Sim-to-real transfer remains a significant challenge in soft robotics due to the unpredictability introduced by common manufacturing processes such as 3D printing and molding. These processes often result in deviations from simulated designs, requiring multiple prototypes before achieving a functional system. In this study, we propose a novel methodology to address these limitations by combining advanced rapid prototyping techniques and an efficient optimization strategy. Firstly, we employ rapid prototyping methods typically used for rigid structures, leveraging their precision to fabricate compliant components with reduced manufacturing errors. Secondly, our optimization framework minimizes the need for extensive prototyping, significantly reducing the iterative design process. The methodology enables the identification of stiffness parameters that are more practical and achievable within current manufacturing capabilities. The proposed approach demonstrates a substantial improvement in the efficiency of prototype development while maintaining the desired performance characteristics. This work represents a step forward in bridging the sim-to-real gap in soft robotics, paving the way towards a faster and more reliable deployment of soft robotic systems.

Federated learning (FL) has emerged as a pivotal solution for training machine learning models over wireless networks, particularly for Internet of Things (IoT) devices with limited computation resources. Despite its benefits, the efficiency of FL is often restricted by the communication quality between IoT devices and the central server. To address this issue, we introduce an innovative approach by deploying an unmanned aerial vehicle (UAV) as a mobile FL server to enhance the training process of FL. By leveraging the UAV's maneuverability, we establish robust line-of-sight connections with IoT devices, significantly improving communication capacity. To improve the overall training efficiency, we formulate a latency minimization problem by jointly optimizing the bandwidth allocation, computing frequencies, transmit power for both the UAV and IoT devices, and the UAV's trajectory. Then, an efficient alternating optimization algorithm is developed to solve it efficiently. Furthermore, we analyze the convergence and computational complexity of the proposed algorithm. Finally, numerical results demonstrate that our proposed scheme not only outperforms existing benchmark schemes in terms of latency but also achieves training efficiency that closely approximate the ideal scenario.

Self-supervised learning has the potential of lifting several of the key challenges in reinforcement learning today, such as exploration, representation learning, and reward design. Recent work (METRA) has effectively argued that moving away from mutual information and instead optimizing a certain Wasserstein distance is important for good performance. In this paper, we argue that the benefits seen in that paper can largely be explained within the existing framework of mutual information skill learning (MISL). Our analysis suggests a new MISL method (contrastive successor features) that retains the excellent performance of METRA with fewer moving parts, and highlights connections between skill learning, contrastive representation learning, and successor features. Finally, through careful ablation studies, we provide further insight into some of the key ingredients for both our method and METRA.

We consider the problem of finite-horizon sequential experimental design to solve multi-objective optimization (MOO) of expensive black-box objective functions. This problem arises in many real-world applications, including materials design, where we have a small resource budget to make and evaluate candidate materials in the lab. We solve this problem using the framework of Bayesian optimization (BO) and propose the first set of non-myopic methods for MOO problems. Prior work on non-myopic BO for single-objective problems relies on the Bellman optimality principle to handle the lookahead reasoning process. However, this principle does not hold for most MOO problems because the reward function needs to satisfy some conditions: scalar variable, monotonicity, and additivity. We address this challenge by using hypervolume improvement (HVI) as our scalarization approach, which allows us to use a lower-bound on the Bellman equation to approximate the finite-horizon using a batch expected hypervolume improvement (EHVI) acquisition function (AF) for MOO. Our formulation naturally allows us to use other improvement-based scalarizations and compare their efficacy to HVI. We derive three non-myopic AFs for MOBO: 1) the Nested AF, which is based on the exact computation of the lower bound, 2) the Joint AF, which is a lower bound on the nested AF, and 3) the BINOM AF, which is a fast and approximate variant based on batch multi-objective acquisition functions. Our experiments on multiple diverse real-world MO problems demonstrate that our non-myopic AFs substantially improve performance over the existing myopic AFs for MOBO.

In this work, we present an approach to minimizing the time necessary for the end-effector of a redundant robot manipulator to traverse a Cartesian path by optimizing the trajectory of its joints. Each joint has limits in the ranges of position, velocity and acceleration, the latter making jerks in joint space undesirable. The proposed approach takes this nonlinear optimization problem whose variables are path speed and joint trajectory and reformulates it into a bi-level problem. The lower-level formulation is a convex subproblem that considers a fixed joint trajectory and maximizes path speed while considering all joint velocity and acceleration constraints. Under particular conditions, this subproblem has a closed-form solution. Then, we solve a higher-level subproblem by leveraging the directional derivative of the lower-level value with respect to the joint trajectory parameters. In particular, we use this direction to implement a Primal-Dual method that considers the path accuracy and joint position constraints. We show the efficacy of our proposed approach with simulations and experimental results.

However, due to the high-dimensional nature of the problem space and scarcity of high-quality 3D data, these pre-trained models still struggle to generalize to many challenging circumstances, such as limited view overlap or low lighting. To address this, we propose LoRA3D, an efficient self-calibration pipeline to specialize the pre-trained models to target scenes using their own multi-view predictions. Taking sparse RGB images as input, we leverage robust optimization techniques to refine multiview predictions and align them into a global coordinate frame. In particular, we incorporate prediction confidence into the geometric optimization process, automatically re-weighting the confidence to better reflect point estimation accuracy. We use the calibrated confidence to generate high-quality pseudo labels for the calibrating views and use low-rank adaptation (LoRA) to fine-tune the models on the pseudo-labeled data. Our method does not require any external priors or manual labels. It completes the self-calibration process on a single standard GPU within just 5 minutes. Each low-rank adapter requires only 18MB of storage. We evaluated our method on more than 160 scenes from the Replica, TUM and Waymo Open datasets, achieving up to 88% performance improvement on 3D reconstruction, multi-view pose estimation and novel-view rendering. Figure 1: Given sparse RGB images, our self-calibration pipeline efficiently specializes a pre-trained 3D foundation model to a target scene to improve its performance for a variety of 3D vision tasks. 1 These models, typically enabled by large scale Transformer pre-training, can quickly establish crossview correspondences and directly regress 3D scene geometry from sparse RGB images. They generalize to a broad range of data and exhibit a strong zero-shot performance on novel tasks.

To optimize large Transformer model training, efficient parallel computing and advanced data management are essential. However, current methods often assume a stable and uniform training workload, neglecting imbalances in data sampling and packing that can impede performance. Specifically, data sampling imbalance arises from uneven sequence length distribution of the training data, while data packing imbalance stems from the discrepancy between the linear memory complexity and quadratic time complexity of the attention mechanism. To address these imbalance issues, we develop Hydraulis, which jointly optimizes the parallel strategies and data assignment. For one thing, we introduce large model training with dynamic heterogeneous parallel strategies in response to the sequence length variations within and across training iterations. For another, we devise a two-stage data assignment approach, which strikes a good balance in terms of the training workloads both within and across model replicas. Empirical results demonstrate that Hydraulis outperforms existing systems by 1.32-2.66 times.

Optimal prompt selection is crucial for maximizing large language model (LLM) performance on downstream tasks. As the most powerful models are proprietary and can only be invoked via an API, users often manually refine prompts in a black-box setting by adjusting instructions and few-shot examples until they achieve good performance as measured on a validation set. Recent methods addressing static black-box prompt selection face significant limitations: They often fail to leverage the inherent structure of prompts, treating instructions and few-shot exemplars as a single block of text. Moreover, they often lack query-efficiency by evaluating prompts on all validation instances, or risk sub-optimal selection of a prompt by using random subsets of validation instances. We introduce HbBoPs, a novel Hyperband-based Bayesian optimization method for black-box prompt selection addressing these key limitations. Our approach combines a structural-aware deep kernel Gaussian Process to model prompt performance with Hyperband as a multi-fidelity scheduler to select the number of validation instances for prompt evaluations. The structural-aware modeling approach utilizes separate embeddings for instructions and few-shot exemplars, enhancing the surrogate model's ability to capture prompt performance and predict which prompt to evaluate next in a sample-efficient manner. Together with Hyperband as a multi-fidelity scheduler we further enable query-efficiency by adaptively allocating resources across different fidelity levels, keeping the total number of validation instances prompts are evaluated on low. Extensive evaluation across ten benchmarks and three LLMs demonstrate that HbBoPs outperforms state-of-the-art methods.

Embeddings play a pivotal role across various disciplines, offering compact representations of complex data structures. Randomized methods like Johnson-Lindenstrauss (JL) provide state-of-the-art and essentially unimprovable theoretical guarantees for achieving such representations. These guarantees are worst-case and in particular, neither the analysis, nor the algorithm, takes into account any potential structural information of the data. The natural question is: must we randomize? Could we instead use an optimization-based approach, working directly with the data? A first answer is no: as we show, the distance-preserving objective of JL has a non-convex landscape over the space of projection matrices, with many bad stationary points. But this is not the final answer. We present a novel method motivated by diffusion models, that circumvents this fundamental challenge: rather than performing optimization directly over the space of projection matrices, we use optimization over the larger space of random solution samplers, gradually reducing the variance of the sampler. We show that by moving through this larger space, our objective converges to a deterministic (zero variance) solution, avoiding bad stationary points. This method can also be seen as an optimization-based derandomization approach and is an idea and method that we believe can be applied to many other problems.

This paper studies the performative policy learning problem, where agents adjust their features in response to a released policy to improve their potential outcomes, inducing an endogenous distribution shift. There has been growing interest in training machine learning models in strategic environments, including strategic classification and performative prediction. However, existing approaches often rely on restrictive parametric assumptions: micro-level utility models in strategic classification and macro-level data distribution maps in performative prediction, severely limiting scalability and generalizability. We approach this problem as a complex causal inference task, relaxing parametric assumptions on both micro-level agent behavior and macro-level data distribution. Leveraging bounded rationality, we uncover a practical low-dimensional structure in distribution shifts and construct an effective mediator in the causal path from the deployed model to the shifted data. We then propose a gradient-based policy optimization algorithm with a differentiable classifier as a substitute for the high-dimensional distribution map. Our algorithm efficiently utilizes batch feedback and limited manipulation patterns. Our approach achieves high sample efficiency compared to methods reliant on bandit feedback or zero-order optimization. We also provide theoretical guarantees for algorithmic convergence. Extensive and challenging experiments on high-dimensional settings demonstrate our method's practical efficacy.