Despite recent advancements, the field of text-to-image synthesis still suffers from lack of fine-grained control. Using only text, it remains challenging to deal with issues such as concept coherence and concept contamination. We propose a method to enhance control by generating specific concepts that can be reused throughout multiple images, effectively expanding natural language with new words that can be combined much like a painter's palette. Unlike previous contributions, our method does not copy visuals from input data and can generate concepts through text alone. We perform a set of comparisons that finds our method to be a significant improvement over text-only prompts.

ABSTRACT Short-term demand forecasting for on-demand ride-hailing services is one of the fundamental issues in intelligent transportation systems. However, previous travel demand forecasting research predominantly focused on improving prediction accuracy, ignoring fairness issues such as systematic underestimations of travel demand in disadvantaged neighborhoods. This study investigates how to measure, evaluate, and enhance prediction fairness between disadvantaged and privileged communities in spatial-temporal demand forecasting of ride-hailing services. A two-pronged approach is taken to reduce the demand prediction bias. First, we develop a novel deep learning model architecture, named socially aware neural network (SA-Net), to integrate the socio-demographics and ridership information for fair demand prediction through an innovative socially-aware convolution operation. Second, we propose a bias-mitigation regularization method to mitigate the mean percentage prediction error gap between different groups. The experimental results, validated on the real-world Chicago Transportation Network Company (TNC) data, show that the de-biasing SA-Net can achieve better predictive performance in both prediction accuracy and fairness. Specifically, the SA-Net improves prediction accuracy for both the disadvantaged and privileged groups compared with the state-of-the-art models. When coupled with the bias mitigation regularization method, the de-biasing SA-Net effectively bridges the mean percentage prediction error gap between the disadvantaged and privileged groups, and also protects the disadvantaged regions against systematic underestimation of TNC demand. Our proposed de-biasing method can be adopted in many existing short-term travel demand estimation models, and can be utilized for various other spatial-temporal prediction tasks such as crime incidents predictions. This is one of the first studies to consider prediction fairness in short-term travel demand forecasting. Keywords: Spatial-temporal travel demand prediction, algorithmic fairness, demand forecasting, ride-hailing service 2 1. INTRODUCTION In recent years, on-demand ride-hailing services have grown rapidly.

Esker, a global cloud platform and leader in AI-driven process automation solutions for Finance and Customer Service functions, announced a strategic partnership with Ecuador-based BPONE: The Best Professional Outsourcing, a global company specializing in outsourcing and consulting services. With BPONE's deep understanding of the local market and Esker's industry-leading technology, the partnership is poised to drive significant growth and impact for both companies in Latin America as they seek to advance digitization throughout the region. "Many Latin American businesses continue to rely on manual processes to handle back-office tasks rather than applying technology-forward advancements to boost productivity" Since 2016, BPONE has maintained a growth mindset at the forefront of its operations. The company successfully expanded from Ecuador to open new offices in Colombia, Peru, the U.S., Spain and more to further establish its global footprint. As its reach grew, company leadership recognized the need for a sophisticated automation intelligence system to offer to its clients that could handle an influx of invoices and streamline efficiencies while decreasing mistakes caused by manual tasks.

In recent years, the problem of fuzzy clustering has been widely concerned. The membership iteration of existing methods is mostly considered globally, which has considerable problems in noisy environments, and iterative calculations for clusters with a large number of different sample sizes are not accurate and efficient. In this paper, starting from the strategy of large-scale priority, the data is fuzzy iterated using granular-balls, and the membership degree of data only considers the two granular-balls where it is located, thus improving the efficiency of iteration. The formed fuzzy granular-balls set can use more processing methods in the face of different data scenarios, which enhances the practicability of fuzzy clustering calculations.

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It also iteratively revises LLM prompts to improve model responses using feedback generated by utility functions, e.g., the factuality score of a LLM-generated response. The effectiveness of LLM-Augmenter is empirically validated on two types of scenarios, task-oriented dialog and open-domain question answering. LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses. We make the source code and models publicly available.

Global financial systems have seen considerable growth in size, concentration, and complexity over the past few decades, the complexity of financial systems exceeds the modelling capabilities of traditional quantitative methods. In addition, some very useful data sets, such as satellite images, voice recordings or news sentiment, are beyond the reach of econometrics[2]. In recent years, many hedge funds have started experimenting with machine learning (ML) methods. ML is a subset of artificial intelligence, where machines are used to learn from previous experience[3]. Unlike traditional programming, where developers need to predict every potential condition to program, ML's solution can effectively tailor the output to the data.

I present a quick and sound method for the robustness verification of a sort of quantum classifiers who are Linear Sound. Since quantum machine learning has been put into practice in relevant fields and Linear Sound Property, LSP is a pervasive property, the method could be universally applied. I implemented my method with a Quantum Convolutional Neural Network, QCNN using MindQuantum, Huawei and successfully verified its robustness when classifying MNIST dataset.

Convolution is one of the most computationally intensive operations that must be performed for machine-learning model inference. A traditional approach to compute convolutions is known as the Im2Col + BLAS method. This paper proposes SConv: a direct-convolution algorithm based on a MLIR/LLVM code-generation toolchain that can be integrated into machine-learning compilers . This algorithm introduces: (a) Convolution Slicing Analysis (CSA) - a convolution-specific 3D cache-blocking analysis pass that focuses on tile reuse over the cache hierarchy; (b) Convolution Slicing Optimization (CSO) - a code-generation pass that uses CSA to generate a tiled direct-convolution macro-kernel; and (c) Vector-Based Packing (VBP) - an architecture-specific optimized input-tensor packing solution based on vector-register shift instructions for convolutions with unitary stride. Experiments conducted on 393 convolutions from full ONNX-MLIR machine-learning models indicate that the elimination of the Im2Col transformation and the use of fast packing routines result in a total packing time reduction, on full model inference, of 2.0x - 3.9x on Intel x86 and 3.6x - 7.2x on IBM POWER10. The speed-up over an Im2Col + BLAS method based on current BLAS implementations for end-to-end machine-learning model inference is in the range of 9% - 25% for Intel x86 and 10% - 42% for IBM POWER10 architectures. The total convolution speedup for model inference is 12% - 27% on Intel x86 and 26% - 46% on IBM POWER10. SConv also outperforms BLAS GEMM, when computing pointwise convolutions, in more than 83% of the 219 tested instances.

This work investigates the importance of feature selection for improving the forecasting performance of machine learning algorithms for financial data. Artificial neural networks (ANN), convolutional neural networks (CNN), long-short term memory (LSTM) networks, as well as linear models were applied for forecasting purposes. The Feature Selection with Annealing (FSA) algorithm was used to select the features from about 1000 possible predictors obtained from 26 technical indicators with specific periods and their lags. In addition to this, the Boruta feature selection algorithm was applied as a baseline feature selection method. The dependent variables consisted of daily logarithmic returns and daily trends of ten financial data sets, including cryptocurrency and different stocks. Experiments indicate that the FSA algorithm increased the performance of ML models regardless of the problem type. The FSA hybrid machine learning models showed better performance in 10 out of 10 data sets for regression and 8 out of 10 data sets for classification. None of the hybrid Boruta models outperformed the hybrid FSA models. However, the BORCNN model performance was comparable to the best model for 4 out of 10 data sets for regression estimates. BOR-LR and BOR-CNN models showed comparable performance with the best hybrid FSA models in 2 out of 10 datasets for classification. FSA was observed to improve the model performance in both better performance metrics as well as a decreased computation time by providing a lower dimensional input feature space.

Clinicians prescribe antibiotics by looking at the patient's health record with an experienced eye. However, the therapy might be rendered futile if the patient has drug resistance. Determining drug resistance requires time-consuming laboratory-level testing while applying clinicians' heuristics in an automated way is difficult due to the categorical or binary medical events that constitute health records. In this paper, we propose a novel framework for rapid clinical intervention by viewing health records as graphs whose nodes are mapped from medical events and edges as correspondence between events in given a time window. A novel graph-based model is then proposed to extract informative features and yield automated drug resistance analysis from those high-dimensional and scarce graphs. The proposed method integrates multi-task learning into a common feature extracting graph encoder for simultaneous analyses of multiple drugs as well as stabilizing learning. On a massive dataset comprising over 110,000 patients with urinary tract infections, we verify the proposed method is capable of attaining superior performance on the drug resistance prediction problem. Furthermore, automated drug recommendations resemblant to laboratory-level testing can also be made based on the model resistance analysis.