Search

Timing control while preserving determinism is often a key requirement for ensuring the safety and correctness of distributed cyber-physical systems (CPS). Discrete-event (DE) systems provide a suitable model of computation (MoC) for time-sensitive distributed CPS. The high-level architecture (HLA) is a useful tool for the distributed simulation of DE systems, but its techniques can be adapted for implementing distributed CPS. However, HLA incurs considerable overhead in network messages conveying timing information between the distributed nodes and the centralized run-time infrastructure (RTI). This paper gives a novel approach and implementation that reduces such network messages while preserving DE semantics. An evaluation of our runtime demonstrates that our approach significantly reduces the volume of messages for timing information in HLA., Comment: To appear in Proceedings of the 22nd ACM-IEEE International Conference on Formal Methods and Models for System Design (MEMOCODE'24)

Crystallisation is an important phenomenon which facilitates the purification as well as structural and bulk phase material characterisation using crystallographic methods. However, different conditions can lead to a vast set of different crystal structure polymorphs and these often exhibit different physical properties, allowing materials to be tailored to specific purposes. This means the high dimensionality that can result from variations in the conditions which affect crystallisation, and the interaction between them, means that exhaustive exploration is difficult, time-consuming, and costly to explore. Herein we present a robotic crystal search engine for the automated and efficient high-throughput approach to the exploration of crystallisation conditions. The system comprises a closed-loop computer crystal-vision system that uses machine learning to both identify crystals and classify their identity in a multiplexed robotic platform. By exploring the formation of a well-known polymorph, we were able to show how a robotic system could be used to efficiently search experimental space as a function of relative polymorph amount and efficiently create a high dimensionality phase diagram with minimal experimental budget and without expensive analytical techniques such as crystallography. In this way, we identify the set of polymorphs possible within a set of experimental conditions, as well as the optimal values of these conditions to grow each polymorph., Comment: 18 pages, 6 figures, 20 references

We introduce EXAONE 3.0 instruction-tuned language model, the first open model in the family of Large Language Models (LLMs) developed by LG AI Research. Among different model sizes, we publicly release the 7.8B instruction-tuned model to promote open research and innovations. Through extensive evaluations across a wide range of public and in-house benchmarks, EXAONE 3.0 demonstrates highly competitive real-world performance with instruction-following capability against other state-of-the-art open models of similar size. Our comparative analysis shows that EXAONE 3.0 excels particularly in Korean, while achieving compelling performance across general tasks and complex reasoning. With its strong real-world effectiveness and bilingual proficiency, we hope that EXAONE keeps contributing to advancements in Expert AI. Our EXAONE 3.0 instruction-tuned model is available at https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct

This paper introduces the Precision-Timed Virtual Machine (PretVM), an intermediate platform facilitating the execution of quasi-static schedules compiled from a subset of programs written in the Lingua Franca (LF) coordination language. The subset consists of those programs that in principle should have statically verifiable and predictable timing behavior. The PretVM provides a schedule with well-defined worst-case timing bounds. The PretVM provides a clean separation between application logic and coordination logic, yielding more analyzable program executions. Experiments compare the PretVM against the default (more dynamic) LF scheduler and show that it delivers time-accurate deterministic execution.

Discrete-event (DE) systems are concurrent programs where components communicate via tagged events, where tags are drawn from a totally ordered set. Reactors are an emerging model of computation based on DE and realized in the open-source coordination language Lingua Franca. Distributed DE (DDE) systems are DE systems where the components (reactors) communicate over networks. The prior art has required that for DDE systems with cycles, each cycle must contain at least one logical delay, where the tag of events is incremented. Such delays, however, are not required by the elegant fixed-point semantics of DE. The only requirement is that the program be constructive, meaning it is free of causality cycles. This paper gives a way to coordinate the execution of DDE systems that can execute any constructive program, even one with zero-delay cycles. It provides a formal model that exposes exactly the information that must be shared across networks for such execution to be possible. Furthermore, it describes a concrete implementation that is an extension of the coordination mechanisms in Lingua Franca.

Magnetic resonance imaging (MRI) is the standard modality to understand human brain structure and function in vivo (antemortem). Decades of research in human neuroimaging has led to the widespread development of methods and tools to provide automated volume-based segmentations and surface-based parcellations which help localize brain functions to specialized anatomical regions. Recently ex vivo (postmortem) imaging of the brain has opened-up avenues to study brain structure at sub-millimeter ultra high-resolution revealing details not possible to observe with in vivo MRI. Unfortunately, there has been limited methodological development in ex vivo MRI primarily due to lack of datasets and limited centers with such imaging resources. Therefore, in this work, we present one-of-its-kind dataset of 82 ex vivo T2w whole brain hemispheres MRI at 0.3 mm isotropic resolution spanning Alzheimer's disease and related dementias. We adapted and developed a fast and easy-to-use automated surface-based pipeline to parcellate, for the first time, ultra high-resolution ex vivo brain tissue at the native subject space resolution using the Desikan-Killiany-Tourville (DKT) brain atlas. This allows us to perform vertex-wise analysis in the template space and thereby link morphometry measures with pathology measurements derived from histology. We will open-source our dataset docker container, Jupyter notebooks for ready-to-use out-of-the-box set of tools and command line options to advance ex vivo MRI clinical brain imaging research on the project webpage.

The third ML4H symposium was held in person on December 10, 2023, in New Orleans, Louisiana, USA. The symposium included research roundtable sessions to foster discussions between participants and senior researchers on timely and relevant topics for the \ac{ML4H} community. Encouraged by the successful virtual roundtables in the previous year, we organized eleven in-person roundtables and four virtual roundtables at ML4H 2022. The organization of the research roundtables at the conference involved 17 Senior Chairs and 19 Junior Chairs across 11 tables. Each roundtable session included invited senior chairs (with substantial experience in the field), junior chairs (responsible for facilitating the discussion), and attendees from diverse backgrounds with interest in the session's topic. Herein we detail the organization process and compile takeaways from these roundtable discussions, including recent advances, applications, and open challenges for each topic. We conclude with a summary and lessons learned across all roundtables. This document serves as a comprehensive review paper, summarizing the recent advancements in machine learning for healthcare as contributed by foremost researchers in the field., Comment: ML4H 2023, Research Roundtables

Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation models is the lack of data grounded in the physical world. In this paper, we propose AutoRT, a system that leverages existing foundation models to scale up the deployment of operational robots in completely unseen scenarios with minimal human supervision. AutoRT leverages vision-language models (VLMs) for scene understanding and grounding, and further uses large language models (LLMs) for proposing diverse and novel instructions to be performed by a fleet of robots. Guiding data collection by tapping into the knowledge of foundation models enables AutoRT to effectively reason about autonomy tradeoffs and safety while significantly scaling up data collection for robot learning. We demonstrate AutoRT proposing instructions to over 20 robots across multiple buildings and collecting 77k real robot episodes via both teleoperation and autonomous robot policies. We experimentally show that such "in-the-wild" data collected by AutoRT is significantly more diverse, and that AutoRT's use of LLMs allows for instruction following data collection robots that can align to human preferences., Comment: 26 pages, 9 figures, ICRA 2024 VLMNM Workshop

Parallel Reinforcement Learning (RL) frameworks are essential for mapping RL workloads to multiple computational resources, allowing for faster generation of samples, estimation of values, and policy improvement. These computational paradigms require a seamless integration of training, serving, and simulation workloads. Existing frameworks, such as Ray, are not managing this orchestration efficiently, especially in RL tasks that demand intensive input/output and synchronization between actors on a single node. In this study, we have proposed a solution implementing the reactor model, which enforces a set of actors to have a fixed communication pattern. This allows the scheduler to eliminate work needed for synchronization, such as acquiring and releasing locks for each actor or sending and processing coordination-related messages. Our framework, Lingua Franca (LF), a coordination language based on the reactor model, also supports true parallelism in Python and provides a unified interface that allows users to automatically generate dataflow graphs for RL tasks. In comparison to Ray on a single-node multi-core compute platform, LF achieves 1.21x and 11.62x higher simulation throughput in OpenAI Gym and Atari environments, reduces the average training time of synchronized parallel Q-learning by 31.2%, and accelerates multi-agent RL inference by 5.12x., Comment: 10 pages, 11 figures

Type qualifiers offer a lightweight mechanism for enriching existing type systems to enforce additional, desirable, program invariants. They do so by offering a restricted but effective form of subtyping. While the theory of type qualifiers is well understood and present in many programming languages today, polymorphism over type qualifiers is an area that is less examined. We explore how such a polymorphic system could arise by constructing a calculus System F<:Q which combines the higher-rank bounded polymorphism of System F<: with the theory of type qualifiers. We explore how the ideas used to construct System F<:Q can be reused in situations where type qualifiers naturally arise -- in reference immutability, function colouring, and capture checking. Finally, we re-examine other qualifier systems in the literature in light of the observations presented while developing System F<:Q., Comment: 24 pages

Reference immutability is a type based technique for taming mutation that has long been studied in the context of object-oriented languages, like Java. Recently, though, languages like Scala have blurred the lines between functional programming languages and object oriented programming languages. We explore how reference immutability interacts with features commonly found in these hybrid languages, in particular with higher-order functions -- polymorphism -- and subtyping. We construct a calculus System F-sub-M which encodes a reference immutability system as a simple extension of F-sub and prove that it satisfies the standard soundness and immutability safety properties., Comment: 25 pages

Animals have evolved various agile locomotion strategies, such as sprinting, leaping, and jumping. There is a growing interest in developing legged robots that move like their biological counterparts and show various agile skills to navigate complex environments quickly. Despite the interest, the field lacks systematic benchmarks to measure the performance of control policies and hardware in agility. We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. This encourages researchers to develop controllers that not only move fast, but do so in a controllable and versatile way. To set strong baselines, we present two methods for tackling the benchmark. In the first approach, we train specialist locomotion skills using on-policy reinforcement learning methods and combine them with a high-level navigation controller. In the second approach, we distill the specialist skills into a Transformer-based generalist locomotion policy, named Locomotion-Transformer, that can handle various terrains and adjust the robot's gait based on the perceived environment and robot states. Using a custom-built quadruped robot, we demonstrate that our method can complete the course at half the speed of a dog. We hope that our work represents a step towards creating controllers that enable robots to reach animal-level agility., Comment: 17 pages, 19 figures

While it is well known that population differences from genetics, sex, race, and environmental factors contribute to disease, AI studies in medicine have largely focused on locoregional patient cohorts with less diverse data sources. Such limitation stems from barriers to large-scale data share and ethical concerns over data privacy. Federated learning (FL) is one potential pathway for AI development that enables learning across hospitals without data share. In this study, we show the results of various FL strategies on one of the largest and most diverse COVID-19 chest CT datasets: 21 participating hospitals across five continents that comprise >10,000 patients with >1 million images. We also propose an FL strategy that leverages synthetically generated data to overcome class and size imbalances. We also describe the sources of data heterogeneity in the context of FL, and show how even among the correctly labeled populations, disparities can arise due to these biases.

Postmortem MRI allows brain anatomy to be examined at high resolution and to link pathology measures with morphometric measurements. However, automated segmentation methods for brain mapping in postmortem MRI are not well developed, primarily due to limited availability of labeled datasets, and heterogeneity in scanner hardware and acquisition protocols. In this work, we present a high resolution of 135 postmortem human brain tissue specimens imaged at 0.3 mm$^{3}$ isotropic using a T2w sequence on a 7T whole-body MRI scanner. We developed a deep learning pipeline to segment the cortical mantle by benchmarking the performance of nine deep neural architectures, followed by post-hoc topological correction. We then segment four subcortical structures (caudate, putamen, globus pallidus, and thalamus), white matter hyperintensities, and the normal appearing white matter. We show generalizing capabilities across whole brain hemispheres in different specimens, and also on unseen images acquired at 0.28 mm^3 and 0.16 mm^3 isotropic T2*w FLASH sequence at 7T. We then compute localized cortical thickness and volumetric measurements across key regions, and link them with semi-quantitative neuropathological ratings. Our code, Jupyter notebooks, and the containerized executables are publicly available at: https://pulkit-khandelwal.github.io/exvivo-brain-upenn, Comment: Preprint submitted to NeuroImage Project website: https://pulkit-khandelwal.github.io/exvivo-brain-upenn

When developing tools for automated cortical segmentation, the ability to produce topologically correct segmentations is important in order to compute geometrically valid morphometry measures. In practice, accurate cortical segmentation is challenged by image artifacts and the highly convoluted anatomy of the cortex itself. To address this, we propose a novel deep learning-based cortical segmentation method in which prior knowledge about the geometry of the cortex is incorporated into the network during the training process. We design a loss function which uses the theory of Laplace's equation applied to the cortex to locally penalize unresolved boundaries between tightly folded sulci. Using an ex vivo MRI dataset of human medial temporal lobe specimens, we demonstrate that our approach outperforms baseline segmentation networks, both quantitatively and qualitatively., Comment: Accepted at the 28th biennial international conference on Information Processing in Medical Imaging (IPMI 2023)

Complex software systems often feature distinct modes of operation, each designed to handle a particular scenario that may require the system to respond in a certain way. Breaking down system behavior into mutually exclusive modes and discrete transitions between modes is a commonly used strategy to reduce implementation complexity and promote code readability. However, such capabilities often come in the form of self-contained domain specific languages or language-specific frameworks. The work in this paper aims to bring the advantages of modal models to mainstream programming languages, by following the polyglot coordination approach of Lingua Franca (LF), in which verbatim target code (e.g., C, C++, Python, Typescript, or Rust) is encapsulated in composable reactive components called reactors. Reactors can form a dataflow network, are triggered by timed as well as sporadic events, execute concurrently, and can be distributed across nodes on a network. With modal models in LF, we introduce a lean extension to the concept of reactors that enables the coordination of reactive tasks based on modes of operation. The implementation of modal reactors outlined in this paper generalizes to any LF-supported language with only modest modifications to the generic runtime system.

In distributed applications, Brewer's CAP theorem tells us that when networks become partitioned (P), one must give up either consistency (C) or availability (A). Consistency is agreement on the values of shared variables; availability is the ability to respond to reads and writes accessing those shared variables. Availability is a real-time property whereas consistency is a logical property. We have extended the CAP theorem to relate quantitative measures of these two properties to quantitative measures of communication and computation latency (L), obtaining a relation called the CAL theorem that is linear in a max-plus algebra. This paper shows how to use the CAL theorem in various ways to help design real-time systems. We develop a methodology for systematically trading off availability and consistency in application-specific ways and to guide the system designer when putting functionality in end devices, in edge computers, or in the cloud. We build on the Lingua Franca coordination language to provide system designers with concrete analysis and design tools to make the required tradeoffs in deployable software., Comment: 12 pages. arXiv admin note: text overlap with arXiv:2109.07771

We introduce an algorithm for estimating the entropy of pairwise, probabilistic graph models by leveraging bridges between social communities and an accurate entropy estimator on sparse samples. We propose using a measure of investment from the sociological literature, Burt's structural constraint, as a heuristic for identifying bridges that partition a graph into conditionally independent components. We combine this heuristic with the Nemenman-Shafee-Bialek entropy estimator to obtain a faster and more accurate estimator. We demonstrate it on the pairwise maximum entropy, or Ising, models of judicial voting, to improve na\"ive entropy estimates. We use our algorithm to estimate the partition function closely, which we then apply to the problem of model selection, where estimating the likelihood is difficult. This serves as an improvement over existing methods that rely on point correlation functions to test fit can be extended to other graph models with a straightforward modification of the open-source implementation.

Actor frameworks and similar reactive programming techniques are widely used for building concurrent systems. They promise to be efficient and scale well to a large number of cores or nodes in a distributed system. However, they also expose programmers to nondeterminism, which often makes implementations hard to understand, debug, and test. The recently proposed reactor model is a promising alternative that enables efficient deterministic concurrency. In this paper, we show that determinacy does neither imply a loss in expressivity nor in performance. To show this, we evaluate Lingua Franca (LF), a reactor-oriented coordination language that equips mainstream programming languages with a concurrency model that automatically takes advantage of opportunities to exploit parallelism that do not introduce nondeterminism. Our implementation of the Savina benchmark suite demonstrates that, in terms of execution time, the runtime performance of LF programs even exceeds popular and highly optimized actor frameworks. We compare against Akka and CAF, which LF outperforms by 1.86x and 1.42x, respectively.

Conflicts, like many social processes, are related events that span multiple scales in time, from the instantaneous to multi-year developments, and in space, from one neighborhood to continents. Yet, there is little systematic work on connecting the multiple scales, formal treatment of causality between events, and measures of uncertainty for how events are related to one another. We develop a method for extracting related chains of events that addresses these limitations with armed conflict. Our method explicitly accounts for an adjustable spatial and temporal scale of interaction for clustering individual events from a detailed data set, the Armed Conflict Event & Location Data Project. With it, we discover a mesoscale ranging from a week to a few months and from tens to a few hundred kilometers, where long-range correlations and nontrivial dynamics relating conflict events emerge. Importantly, clusters in the mesoscale, while extracted only from conflict statistics, are identifiable with causal mechanism cited in field studies. We leverage our technique to identify zones of causal interaction around conflict hotspots that naturally incorporate uncertainties. Thus, we show how a systematic, data-driven procedure extracts social objects for study, providing a scope for scrutinizing and predicting conflict amongst other processes., Comment: 17 pages

Social and biological collectives need to exchange information to persist and to function. This happens across internal networks, whose structure represents static channels through which information flows. Less studied is the quantity and variety of information transmitted. We characterize a part of the information flow, the information going into organizations, primarily business firms. We measure what firms read using a data set of hundreds of millions of records of news articles accessed by employees across millions of firms. We measure and relate quantitatively three essential aspects: reading volume, reading variety, and firm size. First we compare volume with firm size, showing that firms grow sublinearly with the volume of their reading. The scaling means that inequality in information volume exaggerates the classic Zipf's law inequality in firm size, pointing to an economy of scale in information consumption. Then, by connecting variety and volume, we show that the firms vary in their reading habits to a limited degree. Firms above a certain size become repetitive readers, consistent with the sudden onset of a coordination cost between teams, not individual employees. Finally, we relate information variety to size to show that large firms tend to increase investments in existing areas of interest instead of divesting from them to move to new areas. We argue that this reflects structural constraints in growth. The results indicate how information consumption reflects the role of internal structure, beyond individual employees, analogous to information processing in other social and biological systems.

Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e.g., in cluttered home environments or in human-occupied public spaces. To address this, we present a new class of implicit control policies combining the benefits of imitation learning with the robust handling of system constraints from Model Predictive Control (MPC). Our approach, called Performer-MPC, uses a learned cost function parameterized by vision context embeddings provided by Performers -- a low-rank implicit-attention Transformer. We jointly train the cost function and construct the controller relying on it, effectively solving end-to-end the corresponding bi-level optimization problem. We show that the resulting policy improves standard MPC performance by leveraging a few expert demonstrations of the desired navigation behavior in different challenging real-world scenarios. Compared with a standard MPC policy, Performer-MPC achieves >40% better goal reached in cluttered environments and >65% better on social metrics when navigating around humans.

As robots increasingly enter human-centered environments, they must not only be able to navigate safely around humans, but also adhere to complex social norms. Humans often rely on non-verbal communication through gestures and facial expressions when navigating around other people, especially in densely occupied spaces. Consequently, robots also need to be able to interpret gestures as part of solving social navigation tasks. To this end, we present Gesture2Path, a novel social navigation approach that combines image-based imitation learning with model-predictive control. Gestures are interpreted based on a neural network that operates on streams of images, while we use a state-of-the-art model predictive control algorithm to solve point-to-point navigation tasks. We deploy our method on real robots and showcase the effectiveness of our approach for the four gestures-navigation scenarios: left/right, follow me, and make a circle. Our experiments indicate that our method is able to successfully interpret complex human gestures and to use them as a signal to generate socially compliant trajectories for navigation tasks. We validated our method based on in-situ ratings of participants interacting with the robots., Comment: 8 pages, 12 figures

Adaptation to changing environments is a universal feature of life and can involve the organism modifying itself in response to the environment as well as actively modifying the environment to control selection pressures. The latter case couples the organism to environment. Then, how quickly should the organism change in response to the environment? We formulate this question in terms of how memory duration scales with environmental rate of change when there are trade-offs in remembering vs. forgetting. We derive a universal scaling law for optimal memory duration, taking into account memory precision as well as two components of environmental volatility, bias and stability. We find sublinear scaling with any amount of environmental volatility. We use a memory complexity measure to explore the strategic conditions (game dynamics) favoring actively reducing environmental volatility -- outsourcing memory through niche construction -- over investing in neural tissue. We predict stabilizing niche construction will evolve when neural tissue is costly, the environment is variable, and it is beneficial to be able to encode a rich repertoire of environmental states.