Search

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the LLM in parallel. Small models that utilise activations from the LLM currently achieve the fastest decoding speeds. However, we identify several limitations of SD models including the lack of on-policyness during training and partial observability. To address these shortcomings, we propose a more grounded architecture for small models by introducing a Mixture of Attentions for SD. Our novel architecture can be applied in two scenarios: a conventional single device deployment and a novel client-server deployment where the small model is hosted on a consumer device and the LLM on a server. In a single-device scenario, we demonstrate state-of-the-art speedups improving EAGLE-2 by 9.5% and its acceptance length by 25%. In a client-server setting, our experiments demonstrate: 1) state-of-the-art latencies with minimal calls to the server for different network conditions, and 2) in the event of a complete disconnection, our approach can maintain higher accuracy compared to other SD methods and demonstrates advantages over API calls to LLMs, which would otherwise be unable to continue the generation process.

There is an ongoing effort to develop feature selection algorithms to improve interpretability, reduce computational resources, and minimize overfitting in predictive models. Neural networks stand out as architectures on which to build feature selection methods, and recently, neuron pruning and regrowth have emerged from the sparse neural network literature as promising new tools. We introduce RelChaNet, a novel and lightweight feature selection algorithm that uses neuron pruning and regrowth in the input layer of a dense neural network. For neuron pruning, a gradient sum metric measures the relative change induced in a network after a feature enters, while neurons are randomly regrown. We also propose an extension that adapts the size of the input layer at runtime. Extensive experiments on nine different datasets show that our approach generally outperforms the current state-of-the-art methods, and in particular improves the average accuracy by 2% on the MNIST dataset. Our code is available at https://github.com/flxzimmer/relchanet.

Understanding the dynamical behavior of complex systems from their underlying network architectures is a long-standing question in complexity theory. Therefore, many metrics have been devised to extract network features like motifs, centrality, and modularity measures. It has previously been proposed that network symmetries are of particular importance since they are expected to underly the synchronization of a system's units, which is ubiquitously observed in nervous system activity patterns. However, perfectly symmetrical structures are difficult to assess in noisy measurements of biological systems, like neuronal connectomes. Here, we devise a principled method to infer network symmetries from combined connectome and neuronal activity data. Using nervous system-wide population activity recordings of the \textit{C.elegans} backward locomotor system, we infer structures in the connectome called fibration symmetries, which can explain which group of neurons synchronize their activity. Our analysis suggests functional building blocks in the animal's motor periphery, providing new testable hypotheses on how descending interneuron circuits communicate with the motor periphery to control behavior. Our approach opens a new door to exploring the structure-function relations in other complex systems, like the nervous systems of larger animals., Comment: 32 pages, 7 figures

In his book 'A Beautiful Question', physicist Frank Wilczek argues that symmetry is 'nature's deep design,' governing the behavior of the universe, from the smallest particles to the largest structures. While symmetry is a cornerstone of physics, it has not yet been found widespread applicability to describe biological systems, particularly the human brain. In this context, we study the human brain network engaged in language and explore the relationship between the structural connectivity (connectome or structural network) and the emergent synchronization of the mesoscopic regions of interest (functional network). We explain this relationship through a different kind of symmetry than physical symmetry, derived from the categorical notion of Grothendieck fibrations. This introduces a new understanding of the human brain by proposing a local symmetry theory of the connectome, which accounts for how the structure of the brain's network determines its coherent activity. Among the allowed patterns of structural connectivity, synchronization elicits different symmetry subsets according to the functional engagement of the brain. We show that the resting state is a particular realization of the cerebral synchronization pattern characterized by a fibration symmetry that is broken in the transition from rest to language. Our findings suggest that the brain's network symmetry at the local level determines its coherent function, and we can understand this relationship from theoretical principles., Comment: 43 pages, 9 figures

Accurately detecting 3D objects from monocular images in dynamic roadside scenarios remains a challenging problem due to varying camera perspectives and unpredictable scene conditions. This paper introduces a two-stage training strategy to address these challenges. Our approach initially trains a model on the large-scale synthetic dataset, RoadSense3D, which offers a diverse range of scenarios for robust feature learning. Subsequently, we fine-tune the model on a combination of real-world datasets to enhance its adaptability to practical conditions. Experimental results of the Cube R-CNN model on challenging public benchmarks show a remarkable improvement in detection performance, with a mean average precision rising from 0.26 to 12.76 on the TUM Traffic A9 Highway dataset and from 2.09 to 6.60 on the DAIR-V2X-I dataset when performing transfer learning. Code, data, and qualitative video results are available on the project website: https://roadsense3d.github.io., Comment: 18 pages. Accepted for ECVA European Conference on Computer Vision 2024 (ECCV'24)

Quantum Computing (QC) offers significant potential to enhance scientific discovery in fields such as quantum chemistry, optimization, and artificial intelligence. Yet QC faces challenges due to the noisy intermediate-scale quantum era's inherent external noise issues. This paper discusses the integration of QC as a computational accelerator within classical scientific high-performance computing (HPC) systems. By leveraging a broad spectrum of simulators and hardware technologies, we propose a hardware-agnostic framework for augmenting classical HPC with QC capabilities. Drawing on the HPC expertise of the Oak Ridge National Laboratory (ORNL) and the HPC lifecycle management of the Department of Energy (DOE), our approach focuses on the strategic incorporation of QC capabilities and acceleration into existing scientific HPC workflows. This includes detailed analyses, benchmarks, and code optimization driven by the needs of the DOE and ORNL missions. Our comprehensive framework integrates hardware, software, workflows, and user interfaces to foster a synergistic environment for quantum and classical computing research. This paper outlines plans to unlock new computational possibilities, driving forward scientific inquiry and innovation in a wide array of research domains.

Stroke remains a leading cause of global morbidity and mortality, placing a heavy socioeconomic burden. Over the past decade, advances in endovascular reperfusion therapy and the use of CT and MRI imaging for treatment guidance have significantly improved patient outcomes and are now standard in clinical practice. To develop machine learning algorithms that can extract meaningful and reproducible models of brain function for both clinical and research purposes from stroke images - particularly for lesion identification, brain health quantification, and prognosis - large, diverse, and well-annotated public datasets are essential. While only a few datasets with (sub-)acute stroke data were previously available, several large, high-quality datasets have recently been made publicly accessible. However, these existing datasets include only MRI data. In contrast, our dataset is the first to offer comprehensive longitudinal stroke data, including acute CT imaging with angiography and perfusion, follow-up MRI at 2-9 days, as well as acute and longitudinal clinical data up to a three-month outcome. The dataset includes a training dataset of n = 150 and a test dataset of n = 100 scans. Training data is publicly available, while test data will be used exclusively for model validation. We are making this dataset available as part of the 2024 edition of the Ischemic Stroke Lesion Segmentation (ISLES) challenge (https://www.isles-challenge.org/), which continuously aims to establish benchmark methods for acute and sub-acute ischemic stroke lesion segmentation, aiding in creating open stroke imaging datasets and evaluating cutting-edge image processing algorithms.

Artificial Intelligence (AI) technologies have profoundly transformed the field of remote sensing, revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, remote sensing has been significantly enhanced by the advent of foundation models--large-scale, pre-trained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This paper provides a comprehensive survey of foundation models in the remote sensing domain, covering models released between June 2021 and June 2024. We categorize these models based on their applications in computer vision and domain-specific tasks, offering insights into their architectures, pre-training datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by these foundation models. Additionally, we discuss the technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pre-training methods, particularly self-supervised learning techniques like contrastive learning and masked autoencoders, significantly enhance the performance and robustness of foundation models in remote sensing tasks such as scene classification, object detection, and other applications. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for continued development and application of foundation models in remote sensing.

We investigate the use of derivative information for Batch Active Learning in Gaussian Process regression models. The proposed approach employs the predictive covariance matrix for selection of data batches to exploit full correlation of samples. We theoretically analyse our proposed algorithm taking different optimality criteria into consideration and provide empirical comparisons highlighting the advantage of incorporating derivatives information. Our results show the effectiveness of our approach across diverse applications., Comment: 29 pages, 10 figures

Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this challenge and enhance the performance of roadside monocular 3D detection. In this study, we introduce the TUMTraf Synthetic Dataset, offering a diverse and substantial collection of high-quality 3D data to augment scarce real-world datasets. Besides, we present WARM-3D, a concise yet effective framework to aid the Sim2Real domain transfer for roadside monocular 3D detection. Our method leverages cheap synthetic datasets and 2D labels from an off-the-shelf 2D detector for weak supervision. We show that WARM-3D significantly enhances performance, achieving a +12.40% increase in mAP 3D over the baseline with only pseudo-2D supervision. With 2D GT as weak labels, WARM-3D even reaches performance close to the Oracle baseline. Moreover, WARM-3D improves the ability of 3D detectors to unseen sample recognition across various real-world environments, highlighting its potential for practical applications.

Carbon black (CB)-elastomers can serve as low-cost, highly deformable sensor materials, but hardly any work exists on their structure-property relationships. We report on flow-induced anisotropy, considering CB-silicone films generated via doctor blade coating. Cured films showed slight electrical anisotropy, with conductivity parallel to the coating direction being lower than perpendicular to it. Furthermore, piezoresistive sensitivity was much larger for stretch perpendicular to the coating direction than for parallel stretch. Structural analysis for length scales up to the CB agglomerate level yielded only weak evidence of anisotropy. Based on this evidence and insight from CB network simulations, we hypothesize that shear flow during coating fragments the CB network and then induces a preferential aggregate alignment, as well as increased inter-particle distances, parallel to the coating direction. As a practical conclusion, already weak anisotropic structuration suffices to cause significant electric anisotropy.

We present the construction of a sparse-compressed operator that approximates the solution operator of elliptic PDEs with rough coefficients. To derive the compressed operator, we construct a hierarchical basis of an approximate solution space, with superlocalized basis functions that are quasi-orthogonal across hierarchy levels with respect to the inner product induced by the energy norm. The superlocalization is achieved through a novel variant of the Super-Localized Orthogonal Decomposition method that is built upon corrections of basis functions arising from the Localized Orthogonal Decomposition method. The hierarchical basis not only induces a sparse compression of the solution space but also enables an orthogonal multiresolution decomposition of the approximate solution operator, decoupling scales and solution contributions of each level of the hierarchy. With this decomposition, the solution of the PDE reduces to the solution of a set of independent linear systems per level with mesh-independent condition numbers that can be computed simultaneously. We present an accuracy study of the compressed solution operator as well as numerical results illustrating our theoretical findings and beyond, revealing that desired optimal error rates with well-behaved superlocalized basis functions can still be attained even in the challenging case of coefficients with high-contrast channels., Comment: 29 pages

Active learning (AL) is a sequential learning scheme aiming to select the most informative data. AL reduces data consumption and avoids the cost of labeling large amounts of data. However, AL trains the model and solves an acquisition optimization for each selection. It becomes expensive when the model training or acquisition optimization is challenging. In this paper, we focus on active nonparametric function learning, where the gold standard Gaussian process (GP) approaches suffer from cubic time complexity. We propose an amortized AL method, where new data are suggested by a neural network which is trained up-front without any real data (Figure 1). Our method avoids repeated model training and requires no acquisition optimization during the AL deployment. We (i) utilize GPs as function priors to construct an AL simulator, (ii) train an AL policy that can zero-shot generalize from simulation to real learning problems of nonparametric functions and (iii) achieve real-time data selection and comparable learning performances to time-consuming baseline methods., Comment: Accepted for publication at ECML-PKDD 2024 Workshop & Tutorial on Interactive Adaptive Learning

Ultrasonography is an essential tool in mid-pregnancy for assessing fetal development, appreciated for its non-invasive and real-time imaging capabilities. Yet, the interpretation of ultrasound images is often complicated by acoustic shadows, speckle noise, and other artifacts that obscure crucial diagnostic details. To address these challenges, our study presents a novel unsupervised anomaly detection framework specifically designed for fetal ultrasound imaging. This framework incorporates gestational age filtering, precise identification of fetal standard planes, and targeted segmentation of brain regions to enhance diagnostic accuracy. Furthermore, we introduce the use of denoising diffusion probabilistic models in this context, marking a significant innovation in detecting previously unrecognized anomalies. We rigorously evaluated the framework using various diffusion-based anomaly detection methods, noise types, and noise levels. Notably, AutoDDPM emerged as the most effective, achieving an area under the precision-recall curve of 79.8\% in detecting anomalies. This advancement holds promise for improving the tools available for nuanced and effective prenatal diagnostics., Comment: ASMUS 2024: 5th International Workshop on Advances in Simplifying Medical Ultrasound

After decoupling, relic neutrinos traverse the evolving gravitational imhomogeneities along their trajectories. Once they turn non-relativistic, this results in a significant amplification of the anisotropies in the cosmic neutrino background (C$\nu$B). Past studies have reconstructed the phase-space distribution of relic neutrinos from the local distribution of matter (accounting for the Milky Way halo and the surrounding large-scale structures), but have neglected the C$\nu$B anisotropies in the initial conditions of neutrino trajectories. Using our previously developed N-1-body simulation framework, we show that including these primordial fluctuations in the initial conditions can be important, as it produces similar effects on the abundance and anisotropies of the C$\nu$B as the inclusion of large-scale structures beyond the Milky Way halo. Interpretability of data from future C$\nu$B observatories like PTOLEMY therefore depends on correctly modelling these effects., Comment: 15 pages, 9 figures, comments are welcome

General vision encoders like DINOv2 and SAM have recently transformed computer vision. Even though they are trained on natural images, such encoder models have excelled in medical imaging, e.g., in classification, segmentation, and registration. However, no in-depth comparison of different state-of-the-art general vision encoders for medical registration is available. In this work, we investigate how well general vision encoder features can be used in the dissimilarity metrics for medical image registration. We explore two encoders that were trained on natural images as well as one that was fine-tuned on medical data. We apply the features within the well-established B-spline FFD registration framework. In extensive experiments on cardiac cine MRI data, we find that using features as additional guidance for conventional metrics improves the registration quality. The code is available at github.com/compai-lab/2024-miccai-koegl., Comment: Accepted at WBIR MICCAI 2024

Physics-inspired regularization is desired for intra-patient image registration since it can effectively capture the biomechanical characteristics of anatomical structures. However, a major challenge lies in the reliance on physical parameters: Parameter estimations vary widely across the literature, and the physical properties themselves are inherently subject-specific. In this work, we introduce a novel data-driven method that leverages hypernetworks to learn the tissue-dependent elasticity parameters of an elastic regularizer. Notably, our approach facilitates the estimation of patient-specific parameters without the need to retrain the network. We evaluate our method on three publicly available 2D and 3D lung CT and cardiac MR datasets. We find that with our proposed subject-specific tissue-dependent regularization, a higher registration quality is achieved across all datasets compared to using a global regularizer. The code is available at https://github.com/compai-lab/2024-miccai-reithmeir., Comment: Accepted at MICCAI 2024

With the increasing incidence of neurodegenerative diseases such as Alzheimer's Disease (AD), there is a need for further research that enhances detection and monitoring of the diseases. We present MORPHADE (Morphological Autoencoders for Alzheimer's Disease Detection), a novel unsupervised learning approach which uses deformations to allow the analysis of 3D T1-weighted brain images. To the best of our knowledge, this is the first use of deformations with deep unsupervised learning to not only detect, but also localize and assess the severity of structural changes in the brain due to AD. We obtain markedly higher anomaly scores in clinically important areas of the brain in subjects with AD compared to healthy controls, showcasing that our method is able to effectively locate AD-related atrophy. We additionally observe a visual correlation between the severity of atrophy highlighted in our anomaly maps and medial temporal lobe atrophy scores evaluated by a clinical expert. Finally, our method achieves an AUROC of 0.80 in detecting AD, out-performing several supervised and unsupervised baselines. We believe our framework shows promise as a tool towards improved understanding, monitoring and detection of AD. To support further research and application, we have made our code publicly available at github.com/ci-ber/MORPHADE., Comment: 11 pages, 5 figures

We present a framework for intuitive robot programming by non-experts, leveraging natural language prompts and contextual information from the Robot Operating System (ROS). Our system integrates large language models (LLMs), enabling non-experts to articulate task requirements to the system through a chat interface. Key features of the framework include: integration of ROS with an AI agent connected to a plethora of open-source and commercial LLMs, automatic extraction of a behavior from the LLM output and execution of ROS actions/services, support for three behavior modes (sequence, behavior tree, state machine), imitation learning for adding new robot actions to the library of possible actions, and LLM reflection via human and environment feedback. Extensive experiments validate the framework, showcasing robustness, scalability, and versatility in diverse scenarios, including long-horizon tasks, tabletop rearrangements, and remote supervisory control. To facilitate the adoption of our framework and support the reproduction of our results, we have made our code open-source. You can access it at: https://github.com/huawei-noah/HEBO/tree/master/ROSLLM., Comment: This document contains 26 pages and 13 figures

A micromechanically motivated phase-field damage model is proposed to investigate the fracture behaviour in crosslinked polyurethane adhesive. The crosslinked polyurethane adhesive typically show viscoelastic behaviour with geometric nonlinearity. The finite-strain viscoelastic behaviour is modelled using a micromechanical network model considering shorter and longer chain length distribution. The micromechanical viscoelastic network model also consider the softening due to breakage/debonding of the short chains with increase in deformation. The micromechanical model is coupled with the phase-field damage model to investigate the crack initiation and propagation. Critical energy release rate is needed as a material property to solve phase-field equation. The energy release rate is formulated based on the polymer chain network. The numerical investigation is performed using finite element method. The force-displacement curves from the numerical analysis and experiments are compared to validate the proposed material model.

Crosslinked polyurethane adhesives show large deformation viscoelastic behaviour and age under the moisture influence because of their hygroscopic behaviour. The viscoelastic behaviour of the material is modelled with the micromechanical network model. The micromechanical model considers the shorter and longer chains with a probability distribution function. The network evolution concept is used to model softening of material due to the breakage of the shorter chains with an increase in deformation. The moisture diffusion in the polyurethane adhesive is behaviour, therefore Langmuir-type diffusion model is used to model moisture diffusion. The transported moisture in the material leads to an exponential decay in the mechanical properties causing the ageing of the material. The micromechanical model needs to be coupled with the Langmuir-type diffusion model to analyse the ageing process, where the mechanical properties are considered as the function of the local moisture concentration.

Generative AI models are capable of performing a wide range of tasks that traditionally require creativity and human understanding. They learn patterns from existing data during training and can subsequently generate new content such as texts, images, and music that follow these patterns. Due to their versatility and generally high-quality results, they, on the one hand, represent an opportunity for digitalization. On the other hand, the use of generative AI models introduces novel IT security risks that need to be considered for a comprehensive analysis of the threat landscape in relation to IT security. In response to this risk potential, companies or authorities using them should conduct an individual risk analysis before integrating generative AI into their workflows. The same applies to developers and operators, as many risks in the context of generative AI have to be taken into account at the time of development or can only be influenced by the operating company. Based on this, existing security measures can be adjusted, and additional measures can be taken., Comment: 33 pages, 3 figures

We propose a framework for global-scale canopy height estimation based on satellite data. Our model leverages advanced data preprocessing techniques, resorts to a novel loss function designed to counter geolocation inaccuracies inherent in the ground-truth height measurements, and employs data from the Shuttle Radar Topography Mission to effectively filter out erroneous labels in mountainous regions, enhancing the reliability of our predictions in those areas. A comparison between predictions and ground-truth labels yields an MAE / RMSE of 2.43 / 4.73 (meters) overall and 4.45 / 6.72 (meters) for trees taller than five meters, which depicts a substantial improvement compared to existing global-scale maps. The resulting height map as well as the underlying framework will facilitate and enhance ecological analyses at a global scale, including, but not limited to, large-scale forest and biomass monitoring., Comment: ICML Camera-Ready, 17 pages, 14 figures, 7 tables

Experimental exploration of high-cost systems with safety constraints, common in engineering applications, is a challenging endeavor. Data-driven models offer a promising solution, but acquiring the requisite data remains expensive and is potentially unsafe. Safe active learning techniques prove essential, enabling the learning of high-quality models with minimal expensive data points and high safety. This paper introduces a safe active learning framework tailored for time-varying systems, addressing drift, seasonal changes, and complexities due to dynamic behavior. The proposed Time-aware Integrated Mean Squared Prediction Error (T-IMSPE) method minimizes posterior variance over current and future states, optimizing information gathering also in the time domain. Empirical results highlight T-IMSPE's advantages in model quality through toy and real-world examples. State of the art Gaussian processes are compatible with T-IMSPE. Our theoretical contributions include a clear delineation which Gaussian process kernels, domains, and weighting measures are suitable for T-IMSPE and even beyond for its non-time aware predecessor IMSPE.

Accurate and effective 3D object detection is critical for ensuring the driving safety of autonomous vehicles. Recently, state-of-the-art two-stage 3D object detectors have exhibited promising performance. However, these methods refine proposals individually, ignoring the rich contextual information in the object relationships between the neighbor proposals. In this study, we introduce an object relation module, consisting of a graph generator and a graph neural network (GNN), to learn the spatial information from certain patterns to improve 3D object detection. Specifically, we create an inter-object relationship graph based on proposals in a frame via the graph generator to connect each proposal with its neighbor proposals. Afterward, the GNN module extracts edge features from the generated graph and iteratively refines proposal features with the captured edge features. Ultimately, we leverage the refined features as input to the detection head to obtain detection results. Our approach improves upon the baseline PV-RCNN on the KITTI validation set for the car class across easy, moderate, and hard difficulty levels by 0.82%, 0.74%, and 0.58%, respectively. Additionally, our method outperforms the baseline by more than 1% under the moderate and hard levels BEV AP on the test server.

In the context of Intelligent Transportation Systems (ITS), efficient data compression is crucial for managing large-scale point cloud data acquired by roadside LiDAR sensors. The demand for efficient storage, streaming, and real-time object detection capabilities for point cloud data is substantial. This work introduces PointCompress3D, a novel point cloud compression framework tailored specifically for roadside LiDARs. Our framework addresses the challenges of compressing high-resolution point clouds while maintaining accuracy and compatibility with roadside LiDAR sensors. We adapt, extend, integrate, and evaluate three cutting-edge compression methods using our real-world-based TUMTraf dataset family. We achieve a frame rate of 10 FPS while keeping compression sizes below 105 Kb, a reduction of 50 times, and maintaining object detection performance on par with the original data. In extensive experiments and ablation studies, we finally achieved a PSNR d2 of 94.46 and a BPP of 6.54 on our dataset. Future work includes the deployment on the live system. The code is available on our project website: https://pointcompress3d.github.io.

During the pandemic, a number of states instituted hold-harmless funding policies to protect school district financially from declining enrollments (Center for Public Education, 2021). In addition, some school choice policies have protected traditional public schools financially from declining enrollments. Together, these policies raise the question of whether competitive effects can exist in a policy environment of reduced financial pressure. Theoretically, despite the lack of financial pressure, schools could feel competitive pressure in other ways including a loss of reputation as students move to schools of choice (Epple, Romono, & Urquiola, 2017; Friedman, 1962; MacLeod & Urquiola, 2009; Urquiola, 2016). To provide insights on whether schools can improve without the threat of financial loss, we examine the Seoul school choice program which introduced autonomous private high schools (APHSs) in the context in which there is equalized funding across schools. More specifically, we examine whether competition induced by APHSs affects the achievement of students attending traditional public and private schools. The effect of APHSs is identified by exploiting plausible exogenous APHSs' entry through the random assignment of students. We find a small and positive effect of APHS penetration on the Korean and English achievement of private school students while finding no effects for traditional public schools, which have limited ability to respond.

We obtain a bi-Lipschitz rigidity theorem for a Zariski dense discrete subgroup of a connected simple real algebraic group. As an application, we show that any Zariski dense discrete subgroup of a higher rank semisimple algebraic group $G$ cannot have a $C^1$-smooth slim limit set in $G/P$ for any non-maximal parabolic subgroup $P$.

This work introduces SwarmRL, a Python package designed to study intelligent active particles. SwarmRL provides an easy-to-use interface for developing models to control microscopic colloids using classical control and deep reinforcement learning approaches. These models may be deployed in simulations or real-world environments under a common framework. We explain the structure of the software and its key features and demonstrate how it can be used to accelerate research. With SwarmRL, we aim to streamline research into micro-robotic control while bridging the gap between experimental and simulation-driven sciences. SwarmRL is available open-source on GitHub at https://github.com/SwarmRL/SwarmRL., Comment: 16 pages, 3 figures

With the robust uptick in the applications of Bayesian external data borrowing, eliciting a prior distribution with the proper amount of information becomes increasingly critical. The prior effective sample size (ESS) is an intuitive and efficient measure for this purpose. The majority of ESS definitions have been proposed in the context of borrowing control information. While many Bayesian models can be naturally extended to leveraging external information on the treatment effect scale, very little attention has been directed to computing the prior ESS in this setting. In this research, we bridge this methodological gap by extending the popular ELIR ESS definition. We lay out the general framework, and derive the prior ESS for various types of endpoints and treatment effect measures. The posterior distribution and the predictive consistency property of ESS are also examined. The methods are implemented in R programs available on GitHub: https://github.com/squallteo/TrtEffESS.

We establish counting, mixing and equidistribution results for finite BMS measures on flow spaces associated to geometrically finite convergence group actions. We show that, in particular, these results apply to flow spaces associated to relatively Anosov groups., Comment: v2: 56 pages. Substantial changes to extend results to more general Gromov products. Now ready for submission

In this paper we develop a theory of Patterson--Sullivan measures associated to coarse cocycles of convergence groups. This framework includes Patterson-Sullivan measures associated to the Busemann cocycle on the geodesic boundary of a Gromov hyperbolic metric spaces and Patterson-Sullivan measures on flag manifolds associated to Anosov (or more general transverse) subgroups of semisimple Lie groups, as well as more examples. Under some natural geometric assumptions on the coarse cocycle, we prove existence, uniqueness, and ergodicity results., Comment: v2: 72 pages. Substantial changes to extend results to more general cocycles and Gromov products. Now ready for submission

We reconsider the fundamental problem of coarse-graining infinite-dimensional Hamiltonian dynamics to obtain a macroscopic system which includes dissipative mechanisms. In particular, we study the thermodynamical implications concerning Hamiltonians, energy, and entropy and the induced geometric structures such as Poisson and Onsager brackets (symplectic and dissipative brackets). We start from a general finite-dimensional Hamiltonian system that is coupled linearly to an infinite-dimensional heat bath with linear dynamics. The latter is assumed to admit a compression to a finite-dimensional dissipative semigroup (i.e., the heat bath is a dilation of the semigroup) describing the dissipative evolution of new macroscopic variables. Already in the finite-energy case (zero-temperature heat bath) we obtain the so-called GENERIC structure (General Equations for Non-Equilibrium Reversible Irreversibe Coupling), with conserved energy, nondecreasing entropy, a new Poisson structure, and an Onsager operator describing the dissipation. However, their origin is not obvious at this stage. After extending the system in a natural way to the case of positive temperature, giving a heat bath with infinite energy, the compression property leads to an exact multivariate Ornstein-Uhlenbeck process that drives the rest of the system. Thus, we are able to identify a conserved energy, an entropy, and an Onsager operator (involving the Green-Kubo formalism) which indeed provide a GENERIC structure for the macroscopic system.

We present two novel six-colorings of the Euclidean plane that avoid monochromatic pairs of points at unit distance in five colors and monochromatic pairs at another specified distance $d$ in the sixth color. Such colorings have previously been known to exist for $0.41 < \sqrt{2} - 1 \le d \le 1 / \sqrt{5} < 0.45$. Our results significantly expand that range to $0.354 \le d \le 0.657$, the first improvement in 30 years. Notably, the constructions underlying this were derived by formalizing colorings suggested by a custom machine learning approach., Comment: An animated version of Figure 2 is available at https://christophspiegel.berlin/hn/fig2.pdf and can be viewed with Acrobat Reader

The digital transformation is fundamentally changing our industries, affecting planning, execution as well as monitoring of production processes in a wide range of application fields. With product line-ups becoming more and more versatile and diverse, the necessary inspection and monitoring sparks significant novel requirements on the corresponding Nondestructive Evaluation (NDE) systems. The establishment of increasingly powerful approaches to incorporate Artificial Intelligence (AI) may provide just the needed innovation to solve some of these challenges. In this paper we provide a comprehensive survey about the usage of AI methods in NDE in light of the recent innovations towards NDE 4.0. Since we cannot discuss each NDE modality in one paper, we limit our attention to magnetic methods, ultrasound, thermography, as well as optical inspection. In addition to reviewing recent AI developments in each field, we draw common connections by pointing out NDE-related tasks that have a common underlying mathematical problem and categorizing the state of the art according to the corresponding sub-tasks. In so doing, interdisciplinary connections are drawn that provide a more complete overall picture.

In lieu of abstract, first paragraph reads: Six months after the author derived a constant of motion for a 1D damped harmonic oscillator [1], a similar result appeared by Liu, Madhavan, and Tegmark [2, 3], without citing the author. However, their derivation contained six serious errors, causing both their method and result to be incorrect. In this Comment, those errors are reviewed., Comment: 2 pages, 1 figure

This paper begins with a dynamical model that was obtained by applying a machine learning technique (FJet) to time-series data; this dynamical model is then analyzed with Lie symmetry techniques to obtain constants of motion. This analysis is performed on both the conserved and non-conserved cases of the 1D and 2D harmonic oscillators. For the 1D oscillator, constants are found in the cases where the system is underdamped, overdamped, and critically damped. The novel existence of such a constant for a non-conserved model is interpreted as a manifestation of the conservation of energy of the {\em total} system (i.e., oscillator plus dissipative environment). For the 2D oscillator, constants are found for the isotropic and anisotropic cases, including when the frequencies are incommensurate; it is also generalized to arbitrary dimensions. In addition, a constant is identified which generalizes angular momentum for all ratios of the frequencies. The approach presented here can produce {\em multiple} constants of motion from a {\em single}, generic data set., Comment: 14 pages, 5 figures

Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consistent and reliable image segmentation. This variability not only reflects the inherent complexity and subjective nature of medical image interpretation but also directly impacts the development and evaluation of automated segmentation algorithms. Accurately modeling and quantifying this variability is essential for enhancing the robustness and clinical applicability of these algorithms. We report the set-up and summarize the benchmark results of the Quantification of Uncertainties in Biomedical Image Quantification Challenge (QUBIQ), which was organized in conjunction with International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020 and 2021. The challenge focuses on the uncertainty quantification of medical image segmentation which considers the omnipresence of inter-rater variability in imaging datasets. The large collection of images with multi-rater annotations features various modalities such as MRI and CT; various organs such as the brain, prostate, kidney, and pancreas; and different image dimensions 2D-vs-3D. A total of 24 teams submitted different solutions to the problem, combining various baseline models, Bayesian neural networks, and ensemble model techniques. The obtained results indicate the importance of the ensemble models, as well as the need for further research to develop efficient 3D methods for uncertainty quantification methods in 3D segmentation tasks., Comment: initial technical report

We introduce Neural Parameter Regression (NPR), a novel framework specifically developed for learning solution operators in Partial Differential Equations (PDEs). Tailored for operator learning, this approach surpasses traditional DeepONets (Lu et al., 2021) by employing Physics-Informed Neural Network (PINN, Raissi et al., 2019) techniques to regress Neural Network (NN) parameters. By parametrizing each solution based on specific initial conditions, it effectively approximates a mapping between function spaces. Our method enhances parameter efficiency by incorporating low-rank matrices, thereby boosting computational efficiency and scalability. The framework shows remarkable adaptability to new initial and boundary conditions, allowing for rapid fine-tuning and inference, even in cases of out-of-distribution examples., Comment: ICLR24 Workshop AI4Differential Equations In Science, 15 pages, 4 figures, 2 tables, 1 algorithm

Cooperative perception offers several benefits for enhancing the capabilities of autonomous vehicles and improving road safety. Using roadside sensors in addition to onboard sensors increases reliability and extends the sensor range. External sensors offer higher situational awareness for automated vehicles and prevent occlusions. We propose CoopDet3D, a cooperative multi-modal fusion model, and TUMTraf-V2X, a perception dataset, for the cooperative 3D object detection and tracking task. Our dataset contains 2,000 labeled point clouds and 5,000 labeled images from five roadside and four onboard sensors. It includes 30k 3D boxes with track IDs and precise GPS and IMU data. We labeled eight categories and covered occlusion scenarios with challenging driving maneuvers, like traffic violations, near-miss events, overtaking, and U-turns. Through multiple experiments, we show that our CoopDet3D camera-LiDAR fusion model achieves an increase of +14.36 3D mAP compared to a vehicle camera-LiDAR fusion model. Finally, we make our dataset, model, labeling tool, and dev-kit publicly available on our website: https://tum-traffic-dataset.github.io/tumtraf-v2x.

Active learning of physical systems must commonly respect practical safety constraints, which restricts the exploration of the design space. Gaussian Processes (GPs) and their calibrated uncertainty estimations are widely used for this purpose. In many technical applications the design space is explored via continuous trajectories, along which the safety needs to be assessed. This is particularly challenging for strict safety requirements in GP methods, as it employs computationally expensive Monte-Carlo sampling of high quantiles. We address these challenges by providing provable safety bounds based on the adaptively sampled median of the supremum of the posterior GP. Our method significantly reduces the number of samples required for estimating high safety probabilities, resulting in faster evaluation without sacrificing accuracy and exploration speed. The effectiveness of our safe active learning approach is demonstrated through extensive simulations and validated using a real-world engine example., Comment: AISTATS 2024

Sequential learning methods such as active learning and Bayesian optimization select the most informative data to learn about a task. In many medical or engineering applications, the data selection is constrained by a priori unknown safety conditions. A promissing line of safe learning methods utilize Gaussian processes (GPs) to model the safety probability and perform data selection in areas with high safety confidence. However, accurate safety modeling requires prior knowledge or consumes data. In addition, the safety confidence centers around the given observations which leads to local exploration. As transferable source knowledge is often available in safety critical experiments, we propose to consider transfer safe sequential learning to accelerate the learning of safety. We further consider a pre-computation of source components to reduce the additional computational load that is introduced by incorporating source data. In this paper, we theoretically analyze the maximum explorable safe regions of conventional safe learning methods. Furthermore, we empirically demonstrate that our approach 1) learns a task with lower data consumption, 2) globally explores multiple disjoint safe regions under guidance of the source knowledge, and 3) operates with computation comparable to conventional safe learning methods.

Federated Learning (FL) algorithms using Knowledge Distillation (KD) have received increasing attention due to their favorable properties with respect to privacy, non-i.i.d. data and communication cost. These methods depart from transmitting model parameters and instead communicate information about a learning task by sharing predictions on a public dataset. In this work, we study the performance of such approaches in the byzantine setting, where a subset of the clients act in an adversarial manner aiming to disrupt the learning process. We show that KD-based FL algorithms are remarkably resilient and analyze how byzantine clients can influence the learning process. Based on these insights, we introduce two new byzantine attacks and demonstrate their ability to break existing byzantine-resilient methods. Additionally, we propose a novel defence method which enhances the byzantine resilience of KD-based FL algorithms. Finally, we provide a general framework to obfuscate attacks, making them significantly harder to detect, thereby improving their effectiveness. Our findings serve as an important building block in the analysis of byzantine FL, contributing through the development of new attacks and new defence mechanisms, further advancing the robustness of KD-based FL algorithms.

Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bounding boxes or bird's eye views as representations of the environment. However, these approaches fall short in offering a comprehensive 3D environmental prediction. To bridge this gap, we introduce the first method for collaborative 3D semantic occupancy prediction. Particularly, it improves local 3D semantic occupancy predictions by hybrid fusion of (i) semantic and occupancy task features, and (ii) compressed orthogonal attention features shared between vehicles. Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation. The experimental findings highlight that: (i) our collaborative semantic occupancy predictions excel above the results from single vehicles by over 30%, and (ii) models anchored on semantic occupancy outpace state-of-the-art collaborative 3D detection techniques in subsequent perception applications, showcasing enhanced accuracy and enriched semantic-awareness in road environments., Comment: Accepted by CVPR2024. Website link: https://rruisong.github.io/publications/CoHFF

Learning a universal policy across different robot morphologies can significantly improve learning efficiency and enable zero-shot generalization to unseen morphologies. However, learning a highly performant universal policy requires sophisticated architectures like transformers (TF) that have larger memory and computational cost than simpler multi-layer perceptrons (MLP). To achieve both good performance like TF and high efficiency like MLP at inference time, we propose HyperDistill, which consists of: (1) A morphology-conditioned hypernetwork (HN) that generates robot-wise MLP policies, and (2) A policy distillation approach that is essential for successful training. We show that on UNIMAL, a benchmark with hundreds of diverse morphologies, HyperDistill performs as well as a universal TF teacher policy on both training and unseen test robots, but reduces model size by 6-14 times, and computational cost by 67-160 times in different environments. Our analysis attributes the efficiency advantage of HyperDistill at inference time to knowledge decoupling, i.e., the ability to decouple inter-task and intra-task knowledge, a general principle that could also be applied to improve inference efficiency in other domains., Comment: ICML 2024

Learning time-series models is useful for many applications, such as simulation and forecasting. In this study, we consider the problem of actively learning time-series models while taking given safety constraints into account. For time-series modeling we employ a Gaussian process with a nonlinear exogenous input structure. The proposed approach generates data appropriate for time series model learning, i.e. input and output trajectories, by dynamically exploring the input space. The approach parametrizes the input trajectory as consecutive trajectory sections, which are determined stepwise given safety requirements and past observations. We analyze the proposed algorithm and evaluate it empirically on a technical application. The results show the effectiveness of our approach in a realistic technical use case., Comment: Clarification / Errata of article originally published at NeurIPS: https://proceedings.neurips.cc/paper/2018/hash/b197ffdef2ddc3308584dce7afa3661b-Abstract.html

The curation of large-scale datasets is still costly and requires much time and resources. Data is often manually labeled, and the challenge of creating high-quality datasets remains. In this work, we fill the research gap using active learning for multi-modal 3D object detection. We propose ActiveAnno3D, an active learning framework to select data samples for labeling that are of maximum informativeness for training. We explore various continuous training methods and integrate the most efficient method regarding computational demand and detection performance. Furthermore, we perform extensive experiments and ablation studies with BEVFusion and PV-RCNN on the nuScenes and TUM Traffic Intersection dataset. We show that we can achieve almost the same performance with PV-RCNN and the entropy-based query strategy when using only half of the training data (77.25 mAP compared to 83.50 mAP) of the TUM Traffic Intersection dataset. BEVFusion achieved an mAP of 64.31 when using half of the training data and 75.0 mAP when using the complete nuScenes dataset. We integrate our active learning framework into the proAnno labeling tool to enable AI-assisted data selection and labeling and minimize the labeling costs. Finally, we provide code, weights, and visualization results on our website: https://active3d-framework.github.io/active3d-framework.