The heterogeneity of neurological and mental health disorders has been a key confound to disease understanding, treatment development and outcome prediction, as patient populations are thought to include multiple disease pathways that selectively respond to treatment (Kapur et al., 2012). These challenges are reflected in poor treatment outcomes; for instance, in depression, approximately only 40% of patients remit after first-line antidepressant treatment or psychotherapy (Amick et al., 2015; Cuijpers et al., 2014; Fava and Davidson, 1996; Trivedi et al., 2006). Diagnostic categories in psychiatry have historically been defined based on signs and symptoms, prioritising diagnostic agreement between clinicians, rather than underlying biological mechanisms (Freedman et al., 2013; Robins and Guze, 1970). Resultingly, the usefulness of supervised machine learning methods as diagnostic tools for mental health disorders (i.e., classifying patients vs. healthy controls) is questionable, as they may simply inherit the flaws of current diagnostic categories. Additional challenges in neurological and mental health disorders are comorbidity (i.e., individuals with one disorder often develop another disorder during their lifespan) and that different disorders can share similar symptoms (Kessler et al., 2005). To address the limitations of current diagnostic categories in psychiatry, the National Institute of Mental Health launched the Research Domain Criteria framework (RDoC) in 2009 (https://www.nimh.nih.gov/research/ 2 research-funded-by-nimh/rdoc) as an attempt to move beyond diagnostic categories and ground psychiatry within neurobiological constructs that combine multiple levels of measures or sources of information (Insel et al., 2010). Multivariate methods, such as Canonical Correlation Analysis (CCA) and related methods, that do not rely on the diagnostic categories, have been widely used to uncover latent disease dimensions capturing associations between brain imaging and non-imaging data (e.g., self-report questionnaires, cognitive tests and genetics). The identified latent dimensions provide information on how a set of non-imaging features (e.g.

Hallucinations (i.e., generating plausible but inaccurate content) and laziness (i.e. excessive refusals or defaulting to "I don't know") persist as major challenges in LLM reasoning. Current efforts to reduce hallucinations primarily focus on factual errors in knowledge-grounded tasks, often neglecting hallucinations related to faulty reasoning. Meanwhile, some approaches render LLMs overly conservative, limiting their problem-solving capabilities. To mitigate hallucination and laziness in reasoning tasks, we propose Automatic Curriculum Expert Iteration (Auto-CEI) to enhance LLM reasoning and align responses to the model's capabilities--assertively answering within its limits and declining when tasks exceed them. In our method, Expert Iteration explores the reasoning trajectories near the LLM policy, guiding incorrect paths back on track to reduce compounding errors and improve robustness; it also promotes appropriate "I don't know" responses after sufficient reasoning attempts. The curriculum automatically adjusts rewards, incentivizing extended reasoning before acknowledging incapability, thereby pushing the limits of LLM reasoning and aligning its behaviour with these limits. We compare Auto-CEI with various SOTA baselines across logical reasoning, mathematics, and planning tasks, where Auto-CEI achieves superior alignment by effectively balancing assertiveness and conservativeness.

Many important problems require modelling large-scale spatio-temporal datasets, with one prevalent example being weather forecasting. Recently, transformer-based approaches have shown great promise in a range of weather forecasting problems. However, these have mostly focused on gridded data sources, neglecting the wealth of unstructured, off-the-grid data from observational measurements such as those at weather stations. A promising family of models suitable for such tasks are neural processes (NPs), notably the family of transformer neural processes (TNPs). Although TNPs have shown promise on small spatio-temporal datasets, they are unable to scale to the quantities of data used by state-of-the-art weather and climate models. This limitation stems from their lack of efficient attention mechanisms. We address this shortcoming through the introduction of gridded pseudo-token TNPs which employ specialised encoders and decoders to handle unstructured observations and utilise a processor containing gridded pseudo-tokens that leverage efficient attention mechanisms. Our method consistently outperforms a range of strong baselines on various synthetic and real-world regression tasks involving large-scale data, while maintaining competitive computational efficiency. The real-life experiments are performed on weather data, demonstrating the potential of our approach to bring performance and computational benefits when applied at scale in a weather modelling pipeline.

The increased adoption of diffusion models in text-to-image generation has triggered concerns on their reliability. Such models are now closely scrutinized under the lens of various metrics, notably calibration, fairness, or compute efficiency. We focus in this work on two issues that arise when deploying these models: a lack of diversity when prompting images, and a tendency to recreate images from the training set. To solve both problems, we propose a method that coaxes the sampled trajectories of pretrained diffusion models to land on images that fall outside of a reference set. We achieve this by adding repellency terms to the diffusion SDE throughout the generation trajectory, which are triggered whenever the path is expected to land too closely to an image in the shielded reference set. Our method is sparse in the sense that these repellency terms are zero and inactive most of the time, and even more so towards the end of the generation trajectory. Our method, named SPELL for sparse repellency, can be used either with a static reference set that contains protected images, or dynamically, by updating the set at each timestep with the expected images concurrently generated within a batch. We show that adding SPELL to popular diffusion models improves their diversity while impacting their FID only marginally, and performs comparatively better than other recent training-free diversity methods. We also demonstrate how SPELL can ensure a shielded generation away from a very large set of protected images by considering all 1.2M images from ImageNet as the protected set. Diffusion models (Song et al., 2021; Ho et al., 2020) are by now widely used for engineering and scientific tasks, to generate realistic signals (Esser et al., 2024) or structured data (Jo et al., 2022; Chamberlain et al., 2021). Diffusion models build upon a strong theoretical foundation used to guide parameter tuning (Kingma & Gao, 2023) and network architectures (Rombach et al., 2022), and are widely adopted thanks to cutting-edge open-source implementations. As these models gain applicability to a wide range of problems, their deployment reveals important challenges.

We provide practical, efficient, and nonparametric methods for auditing the fairness of deployed classification and regression models. Whereas previous work relies on a fixed-sample size, our methods are sequential and allow for the continuous monitoring of incoming data, making them highly amenable to tracking the fairness of real-world systems. We also allow the data to be collected by a probabilistic policy as opposed to sampled uniformly from the population. This enables auditing to be conducted on data gathered for another purpose. Moreover, this policy may change over time and different policies may be used on different subpopulations. Finally, our methods can handle distribution shift resulting from either changes to the model or changes in the underlying population.

Meta, the owner of Facebook and Instagram, has launched its artificial intelligence assistant in the UK, alongside AI-boosted sunglasses modelled by Mark Zuckerberg. Meta's AI assistant, which can generate text and images, is now available on its social media platforms in the UK and Brazil, having already been launched in the US and Australia. Regulatory issues and product testing held up the UK launch, while Meta's AI services remain unavailable in the EU due to the "unpredictable" regulatory environment. Facebook and Instagram users in the UK will now be able to access the Meta AI chatbot by tapping on an icon in their app or by buying a pair of 299 Ray-Ban Meta frames from a UK retailer and accessing its voice assistant. Zuckerberg, Meta's co-founder, sported a pair of the Ray-Bans at a company event last month when he also announced that Meta AI would be able to respond to voice commands and use the voice of celebrities including Judi Dench, John Cena and Keegan-Michael Key.

And if you use Instagram, Facebook and Messenger, you may notice a new purple-blue ring icon from today. Tapping this icon will open Meta's AI chatbot, Meta AI, which has launched in the UK today. This free AI tool is built in to Meta's apps, and will allow you to do everything from generate fake images, to plan dinners based on what's in your fridge. Here's how it works - and how you can try the AI tool through your favourite social media platform. To access the tool, open Instagram, Facebook or Messenger and tap the round blue and purple ring icon.

Meta AI is beginning a big international rollout. The AI assistant will arrive today in Brazil, Bolivia, Guatemala, Paraguay, Philippines and the UK. It is also slated to debut in Algeria, Egypt, Indonesia, Iraq, Jordan, Libya, Malaysia, Morocco, Saudi Arabia, Sudan, Thailand, Tunisia, United Arab Emirates, Vietnam and Yemen over the coming weeks, although the company did not offer specific dates for those countries. This expansion is also adding new language support to Meta AI. Starting today, it is getting support for Tagalog, while Arabic, Indonesian, Thai and Vietnamese will join the assistant "soon."

Deep neural networks set the state-of-the-art across many tasks in computer vision, but their generalization ability to simple image distortions is surprisingly fragile. In contrast, the mammalian visual system is robust to a wide range of perturbations. Recent work suggests that this generalization ability can be explained by useful inductive biases encoded in the representations of visual stimuli throughout the visual cortex. Here, we successfully leveraged these inductive biases with a multi-task learning approach: we jointly trained a deep network to perform image classification and to predict neural activity in macaque primary visual cortex (V1) in response to the same natural stimuli. We measured the out-of-distribution generalization abilities of our resulting network by testing its robustness to common image distortions.

We develop a general framework for agent abstraction based on the situation calculus and the ConGolog agent programming language. We assume that we have a high-level specification and a low-level specification of the agent, both represented as basic action theories. A refinement mapping specifies how each high-level action is implemented by a low-level ConGolog program and how each high-level fluent can be translated into a low-level formula. We define a notion of sound abstraction between such action theories in terms of the existence of a suitable bisimulation between their respective models. Sound abstractions have many useful properties that ensure that we can reason about the agent's actions (e.g., executability, projection, and planning) at the abstract level, and refine and concretely execute them at the low level. We also characterize the notion of complete abstraction where all actions (including exogenous ones) that the high level thinks can happen can in fact occur at the low level. To facilitate verifying that one has a sound/complete abstraction relative to a mapping, we provide a set of necessary and sufficient conditions. Finally, we identify a set of basic action theory constraints that ensure that for any low-level action sequence, there is a unique high-level action sequence that it refines. This allows us to track/monitor what the low-level agent is doing and describe it in abstract terms (i.e., provide high-level explanations, for instance, to a client or manager).