Search

Robots today can exploit the rich world knowledge of large language models to chain simple behavioral skills into long-horizon tasks. However, robots often get interrupted during long-horizon tasks due to primitive skill failures and dynamic environments. We propose VADER, a plan, execute, detect framework with seeking help as a new skill that enables robots to recover and complete long-horizon tasks with the help of humans or other robots. VADER leverages visual question answering (VQA) modules to detect visual affordances and recognize execution errors. It then generates prompts for a language model planner (LMP) which decides when to seek help from another robot or human to recover from errors in long-horizon task execution. We show the effectiveness of VADER with two long-horizon robotic tasks. Our pilot study showed that VADER is capable of performing complex long-horizon tasks by asking for help from another robot to clear a table. Our user study showed that VADER is capable of performing complex long-horizon tasks by asking for help from a human to clear a path. We gathered feedback from people (N=19) about the performance of the VADER performance vs. a robot that did not ask for help. https://google-vader.github.io/, Comment: 9 pages, 4 figures

This paper explores the possibilities of the current generation of Large Language Models for incorporating Machine Learning Operations (MLOps) functionalities into ML training code bases. We evaluate the performance of OpenAI (gpt-3.5-turbo) and WizardCoder (open-source, 15B parameters) models on the automated accomplishment of various MLOps functionalities in different settings. We perform a benchmarking study that assesses the ability of these models to: (1) adapt existing code samples (Inlining) with component-specific MLOps functionality such as MLflow and Weights & Biases for experiment tracking, Optuna for hyperparameter optimization etc., and (2) perform the task of Translation from one component of an MLOps functionality to another, e.g., translating existing GitPython library based version control code to Data Version Control library based. We also propose three different approaches that involve teaching LLMs to comprehend the API documentation of the components as a reference while accomplishing the Translation tasks. In our evaluations, the gpt-3.5-turbo model significantly outperforms WizardCoder by achieving impressive Pass@3 accuracy in model optimization (55% compared to 0% by WizardCoder), experiment tracking (100%, compared to 62.5% by WizardCoder), model registration (92% compared to 42% by WizardCoder) and hyperparameter optimization (83% compared to 58% by WizardCoder) on average, in their best possible settings, showcasing its superior code adaptability performance in complex MLOps tasks., Comment: The work was completed during 2Q, 3Q of Year 2023, when WizardCoder was the top performing Open source LLM for coding. Newer and better models have emerged since then. The processes and methodologies utilized for this benchmarking can still be utilized for evaluating the current SoTA models

This paper investigates the complexities of integrating Large Language Models (LLMs) into software products, with a focus on the challenges encountered for determining their readiness for release. Our systematic review of grey literature identifies common challenges in deploying LLMs, ranging from pre-training and fine-tuning to user experience considerations. The study introduces a comprehensive checklist designed to guide practitioners in evaluating key release readiness aspects such as performance, monitoring, and deployment strategies, aiming to enhance the reliability and effectiveness of LLM-based applications in real-world settings.

This article addresses the pump-scheduling optimization problem to enhance real-time control of real-world water distribution networks (WDNs). Our primary objectives are to adhere to physical operational constraints while reducing energy consumption and operational costs. Traditional optimization techniques, such as evolution-based and genetic algorithms, often fall short due to their lack of convergence guarantees. Conversely, reinforcement learning (RL) stands out for its adaptability to uncertainties and reduced inference time, enabling real-time responsiveness. However, the effective implementation of RL is contingent on building accurate simulation models for WDNs, and prior applications have been limited by errors in simulation training data. These errors can potentially cause the RL agent to learn misleading patterns and actions and recommend suboptimal operational strategies. To overcome these challenges, we present an improved "hybrid RL" methodology. This method integrates the benefits of RL while anchoring it in historical data, which serves as a baseline to incrementally introduce optimal control recommendations. By leveraging operational data as a foundation for the agent's actions, we enhance the explainability of the agent's actions, foster more robust recommendations, and minimize error. Our findings demonstrate that the hybrid RL agent can significantly improve sustainability, operational efficiency, and dynamically adapt to emerging scenarios in real-world WDNs.

With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time requirements. However, data distillation on text-based datasets hasn't been explored much because of the challenges rising due to its discrete nature. Additionally, existing dataset distillation methods often struggle to generalize to new architectures. In the paper, we propose several data distillation techniques for multilingual text classification datasets using language-model-based learning methods. We conduct experiments to analyze their performance in terms of classification strength, and cross-architecture generalization. Furthermore, we investigate the language-specific fairness of the data summaries generated by these methods. Our approach builds upon existing techniques, enhancing cross-architecture generalization in the text data distillation domain.

Silver nanoparticles (AgNP's) possess inherent biological potentials that have obliged an alternative, eco-friendly, sustainable approach to "Green Synthesis." In the present study, we synthesized Green Silver Nanoparticles (GAgNP's) using Curcuma longa L. (C. longa) flower extract as a reducing and capping agent. The synthesized GAgNP's were characterized using UV-Visible spectroscopy, X-ray diffraction (XRD), and High-resolution transmission electron microscopy (HR-TEM), which confirmed their homogeneity and physical characteristics. The GAgNP's were found to contain crystalline silver through XRD, and the particles were confirmed to be homogeneous and spherical with a size of approximately 5 nm, as evidenced by UV-Visible spectroscopy, XRD, and HR-TEM. In addition, the biological potential of GAgNP's was evaluated for their antibacterial activities. GAgNP's showed significant activity and formed different sizes of inhibition zones against all selected bacteria: Mycobacterium smegmatis (M. smegmatis) (26 mm), Mycobacterium phlei (M. phlei), and Staphylococcus aureus (S. aureus) (22 mm), Staphylococcus epidermidis (S. epidermidis) and Klebsiella pneumoniae (K. pneumoniae) (18 mm), and Escherichia coli (E. coli) (13 mm). The MIC value of GAgNP's was found to be between 625 ug/mL-39.06 ug/mL for different microbes tested. With further research, the green synthesis of GAgNP's using C. longa flower extracts could lead to the development of effective antibacterial treatments in the medical field.

Visualizations such as bar charts, scatter plots, and objects on geographical maps often convey critical information, including exact and relative numeric values, using shapes. The choice of shape and method of encoding information is often arbitrarily, or based on convention. However, past studies have shown that the human eye can be fooled by visual representations. The Ebbinghaus illusion demonstrates that the perceived relative sizes of shapes depends on their configuration, which in turn can affect judgements, especially in visualizations like proportional symbol maps. In this study we evaluate the effects of varying the type of shapes and metrics for encoding data in visual representations on a spatio-temporal map interface. We find that some combinations of shape and metric are more conducive to accurate human judgements than others, and provide recommendations for applying these findings in future visualization designs.

While many dashboards for visualizing COVID-19 data exist, most separate geospatial and temporal data into discrete visualizations or tables. Further, the common use of choropleth maps or space-filling map overlays supports only a single geospatial variable at once, making it difficult to compare the temporal and geospatial trends of multiple, potentially interacting variables, such as active cases, deaths, and vaccinations. We present CoronaViz, a COVID-19 visualization system that conveys multilayer, spatiotemporal data in a single, interactive display. CoronaViz encodes variables with concentric, hollow circles, termed geocircles, allowing multiple variables via color encoding and avoiding occlusion problems. The radii of geocircles relate to the values of the variables they represent via the psychophysically determined Flannery formula. The time dimension of spatiotemporal variables is encoded with sequential rendering. Animation controls allow the user to seek through time manually or to view the pandemic unfolding in accelerated time. An adjustable time window allows aggregation at any granularity, from single days to cumulative values for the entire available range. In addition to describing the CoronaViz system, we report findings from a user study comparing CoronaViz with multi-view dashboards from the New York Times and Johns Hopkins University. While participants preferred using the latter two dashboards to perform queries with only a geospatial component or only a temporal component, participants uniformly preferred CoronaViz for queries with both spatial and temporal components, highlighting the utility of a unified spatiotemporal encoding. CoronaViz is open-source and freely available at http://coronaviz.umiacs.io.

With the growing use of deep learning methods, particularly graph neural networks, which encode intricate interconnectedness information, for a variety of real tasks, there is a necessity for explainability in such settings. In this paper, we demonstrate the applicability of popular explainability approaches on Graph Attention Networks (GAT) for a graph-based super-pixel image classification task. We assess the qualitative and quantitative performance of these techniques on three different datasets and describe our findings. The results shed a fresh light on the notion of explainability in GNNs, particularly GATs.

Mid-Air Helicopter Delivery (MAHD) is a new Entry, Descent and Landing (EDL) architecture to enable in situ mobility for Mars science at lower cost than previous missions. It uses a jetpack to slow down a Mars Science Helicopter (MSH) after separation from the backshell, and reach aerodynamic conditions suitable for helicopter take-off in mid air. For given aeroshell dimensions, only MAHD's lander-free approach leaves enough room in the aeroshell to accommodate the largest rotor option for MSH. This drastically improves flight performance, notably allowing +150\% increased science payload mass. Compared to heritage EDL approaches, the simpler MAHD architecture is also likely to reduce cost, and enables access to more hazardous and higher-elevation terrains on Mars. This paper introduces a design for the MAHD system architecture and operations. We present a mechanical configuration that fits both MSH and the jetpack within the 2.65-m Mars heritage aeroshell, and a jetpack control architecture which fully leverages the available helicopter avionics. We discuss preliminary numerical models of the flow dynamics resulting from the interaction between the jets, the rotors and the side winds. We define a force-torque sensing architecture capable of handling the wind and trimming the rotors to prepare for safe take-off. Finally, we analyze the dynamic environment and closed-loop control simulation results to demonstrate the preliminary feasibility of MAHD., Comment: Accepted in 2022 IEEE Aerospace Conference

We give bijective proofs of orthosymplectic analogues of the Cauchy identity and dual Cauchy identity for orthosymplectic Schur functions. To do so, we present two insertion algorithms; these are orthosymplectic versions of Berele's symplectic insertion algorithms, which were used by Sundaram to give bijective proofs of Cauchy identities for symplectic Schur functions.