Fruit harvesting poses a significant labor and financial burden for the industry, highlighting the critical need for advancements in robotic harvesting solutions. Machine vision-based fruit detection has been recognized as a crucial component for robust identification of fruits to guide robotic manipulation. Despite considerable progress in leveraging deep learning and machine learning techniques for fruit detection, a common shortfall is the inability to swiftly extend the developed models across different orchards and/or various fruit species. Additionally, the limited availability of pertinent data further compounds these challenges. In this work, we introduce MetaFruit, the largest publicly available multi-class fruit dataset, comprising 4,248 images and 248,015 manually labeled instances across diverse U.S. orchards. Furthermore, this study proposes an innovative open-set fruit detection system leveraging advanced Vision Foundation Models (VFMs) for fruit detection that can adeptly identify a wide array of fruit types under varying orchard conditions. This system not only demonstrates remarkable adaptability in learning from minimal data through few-shot learning but also shows the ability to interpret human instructions for subtle detection tasks. The performance of the developed foundation model is comprehensively evaluated using several metrics, which outperforms the existing state-of-the-art algorithms in both our MetaFruit dataset and other open-sourced fruit datasets, thereby setting a new benchmark in the field of agricultural technology and robotic harvesting. The MetaFruit dataset and detection framework are open-sourced to foster future research in vision-based fruit harvesting, marking a significant stride toward addressing the urgent needs of the agricultural sector.

The integration of multimodal Electronic Health Records (EHR) data has significantly improved clinical predictive capabilities. Leveraging clinical notes and multivariate time-series EHR, existing models often lack the medical context relevent to clinical tasks, prompting the incorporation of external knowledge, particularly from the knowledge graph (KG). Previous approaches with KG knowledge have primarily focused on structured knowledge extraction, neglecting unstructured data modalities and semantic high dimensional medical knowledge. In response, we propose REALM, a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR representations that address these limitations. Firstly, we apply Large Language Model (LLM) to encode long context clinical notes and GRU model to encode time-series EHR data. Secondly, we prompt LLM to extract task-relevant medical entities and match entities in professionally labeled external knowledge graph (PrimeKG) with corresponding medical knowledge. By matching and aligning with clinical standards, our framework eliminates hallucinations and ensures consistency. Lastly, we propose an adaptive multimodal fusion network to integrate extracted knowledge with multimodal EHR data. Our extensive experiments on MIMIC-III mortality and readmission tasks showcase the superior performance of our REALM framework over baselines, emphasizing the effectiveness of each module. REALM framework contributes to refining the use of multimodal EHR data in healthcare and bridging the gap with nuanced medical context essential for informed clinical predictions.

Electronic Health Record (EHR) data, while rich in information, often suffers from sparsity, posing significant challenges in predictive modeling. Traditional imputation methods inadequately distinguish between real and imputed data, leading to potential inaccuracies in models. Addressing this, we introduce PRISM, a novel approach that indirectly imputes data through prototype representations of similar patients, thus ensuring denser and more accurate embeddings. PRISM innovates further with a feature confidence learner module, which evaluates the reliability of each feature in light of missing data. Additionally, it incorporates a novel patient similarity metric that accounts for feature confidence, avoiding overreliance on imprecise imputed values. Our extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate PRISM's superior performance in predicting in-hospital mortality and 30-day readmission tasks, showcasing its effectiveness in handling EHR data sparsity. For the sake of reproducibility and further research, we have made the code publicly available at https://github.com/yhzhu99/PRISM.

In this paper, we consider the alignment between an upstream dimensionality reduction task of learning a low-dimensional representation of a set of high-dimensional data and a downstream optimization task of solving a stochastic program parameterized by said representation. In this case, standard dimensionality reduction methods (e.g., principal component analysis) may not perform well, as they aim to maximize the amount of information retained in the representation and do not generally reflect the importance of such information in the downstream optimization problem. To address this problem, we develop a prescriptive dimensionality reduction framework that aims to minimize the degree of suboptimality in the optimization phase. For the case where the downstream stochastic optimization problem has an expected value objective, we show that prescriptive dimensionality reduction can be performed via solving a distributionally-robust optimization problem, which admits a semidefinite programming relaxation. Computational experiments based on a warehouse transshipment problem and a vehicle repositioning problem show that our approach significantly outperforms principal component analysis with real and synthetic data sets.