Search

We consider the problem of decomposing a global task assigned to a multi-agent system, expressed as a formula within a fragment of Signal Temporal Logic (STL), under range-limited communication. Given a global task expressed as a conjunction of local tasks defined over the individual and relative states of agents in the system, we propose representing task dependencies among agents as edges of a suitably defined task graph. At the same time, range-limited communication naturally induces the definition of a communication graph that defines which agents have access to each other's states. Within these settings, inconsistencies arise when a task dependency between a pair of agents is not supported by a corresponding communication link due to the limited communication range. As a result, state feedback control laws previously derived to achieve the tasks' satisfaction can not be leveraged. We propose a task decomposition mechanism to distribute tasks assigned to pairs of non-communicating agents in the system as conjunctions of tasks defined over the relative states of communicating agents, thus enforcing consistency between task and communication graphs. Assuming the super-level sets of the predicate functions composing the STL tasks are bounded polytopes, our task decomposition mechanism can be cast as a parameter optimization problem and solved via state-of-the-art decentralized convex optimization algorithms. To guarantee the soundness of our approach, we present various conditions under which the tasks defined in the applied STL fragment are unsatisfiable, and we show sufficient conditions such that our decomposition approach yields satisfiable global tasks after decomposition.

Real-world long-horizon embodied planning underpins embodied AI. To accomplish long-horizon tasks, agents need to decompose abstract instructions into detailed steps. Prior works mostly rely on GPT-4V for task decomposition into predefined actions, which limits task diversity due to GPT-4V's finite understanding of larger skillsets. Therefore, we present ReLEP, a groundbreaking framework for Real world Long-horizon Embodied Planning, which can accomplish a wide range of daily tasks. At its core lies a fine-tuned large vision language model that formulates plans as sequences of skill functions according to input instruction and scene image. These functions are selected from a carefully designed skill library. ReLEP is also equipped with a Memory module for plan and status recall, and a Robot Configuration module for versatility across robot types. In addition, we propose a semi-automatic data generation pipeline to tackle dataset scarcity. Real-world off-line experiments across eight daily embodied tasks demonstrate that ReLEP is able to accomplish long-horizon embodied tasks and outperforms other state-of-the-art baseline methods.

Interactive feedback, where feedback flows in both directions between teacher and student, is more effective than traditional one-way feedback. However, it is often too time-consuming for widespread use in educational practice. While Large Language Models (LLMs) have potential for automating feedback, they struggle with reasoning and interaction in an interactive setting. This paper introduces CAELF, a Contestable AI Empowered LLM Framework for automating interactive feedback. CAELF allows students to query, challenge, and clarify their feedback by integrating a multi-agent system with computational argumentation. Essays are first assessed by multiple Teaching-Assistant Agents (TA Agents), and then a Teacher Agent aggregates the evaluations through formal reasoning to generate feedback and grades. Students can further engage with the feedback to refine their understanding. A case study on 500 critical thinking essays with user studies demonstrates that CAELF significantly improves interactive feedback, enhancing the reasoning and interaction capabilities of LLMs. This approach offers a promising solution to overcoming the time and resource barriers that have limited the adoption of interactive feedback in educational settings.

We introduce a novel distributed sampled-data control method tailored for heterogeneous multi-agent systems under a global spatio-temporal task with acyclic dependencies. Specifically, we consider the global task as a conjunction of independent and collaborative tasks, defined over the absolute and relative states of agent pairs. Task dependencies in this form are then represented by a task graph, which we assume to be acyclic. From the given task graph, we provide an algorithmic approach to define a distributed sampled-data controller prioritizing the fulfilment of collaborative tasks as the primary objective, while fulfilling independent tasks unless they conflict with collaborative ones. Moreover, communication maintenance among collaborating agents is seamlessly enforced within the proposed control framework. A numerical simulation is provided to showcase the potential of our control framework., Comment: Short version of this paper was accepted for the Conference on Decision and Control. Reupload was needed for a misspelt name and corrected minor typos

Announcement games, where information is disseminated by announcers and challenged by validators, are prevalent in real-world scenarios. Validators take effort to verify the validity of the announcements, gaining rewards for successfully challenging invalid ones, while receiving nothing for valid ones. Optimistic Rollup, a Layer 2 blockchain scaling solution, exemplifies such games, offering significant improvements in transaction throughput and cost efficiency. We present a game-theoretic model of announcement games to analyze the potential behaviors of announcers and validators. We identify all Nash equilibria and study the corresponding system losses for different Nash equilibria. Additionally, we analyze the impact of various system parameters on system loss under the Nash equilibrium. Finally, we provide suggestions for mechanism optimization to reduce system losses., Comment: 31 pages

As a special type of collinear antiferromagnetism (AFM), altermagnetism has garnered significant research interest recently. Altermagnets exhibit broken parity-time symmetry and zero net magnetization in real space, leading to substantial band splitting in momentum space even in the absence of spin-orbit coupling. Meanwhile, parity-time symmetry breaking always induce nontrivial band topology such as Weyl nodes. While Weyl semimetal states and nodal lines have been theoretically proposed in altermagnets, rare reports of experimental observation have been made up to this point. Using ARPES and first-principles calculations, we systematically studied the electronic structure of the room-temperature altermagnet candidate CrSb. At generic locations in momentum space, we clearly observed band spin splitting. Furthermore, we identified discrete surface Fermi arcs on the (100) cleaved side surface close to the Fermi level originating from bulk band topology. Our results imply that CrSb contains interesting nontrivial topological Weyl physics, in addition to being an excellent room temperature altermagnet., Comment: 10 pages, 4 figures

In medical image segmentation, personalized cross-silo federated learning (FL) is becoming popular for utilizing varied data across healthcare settings to overcome data scarcity and privacy concerns. However, existing methods often suffer from client drift, leading to inconsistent performance and delayed training. We propose a new framework, Personalized Federated Learning via Feature Enhancement (pFLFE), designed to mitigate these challenges. pFLFE consists of two main stages: feature enhancement and supervised learning. The first stage improves differentiation between foreground and background features, and the second uses these enhanced features for learning from segmentation masks. We also design an alternative training approach that requires fewer communication rounds without compromising segmentation quality, even with limited communication resources. Through experiments on three medical segmentation tasks, we demonstrate that pFLFE outperforms the state-of-the-art methods.

Bioelectronic implants with soft mechanics, biocompatibility, and excellent electrical performance enable biomedical implants to record electrophysiological signals and execute interventions within internal organs, promising to revolutionize the diagnosing, monitoring, and treatment of various pathological conditions. However, challenges remain in improving excessive impedance at the bioelectronic-tissue interface and thus the efficacy of electrophysiological signaling and intervention. Here, we devise orbit symmetry breaking in MXene (a low-cost scalability, biocompatible, and conductive 2D layered material, that we refer to as OBXene), that exhibits low bioelectronic-tissue impedance, originating from the out-of-plane charge transfer. Furthermore, the Schottky-induced piezoelectricity stemming from the asymmetric orbital configuration of OBXene facilitates interlayered charge transport in the device. In this study, we report an OBXene-based cardiac patch applied on the left ventricular epicardium of both rodent and porcine models to enable spatiotemporal epicardium mapping and pacing, while coupling the wireless and battery-free operation for long-term real-time recording and closed-loop stimulation.

Recent developments have introduced a groundbreaking form of collinear magnetism known as "altermagnetism". This emerging magnetic phase is characterized by robust time-reversal symmetry breaking, antiparallel magnetic order, and alternating spin-splitting band structures, yet it exhibits vanishing net magnetization constrained by symmetry. Altermagnetism uniquely integrates traits previously considered mutually exclusive to conventional collinear ferromagnetism and antiferromagnetism, thereby facilitating phenomena and functionalities previously not achievable within these traditional categories of magnetism. Initially proposed theoretically, the existence of the altermagnetic phase has since been corroborated by a range of experimental studies, which have confirmed its unique properties and potential for applications. This review explores the rapidly expanding research on altermagnets, emphasizing the novel physical phenomena they manifest, methodologies for inducing altermagnetism, and promising altermagnetic materials. The goal of this review is to furnish readers with a comprehensive overview of altermagnetism and to inspire further innovative studies on altermagnetic materials which could potentially revolutionize applications in technology and materials science., Comment: Submitted to Adv. Funct. Mater

Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental formulation to leverage machine learning for solving molecular science problems. Yet, its applicability is limited by insufficient labeled data for training. In this work, we highlight that Hamiltonian prediction possesses a self-consistency principle, based on which we propose self-consistency training, an exact training method that does not require labeled data. It distinguishes the task from predicting other molecular properties by the following benefits: (1) it enables the model to be trained on a large amount of unlabeled data, hence addresses the data scarcity challenge and enhances generalization; (2) it is more efficient than running DFT to generate labels for supervised training, since it amortizes DFT calculation over a set of queries. We empirically demonstrate the better generalization in data-scarce and out-of-distribution scenarios, and the better efficiency over DFT labeling. These benefits push forward the applicability of Hamiltonian prediction to an ever-larger scale., Comment: Accepted by ICML 2024

In this work, we propose a method to decompose signal temporal logic (STL) tasks for multi-agent systems subject to constraints imposed by the communication graph. Specifically, we propose to decompose tasks defined over multiple agents which require multi-hop communication, by a set of sub-tasks defined over the states of agents with 1-hop distance over the communication graph. To this end, we parameterize the predicates of the tasks to be decomposed as suitable hyper-rectangles. Then, we show that by solving a constrained convex optimization, optimal parameters maximising the volume of the predicate's super-level sets can be computed for the decomposed tasks. In addition, we provide a formal definition of conflicting conjunctions of tasks for the considered STL fragment and a formal procedure to exclude such conjunctions from the solution set of possible decompositions. The proposed approach is demonstrated through simulations., Comment: This paper is accepted at 2024 American Control Conference (ACC)

Crystal structure prediction (CSP) has made significant progress, but most methods focus on unconditional generations of inorganic crystal with limited atoms in the unit cell. This study introduces XtalNet, the first equivariant deep generative model for end-to-end CSP from Powder X-ray Diffraction (PXRD). Unlike previous methods that rely solely on composition, XtalNet leverages PXRD as an additional condition, eliminating ambiguity and enabling the generation of complex organic structures with up to 400 atoms in the unit cell. XtalNet comprises two modules: a Contrastive PXRD-Crystal Pretraining (CPCP) module that aligns PXRD space with crystal structure space, and a Conditional Crystal Structure Generation (CCSG) module that generates candidate crystal structures conditioned on PXRD patterns. Evaluation on two MOF datasets (hMOF-100 and hMOF-400) demonstrates XtalNet's effectiveness. XtalNet achieves a top-10 Match Rate of 90.2% and 79% for hMOF-100 and hMOF-400 datasets in conditional crystal structure prediction task, respectively. XtalNet represents a significant advance in CSP, enabling the prediction of complex structures from PXRD data without the need for external databases or manual intervention. It has the potential to revolutionize PXRD analysis. It enables the direct prediction of crystal structures from experimental measurements, eliminating the need for manual intervention and external databases. This opens up new possibilities for automated crystal structure determination and the accelerated discovery of novel materials.

This paper investigates an important class of information-flow security property called opacity for stochastic control systems. Opacity captures whether a system's secret behavior (a subset of the system's behavior that is considered to be critical) can be kept from outside observers. Existing works on opacity for control systems only provide a binary characterization of the system's security level by determining whether the system is opaque or not. In this work, we introduce a quantifiable measure of opacity that considers the likelihood of satisfying opacity for stochastic control systems modeled as general Markov decision processes (gMDPs). We also propose verification methods tailored to the new notions of opacity for finite gMDPs by using value iteration techniques. Then, a new notion called approximate opacity-preserving stochastic simulation relation is proposed, which captures the distance between two systems' behaviors in terms of preserving opacity. Based on this new system relation, we show that one can verify opacity for stochastic control systems using their abstractions (modeled as finite gMDPs). We also discuss how to construct such abstractions for a class of gMDPs under certain stability conditions., Comment: 16 pages, 6 figures, journal submission

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

Cortical surface reconstruction (CSR) from MRI is key to investigating brain structure and function. While recent deep learning approaches have significantly improved the speed of CSR, a substantial amount of runtime is still needed to map the cortex to a topologically-correct spherical manifold to facilitate downstream geometric analyses. Moreover, this mapping is possible only if the topology of the surface mesh is homotopic to a sphere. Here, we present a method for simultaneous CSR and spherical mapping efficiently within seconds. Our approach seamlessly connects two sub-networks for white and pial surface generation. Residual diffeomorphic deformations are learned iteratively to gradually warp a spherical template mesh to the white and pial surfaces while preserving mesh topology and uniformity. The one-to-one vertex correspondence between the template sphere and the cortical surfaces allows easy and direct mapping of geometric features like convexity and curvature to the sphere for visualization and downstream processing. We demonstrate the efficacy of our approach on infant brain MRI, which poses significant challenges to CSR due to tissue contrast changes associated with rapid brain development during the first postnatal year. Performance evaluation based on a dataset of infants from 0 to 12 months demonstrates that our method substantially enhances mesh regularity and reduces geometric errors, outperforming state-of-the-art deep learning approaches, all while maintaining high computational efficiency.

Decentralized Federated learning is a distributed edge intelligence framework by exchanging parameter updates instead of training data among participators, in order to retrain or fine-tune deep learning models for mobile intelligent applications. Considering the various topologies of edge networks in mobile internet, the impact of transmission delay of updates during model training is non-negligible for data-intensive intelligent applications on mobile devices, e.g., intelligent medical services, automated driving vehicles, etc.. To address this problem, we analyze the impact of delayed updates for decentralized federated learning, and provide a theoretical bound for these updates to achieve model convergence. Within the theoretical bound of updating period, the latest versions for the delayed updates are reused to continue aggregation, in case the model parameters from a specific neighbor are not collected or updated in time.

Orbital-free density functional theory (OFDFT) is a quantum chemistry formulation that has a lower cost scaling than the prevailing Kohn-Sham DFT, which is increasingly desired for contemporary molecular research. However, its accuracy is limited by the kinetic energy density functional, which is notoriously hard to approximate for non-periodic molecular systems. Here we propose M-OFDFT, an OFDFT approach capable of solving molecular systems using a deep learning functional model. We build the essential non-locality into the model, which is made affordable by the concise density representation as expansion coefficients under an atomic basis. With techniques to address unconventional learning challenges therein, M-OFDFT achieves a comparable accuracy with Kohn-Sham DFT on a wide range of molecules untouched by OFDFT before. More attractively, M-OFDFT extrapolates well to molecules much larger than those seen in training, which unleashes the appealing scaling of OFDFT for studying large molecules including proteins, representing an advancement of the accuracy-efficiency trade-off frontier in quantum chemistry., Comment: Published in Nature Computational Science, March 2024. Full paper with supplementary information

This paper considers the problem of controller synthesis of signal temporal logic (STL) specifications for large-scale multi-agent systems, where the agents are dynamically coupled and subject to collaborative tasks. A compositional framework based on continuous-time assume-guarantee contracts is developed to break the complex and large synthesis problem into subproblems of manageable sizes. We first show how to formulate the collaborative STL tasks as assume-guarantee contracts by leveraging the idea of funnel-based control. The concept of contracts is used to establish our compositionality result, which allows us to guarantee the satisfaction of a global contract by the multi-agent system when all agents satisfy their local contracts. Then, a closed-form continuous-time feedback controller is designed to enforce local contracts over the agents in a distributed manner, which further guarantees the global task satisfaction based on the compositionality result. Finally, the effectiveness of our results is demonstrated by two numerical examples., Comment: arXiv admin note: substantial text overlap with arXiv:2203.10041

In this paper, we present the synthesis of secure-by-construction controllers that address safety and security properties simultaneously in cyber-physical systems. Our focus is on studying a specific security property called opacity, which characterizes the system's ability to maintain plausible deniability of its secret behavior in the presence of an intruder. These controllers are synthesized based on a concept of so-called (augmented) control barrier functions, which we introduce and discuss in detail. We propose conditions that facilitate the construction of the desired (augmented) control barrier functions and their corresponding secure-by-construction controllers. To compute these functions, we propose an iterative scheme that leverages iterative sum-of-square programming techniques. This approach enables efficient computation of these functions, particularly for polynomial systems. Moreover, we demonstrate the flexibility of our approach by incorporating user-defined cost functions into the construction of secure-by-construction controllers. Finally, we validate the effectiveness of our results through two case studies, illustrating the practical applicability and benefits of our proposed approach.