-consuming to alter all settings for each recommendation in a batch. This gives rise to a unique problem in BO: in a recommended batch, a set of variables that are expensive to experimentally change need to be fixed, while the remaining control variables can be varied. We formulate this as a process-constrained batch Bayesian optimisation problem. We propose two algorithms, pc-BO(basic) and pc-BO(nested).

Neural Information Processing Systems http://nips.cc/

We study the problem of learning probabilistic first-order logical rules for knowledge base reasoning. This learning problem is difficult because it requires learning the parameters in a continuous space as well as the structure in a discrete space. We propose a framework, Neural Logic Programming, that combines the parameter and structure learning of first-order logical rules in an end-to-end differentiable model. This approach is inspired by a recently-developed differentiable logic called TensorLog [5], where inference tasks can be compiled into sequences of differentiable operations. We design a neural controller system that learns to compose these operations. Empirically, our method outperforms prior work on multiple knowledge base benchmark datasets, including Freebase and WikiMovies.

World leaders at the next AI summit will focus on the impact on the environment and jobs, including the possibility of ranking the greenest AI companies, it has been announced. Rating artificial intelligence companies in terms of their ecological impact is among the proposals under consideration, while other areas being looked at include the effect on the labour market, giving all countries access to the technology and bringing more states under the wing of global AI governance initiatives. France will host the next global summit on 10 and 11 February, with international politicians expected to attend alongside tech executives and experts. Anne Bouverot, Paris's special envoy for AI, said discussions will include measuring the technology's impact on the environment. "We'll definitely push for more transparency by all players and maybe a way to do that is to have a ranking or leaderboard," she said, adding that such a system would highlight companies that are not transparent about their environmental impact.

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be acquired, stored and processed. Therefore a reasonable alternative is to be able to automatically generate new annotated training samples using a process known as data augmentation. The dominant data augmentation approach in the field assumes that new training samples can be obtained via random geometric or appearance transformations applied to annotated training samples, but this is a strong assumption because it is unclear if this is a reliable generative model for producing new training samples. In this paper, we provide a novel Bayesian formulation to data augmentation, where new annotated training points are treated as missing variables and generated based on the distribution learned from the training set. For learning, we introduce a theoretically sound algorithm -- generalised Monte Carlo expectation maximisation, and demonstrate one possible implementation via an extension of the Generative Adversarial Network (GAN). Classification results on MNIST, CIFAR-10 and CIFAR-100 show the better performance of our proposed method compared to the current dominant data augmentation approach mentioned above -- the results also show that our approach produces better classification results than similar GAN models.

Dolphins seem to make open-mouthed facial expressions most often while they are visible to a playmate, suggesting such displays may be similar to human smiles. While we often perceive these as a smile, there has been little research on facial communication in dolphins. We're finally realising that many species are To find out more, Elisabetta Palagi at the University of Pisa, Italy, and her colleagues analysed the behaviour of 22 captive bottlenose dolphins (Tursiops truncatus) at two wildlife parks: Zoomarine Rome in Italy and Planète Sauvage in Port-Saint-Père, France. In 80 hours of footage, the team observed a total of 1288 open-mouth expressions during social play sessions. More than 90 per cent of these events occurred during play between dolphins, with the rest happening during interactions between the dolphins and people.

Meta has started notifying Instagram and Facebook users across the UK that it is training its AI with their posts – and people are not happy about it. In emails and notifications being sent to UK users, Meta says it's using posts, comments, photos and even captions to help develop its human-like'generative AI', akin to ChatGPT. By being trained with UK user data, Meta told MailOnline that the AI will'reflect and understand British language, geography and culture'. Social media users are fuming over the controversial move, with one person saying the tech giant can'f*** right off'. If you don't want your personal data being handed over to Meta's AI training programme, here's how you can object.

Australians could see fewer deepfake images of celebrities being hauled off in handcuffs, or promoting a fraudulent cryptocurrency investment on Facebook, after Meta launched a new one-stop shop for banks to share information on scams that has blocked 8,000 pages and 9,000 celebrity scams in its first six months of operation. From January to August 2024, Australians reported 43.4m in losses from scams on social media to Scamwatch, with close to 30m relating to fake investment scams. Meta, the parent company of Facebook and Instagram, has faced pressure from politicians and regulators in the past few years to tackle the plague of scams featuring deepfake images of public figures such as David Koch, Gina Rinehart, Anthony Albanese, Larry Emdur, Guy Sebastian and others which are used to promote investment scams. The company is being sued by the mining magnate Andrew Forrest over the company's alleged failure to tackle scams using his image. Meta announced on Wednesday it had partnered with the Australian Financial Crimes Exchange (AFCX) to launch the Fraud Intelligence Reciprocal Exchange (Fire) that provides a dedicated reporting channel for scams between Meta and financial providers of the victims of the scams.