In the following, we use X P to denote that the random variable X follows the law P . See Figure 1a for an illustration of such a graph generated by the Stochastic Block Model. Interestingly, Newman [31] has shown that the modularity objective is the maximum likelihood of a variant of the SBM on two communities, with prescribed degree distribution. However, it leaves the natural question open of whether the Louvain heuristic on the SBM with two communities indeed converges to this solution (the hidden partition). Proving the convergence shows that Louvain's local decisions can indeed be powerful enough to reach the global optimum.

Graph neural networks (GNNs) have exhibited state-of-the-art performance across wide-range of domains such as recommender systems, material design, and drug repurposing. Yet message-passing GNNs suffer from over-squashing -- exponential compression of long-range information from distant nodes -- which limits expressivity. Rewiring techniques can ease this bottleneck; but their practical impacts are unclear due to the lack of a direct empirical over-squashing metric. We propose a rigorous, topology-focused method for assessing over-squashing between node pairs using the decay rate of their mutual sensitivity. We then extend these pairwise assessments to four graph-level statistics (prevalence, intensity, variability, extremity). Coupling these metrics with a within-graph causal design, we quantify how rewiring strategies affect over-squashing on diverse graph- and node-classification benchmarks. Our extensive empirical analyses show that most graph classification datasets suffer from over-squashing (but to various extents), and rewiring effectively mitigates it -- though the degree of mitigation, and its translation into performance gains, varies by dataset and method. We also found that over-squashing is less notable in node classification datasets, where rewiring often increases over-squashing, and performance variations are uncorrelated with over-squashing changes. These findings suggest that rewiring is most beneficial when over-squashing is both substantial and corrected with restraint -- while overly aggressive rewiring, or rewiring applied to minimally over-squashed graphs, is unlikely to help and may even harm performance. Our plug-and-play diagnostic tool lets practitioners decide -- before any training -- whether rewiring is likely to pay off.

Deep learning based diagnostic AI systems based on medical images are starting to provide similar performance as human experts. However these data hungry complex systems are inherently black boxes and therefore slow to be adopted for high risk applications like healthcare. This problem of lack of transparency is exacerbated in the case of recent large foundation models, which are trained in a self supervised manner on millions of data points to provide robust generalisation across a range of downstream tasks, but the embeddings generated from them happen through a process that is not interpretable, and hence not easily trustable for clinical applications. To address this timely issue, we deploy conformal analysis to quantify the predictive uncertainty of a vision transformer (ViT) based foundation model across patient demographics with respect to sex, age and ethnicity for the tasks of skin lesion classification using several public benchmark datasets. The significant advantage of this method is that conformal analysis is method independent and it not only provides a coverage guarantee at population level but also provides an uncertainty score for each individual. We used a model-agnostic dynamic F1-score-based sampling during model training, which helped to stabilize the class imbalance and we investigate the effects on uncertainty quantification (UQ) with or without this bias mitigation step. Thus we show how this can be used as a fairness metric to evaluate the robustness of the feature embeddings of the foundation model (Google DermFoundation) and thus advance the trustworthiness and fairness of clinical AI. Keywords: algorithmic fairness vision transformer (ViT) foundation models skin lesion classification conformal prediction uncertainty quantification transparent trustworthy AI class imbalance 1 Introduction Skin cancer remains a significant global health concern, with melanoma accounting for more than 5% of the total cancer cases diagnosed in the US and causing arXiv:2503.23819v1

Adaptive questionnaires dynamically select the next question for a survey participant based on their previous answers. Due to digitalisation, they have become a viable alternative to traditional surveys in application areas such as political science. One limitation, however, is their dependency on data to train the model for question selection. Often, such training data (i.e., user interactions) are unavailable a priori. To address this problem, we (i) test whether Large Language Models (LLM) can accurately generate such interaction data and (ii) explore if these synthetic data can be used to pre-train the statistical model of an adaptive political survey. To evaluate this approach, we utilise existing data from the Swiss Voting Advice Application (VAA) Smartvote in two ways: First, we compare the distribution of LLM-generated synthetic data to the real distribution to assess its similarity. Second, we compare the performance of an adaptive questionnaire that is randomly initialised with one pre-trained on synthetic data to assess their suitability for training. We benchmark these results against an "oracle" questionnaire with perfect prior knowledge. We find that an off-the-shelf LLM (GPT-4) accurately generates answers to the Smartvote questionnaire from the perspective of different Swiss parties. Furthermore, we demonstrate that initialising the statistical model with synthetic data can (i) significantly reduce the error in predicting user responses and (ii) increase the candidate recommendation accuracy of the VAA. Our work emphasises the considerable potential of LLMs to create training data to improve the data collection process in adaptive questionnaires in LLM-affine areas such as political surveys.

Manipulation of Elasto-Flexible Cables with Single or Multiple UA Vs Chiara Gabellieri 1, Lars Teeuwen 1, Y aolei Shen 1, Antonio Franchi 1, 2 Abstract -- This work considers a large class of systems composed of multiple quadrotors manipulating deformable and extensible cables. The cable is described via a discretized representation, which decomposes it into linear springs interconnected through lumped-mass passive spherical joints. Sets of flat outputs are found for the systems. Numerical simulations support the findings by showing cable manipulation relying on flatness-based trajectories. Eventually, we present an experimental validation of the effectiveness of the proposed discretized cable model for a two-robot example. Moreover, a closed-loop controller based on the identified model and using cable-output feedback is experimentally tested. I NTRODUCTION AND R ELATEDW ORK Deformable object manipulation is an important recent development in aerial robotics with potential applications ranging from fire fighting [1], and in general the manipulation of fluid conduits [2], to waterway maintenance [3], e.g., in case of oil-spill events [4]. Y et, for the challenges it involves [5], deformable object manipulation is still regarded as an open problem.

Using Machine Learning for move sequence visualization and generation in climbing Thomas Rimbot, Martin Jaggi, Luis Barba - EPFL Abstract --In this work, we investigate the application of Machine Learning techniques to sport climbing. Expanding upon previous projects, we develop a visualization tool for move sequence evaluation on a given boulder . Then, we look into move sequence prediction from simple holds sequence information using three different Transformer models. While the results are not conclusive, they are a first step in this kind of approach and lay the ground for future work. I NTRODUCTION Applying Machine Learning techniques to competitive sport has been an increasing trend in the past few years. We can for example cite the case of car racing or hockey. In this project, we focus on bouldering, a form of rock climbing where athletes are tasked with overcoming a small natural or artificial feature (about 4m high), requiring both physical strengths and problem-solving skills.

In a recent computational framework called active inference, discrete models can be linked to their continuous counterparts to perform decision-making in changing environments. From another perspective, simple agents can be combined to better capture the causal relationships of the world. How can we use these two features together to achieve efficient goal-directed behavior? We present an architecture composed of several hybrid -- continuous and discrete -- units replicating the agent's configuration, controlled by a high-level discrete model that achieves dynamic planning and synchronized behavior. Additional factorizations within each level allow to represent hierarchically other agents and objects in relation to the self. We evaluate this hierarchical hybrid model on a non-trivial task: reaching a moving object after having picked a moving tool. This study extends past work on control as inference and proposes an alternative direction to deep reinforcement learning.

This paper introduces Borinot, an open-source flying robotic platform designed to perform hybrid agile locomotion and manipulation. This platform features a compact and powerful hexarotor that can be outfitted with torque-actuated extremities of diverse architecture, allowing for whole-body dynamic control. As a result, Borinot can perform agile tasks such as aggressive or acrobatic maneuvers with the participation of the whole-body dynamics. The extremities attached to Borinot can be utilized in various ways; during contact, they can be used as legs to create contact-based locomotion, or as arms to manipulate objects. In free flight, they can be used as tails to contribute to dynamics, mimicking the movements of many animals. This allows for any hybridization of these dynamic modes, like the jump-flight of chicken and locusts, making Borinot an ideal open-source platform for research on hybrid aerial-contact agile motion. To demonstrate the key capabilities of Borinot, we have fitted a planar 2DoF arm and implemented whole-body torque-level model-predictive-control. The result is a capable and adaptable platform that, we believe, opens up new avenues of research in the field of agile robotics.

Standardized body region labelling of individual images provides data that can improve human and computer use of medical images. A CNN-based classifier was developed to identify body regions in CT and MRI. 17 CT (18 MRI) body regions covering the entire human body were defined for the classification task. Three retrospective databases were built for the AI model training, validation, and testing, with a balanced distribution of studies per body region. The test databases originated from a different healthcare network. Accuracy, recall and precision of the classifier was evaluated for patient age, patient gender, institution, scanner manufacturer, contrast, slice thickness, MRI sequence, and CT kernel. The data included a retrospective cohort of 2,934 anonymized CT cases (training: 1,804 studies, validation: 602 studies, test: 528 studies) and 3,185 anonymized MRI cases (training: 1,911 studies, validation: 636 studies, test: 638 studies). 27 institutions from primary care hospitals, community hospitals and imaging centers contributed to the test datasets. The data included cases of all genders in equal proportions and subjects aged from a few months old to +90 years old. An image-level prediction accuracy of 91.9% (90.2 - 92.1) for CT, and 94.2% (92.0 - 95.6) for MRI was achieved. The classification results were robust across all body regions and confounding factors. Due to limited data, performance results for subjects under 10 years-old could not be reliably evaluated. We show that deep learning models can classify CT and MRI images by body region including lower and upper extremities with high accuracy.

Kusanagi Motoko, Johnny Mnemonic, Takeshi Kovacs, John Perry, Lenny Nero -- the practice of melding biological minds with electronics hardware is a cornerstone technology of modern cyberpunk literature. And, if certain medical device startup companies are to be believed, accomplishing similar cybernetic feats -- from downloadable memories to "Whoa, I Know Kung Fu"-style instantaneous learning -- could become reality sooner than we think. BCIs are, essentially, devices that read the electrochemical firing of the brain's myriad synapses, interprets and translates that signal into a digital format that can be understood by computers. Research on the technology began in the 1970s at the Brain Research Institute of University of California at Los Angeles under the watch of pioneering neurologist, Dr. Jacques J. Vidal. It took researchers more than two decades to sufficiently lay the basic technological groundwork needed to progress from animal models but by the mid-1990s the very first BCI prototypes were being installed in human craniums.