Recent foundation models are capable of handling multiple machine learning (ML) tasks and multiple data modalities with the unified base model structure and several specialized model components. However, the development of such multi-task (MT) multi-modal (MM) models poses significant model management challenges to existing training systems. Due to the sophisticated model architecture and the heterogeneous workloads of different ML tasks and data modalities, training these models usually requires massive GPU resources and suffers from sub-optimal system efficiency. In this paper, we investigate how to achieve high-performance training of large-scale MT MM models through data heterogeneity-aware model management optimization. The key idea is to decompose the model execution into stages and address the joint optimization problem sequentially, including both heterogeneity-aware workload parallelization and dependency-driven execution scheduling. Based on this, we build a prototype system and evaluate it on various large MT MM models. Experiments demonstrate the superior performance and efficiency of our system, with speedup ratio up to 71% compared to state-of-the-art training systems.

Analyzing large datasets to select optimal features is one of the most important research areas in machine learning and data mining. This feature selection procedure involves dimensionality reduction which is crucial in enhancing the performance of the model, making it less complex. Recently, several types of attribute selection methods have been proposed that use different approaches to obtain representative subsets of the attributes. However, population-based evolutionary algorithms like Genetic Algorithms (GAs) have been proposed to provide remedies for these drawbacks by avoiding local optima and improving the selection process itself. This manuscript presents a sweeping review on GA-based feature selection techniques in applications and their effectiveness across different domains. This review was conducted using the PRISMA methodology; hence, the systematic identification, screening, and analysis of relevant literature were performed. Thus, our results hint that the field's hybrid GA methodologies including, but not limited to, GA-Wrapper feature selector and HGA-neural networks, have substantially improved their potential through the resolution of problems such as exploration of unnecessary search space, accuracy performance problems, and complexity. The conclusions of this paper would result in discussing the potential that GAs bear in feature selection and future research directions for their enhancement in applicability and performance.

Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often requiring multiple iterations based on synthesis feedback. In contrast, existing compiler-based methods fall short in addressing complex designs. This paper introduces RTLRewriter, an innovative framework that leverages large models to optimize RTL code. A circuit partition pipeline is utilized for fast synthesis and efficient rewriting. A multi-modal program analysis is proposed to incorporate vital visual diagram information as optimization cues. A specialized search engine is designed to identify useful optimization guides, algorithms, and code snippets that enhance the model ability to generate optimized RTL. Additionally, we introduce a Cost-aware Monte Carlo Tree Search (C-MCTS) algorithm for efficient rewriting, managing diverse retrieved contents and steering the rewriting results. Furthermore, a fast verification pipeline is proposed to reduce verification cost. To cater to the needs of both industry and academia, we propose two benchmarking suites: the Large Rewriter Benchmark, targeting complex scenarios with extensive circuit partitioning, optimization trade-offs, and verification challenges, and the Small Rewriter Benchmark, designed for a wider range of scenarios and patterns. Our comparative analysis with established compilers such as Yosys and E-graph demonstrates significant improvements, highlighting the benefits of integrating large models into the early stages of circuit design. We provide our benchmarks at https://github.com/yaoxufeng/RTLRewriter-Bench.

Data scarcity poses a serious threat to modern machine learning and artificial intelligence, as their practical success typically relies on the availability of big datasets. One effective strategy to mitigate the issue of insufficient data is to first harness information from other data sources possessing certain similarities in the study design stage, and then employ the multi-task or meta learning framework in the analysis stage. In this paper, we focus on multi-task (or multi-source) linear models whose coefficients across tasks share an invariant low-rank component, a popular structural assumption considered in the recent multi-task or meta learning literature. Under this assumption, we propose a new algorithm, called Meta Subspace Pursuit (abbreviated as Meta-SP), that provably learns this invariant subspace shared by different tasks. Under this stylized setup for multi-task or meta learning, we establish both the algorithmic and statistical guarantees of the proposed method. Extensive numerical experiments are conducted, comparing Meta-SP against several competing methods, including popular, off-the-shelf model-agnostic meta learning algorithms such as ANIL. These experiments demonstrate that Meta-SP achieves superior performance over the competing methods in various aspects.

We present a new Monte Carlo Tree Search (MCTS) algorithm to solve the stochastic orienteering problem with chance constraints, i.e., a version of the problem where travel costs are random, and one is assigned a bound on the tolerable probability of exceeding the budget. The algorithm we present is online and anytime, i.e., it alternates planning and execution, and the quality of the solution it produces increases as the allowed computational time increases. Differently from most former MCTS algorithms, for each action available in a state the algorithm maintains estimates of both its value and the probability that its execution will eventually result in a violation of the chance constraint. Then, at action selection time, our proposed solution prunes away trajectories that are estimated to violate the failure probability. Extensive simulation results show that this approach can quickly produce high-quality solutions and is competitive with the optimal but time-consuming solution.

This study focuses on enhancing the design of an existing knee exoskeleton by addressing limitations in the range of motion (ROM) during Sit-to-Stand (STS) motions. While current knee exoskeletons emphasize toughness and rehabilitation, their closed-loop mechanisms hinder optimal ROM, which is crucial for effective rehabilitation. This research aims to optimize the exoskeleton design to achieve the necessary ROM, improving its functionality in rehabilitation. This can be achieved by utilizing kinematic modeling and formulation, the existing design was represented in the non-linear and non-convex mathematical functions. Optimization techniques, considering constraints based on human leg measurements, were applied to determine the best dimensions for the exoskeleton. This resulted in a significant increase in ROM compared to existing models. A MATLAB program was developed to compare the ROM of the optimized exoskeleton with the original design. To validate the practicality of the optimized design, analysis was conducted using a mannequin with average human dimensions, followed by constructing a cardboard dummy model to confirm simulation results. The STS motion of an average human was captured using a camera and TRACKER software, and the motion was compared with that of the dummy model to identify any misalignments between the human and exoskeleton knee joints. Furthermore, a prototype of the knee joint exoskeleton is being developed to further investigate misalignments and improve the design. Future work includes the use of EMG sensors for more detailed analysis and better results.

Representing robotic manipulation tasks as constraints that associate the robot and the environment is a promising way to encode desired robot behaviors. However, it remains unclear how to formulate the constraints such that they are 1) versatile to diverse tasks, 2) free of manual labeling, and 3) optimizable by off-the-shelf solvers to produce robot actions in real-time. In this work, we introduce Relational Keypoint Constraints (ReKep), a visually-grounded representation for constraints in robotic manipulation. Specifically, ReKep is expressed as Python functions mapping a set of 3D keypoints in the environment to a numerical cost. We demonstrate that by representing a manipulation task as a sequence of Relational Keypoint Constraints, we can employ a hierarchical optimization procedure to solve for robot actions (represented by a sequence of end-effector poses in SE(3)) with a perception-action loop at a real-time frequency. Furthermore, in order to circumvent the need for manual specification of ReKep for each new task, we devise an automated procedure that leverages large vision models and vision-language models to produce ReKep from free-form language instructions and RGB-D observations. We present system implementations on a wheeled single-arm platform and a stationary dual-arm platform that can perform a large variety of manipulation tasks, featuring multi-stage, in-the-wild, bimanual, and reactive behaviors, all without task-specific data or environment models. Website at https://rekep-robot.github.io.

Machine learning (ML) provides a broad spectrum of tools and architectures that enable the transformation of data from simulations and experiments into useful and explainable science, thereby augmenting domain knowledge. Furthermore, ML-enhanced numerical modelling can revamp scientific computing for real-world complex engineering systems, creating unique opportunities to examine the operation of the technologies in detail and automate their optimization and control. In recent years, ML applications have seen significant growth across various scientific domains, particularly in fluid mechanics, where ML has shown great promise in enhancing computational modeling of fluid flows. In contrast, ML applications in numerical plasma physics research remain relatively limited in scope and extent. Despite this, the close relationship between fluid mechanics and plasma physics presents a valuable opportunity to create a roadmap for transferring ML advances in fluid flow modeling to computational plasma physics. This Perspective aims to outline such a roadmap. We begin by discussing some general fundamental aspects of ML, including the various categories of ML algorithms and the different types of problems that can be solved with the help of ML. With regard to each problem type, we then present specific examples from the use of ML in computational fluid dynamics, reviewing several insightful prior efforts. We also review recent ML applications in plasma physics for each problem type. The paper discusses promising future directions and development pathways for ML in plasma modelling within the different application areas. Additionally, we point out prominent challenges that must be addressed to realize ML's full potential in computational plasma physics, including the need for cost-effective high-fidelity simulation tools for extensive data generation.

For optimization models to be used in practice, it is crucial that users trust the results. A key factor in this aspect is the interpretability of the solution process. A previous framework for inherently interpretable optimization models used decision trees to map instances to solutions of the underlying optimization model. Based on this work, we investigate how we can use more general optimization rules to further increase interpretability and at the same time give more freedom to the decision maker. The proposed rules do not map to a concrete solution but to a set of solutions characterized by common features. To find such optimization rules, we present an exact methodology using mixed-integer programming formulations as well as heuristics. We also outline the challenges and opportunities that these methods present. In particular, we demonstrate the improvement in solution quality that our approach offers compared to existing frameworks for interpretable optimization and we discuss the relationship between interpretability and performance. These findings are supported by experiments using both synthetic and real-world data.

Home repair and installation services require technicians to visit customers and resolve tasks of different complexity. Technicians often have heterogeneous skills and working experiences. The geographical spread of customers makes achieving only perfect matches between technician skills and task requirements impractical. Additionally, technicians are regularly absent due to sickness. With non-perfect assignments regarding task requirement and technician skill, some tasks may remain unresolved and require a revisit and rework. Companies seek to minimize customer inconvenience due to delay. We model the problem as a sequential decision process where, over a number of service days, customers request service while heterogeneously skilled technicians are routed to serve customers in the system. Each day, our policy iteratively builds tours by adding "important" customers. The importance bases on analytical considerations and is measured by respecting routing efficiency, urgency of service, and risk of rework in an integrated fashion. We propose a state-dependent balance of these factors via reinforcement learning. A comprehensive study shows that taking a few non-perfect assignments can be quite beneficial for the overall service quality. We further demonstrate the value provided by a state-dependent parametrization.