Finding optimal treatment plans in continuous time is crucial for personalized medicine. Existing methods, however, do not explicitly optimize treatment plans and instead focus solely on predicting treatment effects. Naive optimization over these treatment-response models can exploit model errors, resulting in plans that appear optimal under the learned model but perform poorly in practice. To mitigate model exploitation, we propose SigCTO (Signature-based Conservative Treatment Optimization), a conservative framework for continuous-time treatment optimization. We derive a path-space regularizer based on signature-kernel maximum mean discrepancy that penalizes treatment plans for which predicted and true responses differ. Under suitable assumptions, the regularizer allows for consistent estimation, and the regularized objective upper bounds the true treatment cost. Experiments on pharmacometric simulators show that SigCTO finds treatment plans with lower ground-truth costs than state-of-the-art baselines. On real-world ICU data, SigCTO predicts treatment cost more accurately than baselines, and the regularizer detects prediction errors.
Recognising intentions from continuous movement trajectories is an important problem in spatiotemporal data mining. This becomes difficult when behaviours change over time and their boundaries cannot be directly observed. Football provides a useful setting for studying this problem because tactical intentions emerge from the coordinated movements of multiple players during possession. Existing methods for match phase recognition often classify individual frames, use predefined spatial rules, or identify only selected tactical patterns. They therefore cannot fully describe continuous possession sequences in which tactical intentions change over time. We address this gap by treating the identification of the in-possession match phase as a hierarchical sequence segmentation task. The framework includes three tactical intentions (Invade Opponent Space, Keep Possession, and Scoring) and six phases (Build Up, Progression, Counter Attack, Maintenance, Sustained Threat, and Finishing). We propose a Temporal Graph Attention Network (T-GAN) that combines player interaction graphs, contextual features, and Transformer based temporal modelling. The framework was evaluated on seven Bundesliga matches using leave-one-match-out validation and compared with rule-based, Random Forest, GNN, and Transformer baselines at both frame and sequence levels. The results show that temporal modelling is important for coherent phase segmentation, while graph modelling provides additional value for transition phases such as Counter Attack. The framework provides an interpretable method for discovering intention based behavioural segments from continuous player tracking data and supports automated tactical analysis in football.
Realistic patient simulation is a key requirement for developing and testing clinical LLMs at scale without costly user studies. Existing simulators lack realism and controllability: they overshare information and miss the variability of real patient behavior. Here, we introduce PatientsWithPersonality (PWP), a patient simulation framework that generates realistic yet diverse patient responses through explicit personality parametrization over a latent patient state. Grounded in the six-dimensional HEXACO personality model, it gives fine-grained control over conversational style, cooperativeness, and information disclosure. We evaluate PWP in the first direct comparison of different patient simulators under a shared protocol, anchored in transcripts of real physician-patient encounters. Clinicians judge PWP conversations as realistic at least as often as the recorded encounters themselves and far more often than prior simulators, and almost never flag them as "too informative". Our simulator also reproduces the disclosure pacing of real patients, and its HEXACO-conditioned personality traits can be recovered by clinicians and an autorater. PWP further shows a substantially wider behavioral range than the closest baseline. In a downstream benchmark, LLMs interviewing patients simulated by PWP perform closest to how they perform on the real encounters, whereas prior simulators make the task easier. PWP thus provides a realistic, steerable, and diverse patient population for improving and benchmarking clinical LLMs.
Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp radial depth discontinuities, yielding edge depths that back-project to points floating between surfaces. We identify this as a major, directly correctable decoder bottleneck and introduce CRISP: a pixel-space diffusion decoder with a backbone-agnostic latent adapter, DiT-based denoiser, and support mask predictor. CRISP replaces video-VAE and LiDAR-native decoders alike while keeping the encoder and latent generator fixed. Across KITTI-360, SemanticKITTI, and nuScenes, replacing only the decoder reduces FSVD/FPVD by 50.5% on average across frozen backbones; for generic video VAEs, the reductions reach 71%/74%. On the LiDAR-native LiDM backbone, FRID drops by 71%, with the largest gains at depth discontinuities. In a pretrained LiDM world model, the same zero-shot replacement improves FSVD by 15.5%, narrowing the sim-to-real gap. Code and checkpoints will be released at https://andrea25512.github.io/CRISP/.
As enduring carbon sinks, forest ecosystems are vital to the terrestrial carbon cycle and help moderate global warming. However, the long-term dynamics of aboveground carbon (AGC) in forests and their sink-source transitions remain highly uncertain, owing to changing disturbance regimes and inconsistencies in observations, data processing, and analysis methods. Here, we derive reliable, harmonized AGC stocks and fluxes in global forests from 1988 to 2021 at high spatial resolution by integrating multi-source satellite observations with probabilistic deep learning models. Our approach simultaneously estimates AGC and associated uncertainties, showing high reliability across space and time. We find that, although global forests remained an AGC sink of 6.2 PgC over 30 years, moist tropical forests shifted to a substantial AGC source between 2001 and 2010 and, together with boreal forests, transitioned toward a source in the 2011-2021 period. Temperate, dry tropical and subtropical forests generally exhibited increasing AGC stocks, although Europe and Australia became sources after 2011. Regionally, pronounced sink-to-source transitions occurred in tropical forests over the past three decades. The interannual relationship between global atmospheric CO2 growth rates and tropical AGC flux variability became increasingly negative, reaching Pearson's r = -0.63 (p < 0.05) in the most recent decade. In the Brazilian Amazon, the contribution of deforested regions to AGC losses declined from 60% in 1989-2000 to 13% in 2011-2021, while the share from untouched areas increased from 33% to 76%. Our findings suggest a growing role of tropical forest AGC in modulating variability in the terrestrial carbon cycle, with anthropogenic climate change potentially contributing increasingly to AGC changes, particularly in previously untouched areas.
Time series classification is a fundamental task in healthcare and industry, yet the development of time series foundation models (TSFMs) remains limited by the scarcity of publicly available time series datasets. In this work, we propose Time Vision Transformer (TiViT), a framework that converts time series into images to leverage the representational power of frozen Vision Transformers (ViTs) pretrained on large-scale image datasets. First, we theoretically motivate our approach by analyzing the 2D patching of ViTs for time series, showing that it can increase the number of label-relevant tokens and reduce the sample complexity. Second, we empirically demonstrate that TiViT achieves state-of-the-art performance on standard time series classification benchmarks by utilizing the hidden representations of large OpenCLIP models. We explore the structure of TiViT representations and find that intermediate layers with high intrinsic dimension are the most effective for time series classification. Finally, we assess the alignment between TiViT and TSFM representation spaces and identify a strong complementarity, with further performance gains achieved by combining their features. Our findings reveal yet another direction for reusing vision representations in a non-visual domain.
We propose a deep product-unit residual neural network (PURe) that integrates product units into residual blocks to improve the expressiveness and parameter efficiency of deep convolutional networks. Unlike standard summation neurons, product units enable multiplicative feature interactions, potentially offering a more powerful representation of complex patterns. PURe replaces conventional convolutional layers with 2D product units in the second layer of each residual block, eliminating nonlinear activation functions to preserve structural information. We validate PURe on three benchmark datasets. On Galaxy10 DECaLS, PURe34 achieves the highest test accuracy of 84.89%, surpassing the much deeper ResNet152, while converging nearly five times faster and demonstrating strong robustness to Poisson noise. On ImageNet, PURe architectures outperform standard ResNet models at similar depths, with PURe34 achieving a top-1 accuracy of 80.27% and top-5 accuracy of 95.78%, surpassing deeper ResNet variants (ResNet50, ResNet101) while utilizing significantly fewer parameters and computational resources. On CIFAR-10, PURe consistently outperforms ResNet variants across varying depths, with PURe272 reaching 95.01% test accuracy, comparable to ResNet1001 but at less than half the model size. These results demonstrate that PURe achieves a favorable balance between accuracy, efficiency, and robustness. Compared to traditional residual networks, PURe not only achieves competitive classification performance with faster convergence and fewer parameters, but also demonstrates greater robustness to noise. Its effectiveness across diverse datasets highlights the potential of product-unit-based architectures for scalable and reliable deep learning in computer vision.
Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as low experimental hit rates as well as the need for nuanced controllability and efficient modeling of peptide properties. To address these challenges, we introduce OmegAMP, a framework that leverages a diffusion-based generative model with efficient low-dimensional embeddings, precise controllability mechanisms, and novel classifiers with drastically reduced false positive rates for candidate filtering. OmegAMP enables the targeted generation of AMPs with specific physicochemical properties, activity profiles, and species-specific effectiveness. Moreover, it maximizes sample diversity while ensuring faithfulness to the underlying data distribution during generation. We demonstrate that OmegAMP achieves state-of-the-art performance across all stages of the AMP discovery pipeline, significantly advancing the potential of computational frameworks in combating antimicrobial resistance.
We investigate tasks that can be accomplished with unlabelled graphs, where nodes do not have persistent or semantically meaningful labels. New techniques to visualize these graphs have been proposed, but more understanding of unlabelled graph tasks is required before they can be adequately evaluated. Some tasks apply to both labelled and unlabelled graphs, but many do not translate between these contexts. We propose a taxonomy of unlabelled graph abstract tasks, organized according to the Scope of the data at play, the Action intended by the user, and the Target data under consideration. We show the descriptive power of this task abstraction by connecting to concrete examples from previous frameworks, and connect these abstractions to real-world problems. To showcase the evaluative power of the taxonomy, we perform a preliminary assessment of 6 visualizations for each task. For each combination of task and visual encoding, we consider the effort required from viewers, the likelihood of task success, and how both factors vary between small-scale and large-scale graphs.
Scenario-based testing with driving simulators is extensively used to identify failing conditions of automated driving assistance systems (ADAS) and reduce the amount of in-field road testing. However, existing studies have shown that repeated test execution in the same as well as in distinct simulators can yield different outcomes, which can be attributed to sources of flakiness or different implementations of the physics, among other factors. In this paper, we present MultiSim, a novel approach to multi-simulation ADAS testing based on a search-based testing approach that leverages an ensemble of simulators to identify failure-inducing, simulator-agnostic test scenarios. During the search, each scenario is evaluated jointly on multiple simulators. Scenarios that produce consistent results across simulators are prioritized for further exploration, while those that fail on only a subset of simulators are given less priority, as they may reflect simulator-specific issues rather than generalizable failures. Our case study, which involves testing a deep neural network-based ADAS on different pairs of three widely used simulators, demonstrates that MultiSim outperforms single-simulator testing by achieving on average a higher rate of simulator-agnostic failures by 51%. Compared to a state-of-the-art multi-simulator approach that combines the outcome of independent test generation campaigns obtained in different simulators, MultiSim identifies 54% more simulator-agnostic failing tests while showing a comparable validity rate. An enhancement of MultiSim that leverages surrogate models to predict simulator disagreements and bypass executions does not only increase the average number of valid failures but also improves efficiency in finding the first valid failure.
Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence. The scaling of these models, accomplished by increasing the number of parameters and the magnitude of the training datasets, has been linked to various so-called emergent abilities that were previously unobserved. These emergent abilities, ranging from advanced reasoning and in-context learning to coding and problem-solving, have sparked an intense scientific debate: Are they truly emergent, or do they simply depend on external factors, such as training dynamics, the type of problems, or the chosen metric? What underlying mechanism causes them? Despite their transformative potential, emergent abilities remain poorly understood, leading to misconceptions about their definition, nature, predictability, and implications. In this work, we shed light on emergent abilities by conducting a comprehensive review of the phenomenon, addressing both its scientific underpinnings and real-world consequences. We first critically analyze existing definitions, exposing inconsistencies in conceptualizing emergent abilities. We then explore the conditions under which these abilities appear, evaluating the role of scaling laws, task complexity, pre-training loss, quantization, and prompting strategies. Our review extends beyond traditional LLMs and includes Large Reasoning Models (LRMs), which leverage reinforcement learning and inference-time search to amplify reasoning and self-reflection. However, emergence is not inherently positive. As AI systems gain autonomous reasoning capabilities, they also develop harmful behaviors, including deception, manipulation, and reward hacking. We highlight growing concerns about safety and governance, emphasizing the need for better evaluation frameworks and regulatory oversight.
We propose a new approach to falsify causal discovery algorithms without ground truth, which is based on testing the causal model on a pair of variables that has been dropped when learning the causal model. To this end, we use the "Leave-One-Variable-Out (LOVO)" prediction where $Y$ is inferred from $X$ without any joint observations of $X$ and $Y$, given only training data from $X,Z_1,\dots,Z_k$ and from $Z_1,\dots,Z_k,Y$. We demonstrate that causal models on the two subsets, in the form of Acyclic Directed Mixed Graphs (ADMGs), often entail conclusions on the dependencies between $X$ and $Y$, enabling this type of prediction. The prediction error can then be estimated since the joint distribution $P(X, Y)$ is assumed to be available, and $X$ and $Y$ have only been omitted for the purpose of falsification. After presenting this graphical method, which is applicable to general causal discovery algorithms, we illustrate how to construct a LOVO predictor tailored towards algorithms relying on specific a priori assumptions, such as linear additive noise models. Simulations indicate that the LOVO prediction error is indeed correlated with the accuracy of the causal outputs, affirming the method's effectiveness.
Decision Trees are one of the backbones of explainable machine learning, and often serve as interpretable alternatives to black-box models. Traditionally utilized in the supervised setting, there has recently also been a surge of interest in decision trees for unsupervised learning. While several works with worst-case guarantees on the clustering cost have appeared, these results are distribution-agnostic, and do not give insight into when decision trees can actually recover the underlying distribution of the data (up to some small error). In this paper, we therefore introduce the notion of an explainability-to-noise ratio for mixture models, formalizing the intuition that well-clustered data can indeed be explained well using a decision tree. We propose an algorithm that takes as input a mixture model and constructs a suitable tree in data-independent time. Assuming sub-Gaussianity of the mixture components, we prove upper and lower bounds on the error rate of the resulting decision tree. In addition, we demonstrate how concept activation vectors can be used to extend explainable clustering to neural networks. We empirically demonstrate the efficacy of our approach on standard tabular and image datasets.
Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. Training such networks with backpropagation through time is a notoriously difficult problem because their loss gradients tend to explode or vanish. In this contribution, we introduce a computational approach to construct all weights and biases of a recurrent neural network without using gradient-based methods. The approach is based on a combination of random feature networks and Koopman operator theory for dynamical systems. The hidden parameters of a single recurrent block are sampled at random, while the outer weights are constructed using extended dynamic mode decomposition. This approach alleviates all problems with backpropagation commonly related to recurrent networks. The connection to Koopman operator theory also allows us to start using results in this area to analyze recurrent neural networks. In computational experiments on time series, forecasting for chaotic dynamical systems, and control problems, as well as on weather data, we observe that the training time and forecasting accuracy of the recurrent neural networks we construct are improved when compared to commonly used gradient-based methods.