Document question answering is a task of question answering on given documents such as reports, slides, pamphlets, and websites, and it is a truly demanding task as paper and electronic forms of documents are so common in our society. This is known as a quite challenging task because it requires not only text understanding but also understanding of figures and tables, and hence visual question answering (VQA) methods are often examined in addition to textual approaches. We introduce Japanese Document Question Answering (JDocQA), a large-scale document-based QA dataset, essentially requiring both visual and textual information to answer questions, which comprises 5,504 documents in PDF format and annotated 11,600 question-and-answer instances in Japanese. Each QA instance includes references to the document pages and bounding boxes for the answer clues. We incorporate multiple categories of questions and unanswerable questions from the document for realistic question-answering applications. We empirically evaluate the effectiveness of our dataset with text-based large language models (LLMs) and multimodal models. Incorporating unanswerable questions in finetuning may contribute to harnessing the so-called hallucination generation.

Indoor positioning using UWB technology has gained interest due to its centimeter-level accuracy potential. However, multipath effects and non-line-of-sight conditions cause ranging errors between anchors and tags. Existing approaches for mitigating these ranging errors rely on collecting large labeled datasets, making them impractical for real-world deployments. This paper proposes a novel self-supervised deep reinforcement learning approach that does not require labeled ground truth data. A reinforcement learning agent uses the channel impulse response as a state and predicts corrections to minimize the error between corrected and estimated ranges. The agent learns, self-supervised, by iteratively improving corrections that are generated by combining the predictability of trajectories with filtering and smoothening. Experiments on real-world UWB measurements demonstrate comparable performance to state-of-the-art supervised methods, overcoming data dependency and lack of generalizability limitations. This makes self-supervised deep reinforcement learning a promising solution for practical and scalable UWB-ranging error correction.

The aim of attending an educational institution is learning, which in turn is sought after for the reason of independence of thoughts, ideologies as well as physical and material independence. This physical and material independence is gotten from working in the industry, that is, being a part of the independent working population of the country. There needs to be a way by which students upon graduation can easily adapt to the real world with necessary skills and knowledge required. This problem has been a challenge in some computer science departments, which after effects known after the student begins to work in an industry. The objectives of this project include: Designing a web based chat application for the industry and computer science department, Develop a web based chat application for the industry and computer science and Evaluate the web based chat application for the industry and computer science department. Waterfall system development lifecycle is used in establishing a system project plan, because it gives an overall list of processes and sub-processes required in developing a system. The descriptive research method applied in this project is documentary analysis of previous articles. The result of the project is the design, software a web-based chat application that aids communication between the industry and the computer science department and the evaluation of the system. The application is able to store this information which can be decided to be used later. Awareness of the software to companies and universities, implementation of the suggestions made by the industry in the computer science curriculum, use of this software in universities across Nigeria and use of this not just in the computer science field but in other field of study

Mariza Ferro is a professor at the Federal Fluminense University and a visiting professor at Bordeaux University. She has been working in the field of AI since 2002. She works on AI for good, including human-centric AI, ethical and trustworthy AI, green and sustainable AI, and AI for sustainable development goals. She guides her research based on the principle that AI must benefit humankind. Furthermore, she is also working with public outreach by making science available for all.

Musk has announced Grok's expanded availability in a tweet, along with an instructional video on how to post a conversation with the chatbot directly on the X website. Grok has been available to X's Premium subscribers since it exited early beta, but that paid tier on the social network costs 16 a month or 168 for the full year when billed annually. Since the Premium tier costs half that much at 8 a month or 84 a year, this rollout makes Grok a bit more accessible. Later this week, Grok will be enabled for all premium subscribers (not just premium) https://t.co/4u9lbLwe23 Just a couple of weeks before that, the executive sued OpenAI and Sam Altman, accusing them of chasing profits and abandoning their non-profit mission.

Machine learning solutions are very popular in the field of chemoinformatics, where they have numerous applications, such as novel drug discovery or molecular property prediction. Molecular fingerprints are algorithms commonly used for vectorizing chemical molecules as a part of preprocessing in this kind of solution. However, despite their popularity, there are no libraries that implement them efficiently for large datasets, utilizing modern, multicore architectures. On top of that, most of them do not provide the user with an intuitive interface, or one that would be compatible with other machine learning tools. In this project, we created a Python library that computes molecular fingerprints efficiently and delivers an interface that is comprehensive and enables the user to easily incorporate the library into their existing machine learning workflow. The library enables the user to perform computation on large datasets using parallelism. Because of that, it is possible to perform such tasks as hyperparameter tuning in a reasonable time. We describe tools used in implementation of the library and asses its time performance on example benchmark datasets. Additionally, we show that using molecular fingerprints we can achieve results comparable to state-of-the-art ML solutions even with very simple models.

The interest in predicting online learning performance using ML algorithms has been steadily increasing. We first conducted a scientometric analysis to provide a systematic review of research in this area. The findings show that most existing studies apply the ML methods without considering learning behavior patterns, which may compromise the prediction accuracy and precision of the ML methods. This study proposes an integration framework that blends learning behavior analysis with ML algorithms to enhance the prediction accuracy of students' online learning performance. Specifically, the framework identifies distinct learning patterns among students by employing clustering analysis and implements various ML algorithms to predict performance within each pattern. For demonstration, the integration framework is applied to a real dataset from edX and distinguishes two learning patterns, as in, low autonomy students and motivated students. The results show that the framework yields nearly perfect prediction performance for autonomous students and satisfactory performance for motivated students. Additionally, this study compares the prediction performance of the integration framework to that of directly applying ML methods without learning behavior analysis using comprehensive evaluation metrics. The results consistently demonstrate the superiority of the integration framework over the direct approach, particularly when integrated with the best-performing XGBoosting method. Moreover, the framework significantly improves prediction accuracy for the motivated students and for the worst-performing random forest method. This study also evaluates the importance of various learning behaviors within each pattern using LightGBM with SHAP values. The implications of the integration framework and the results for online education practice and future research are discussed.

Synchronous federated learning (FL) is a popular paradigm for collaborative edge learning. It typically involves a set of heterogeneous devices locally training neural network (NN) models in parallel with periodic centralized aggregations. As some of the devices may have limited computational resources and varying availability, FL latency is highly sensitive to stragglers. Conventional approaches discard incomplete intra-model updates done by stragglers, alter the amount of local workload and architecture, or resort to asynchronous settings; which all affect the trained model performance under tight training latency constraints. In this work, we propose straggler-aware layer-wise federated learning (SALF) that leverages the optimization procedure of NNs via backpropagation to update the global model in a layer-wise fashion. SALF allows stragglers to synchronously convey partial gradients, having each layer of the global model be updated independently with a different contributing set of users. We provide a theoretical analysis, establishing convergence guarantees for the global model under mild assumptions on the distribution of the participating devices, revealing that SALF converges at the same asymptotic rate as FL with no timing limitations. This insight is matched with empirical observations, demonstrating the performance gains of SALF compared to alternative mechanisms mitigating the device heterogeneity gap in FL.

Recent advancements highlight the success of instruction tuning with large language models (LLMs) utilizing Chain-of-Thought (CoT) data for mathematical reasoning tasks. Despite the fine-tuned LLMs, challenges persist, such as incorrect, missing, and redundant steps in CoT generation leading to inaccuracies in answer predictions. To alleviate this problem, we propose a dual instruction tuning strategy to meticulously model mathematical reasoning from both forward and reverse directions. This involves introducing the Intermediate Reasoning State Prediction task (forward reasoning) and the Instruction Reconstruction task (reverse reasoning) to enhance the LLMs' understanding and execution of instructions. Training instances for these tasks are constructed based on existing mathematical instruction tuning datasets. Subsequently, LLMs undergo multi-task fine-tuning using both existing mathematical instructions and the newly created data. Comprehensive experiments validate the effectiveness and domain generalization of the dual instruction tuning strategy across various mathematical reasoning tasks.

LLMs have become the go-to choice for code generation tasks, with an exponential increase in the training, development, and usage of LLMs specifically for code generation. To evaluate the ability of LLMs on code, both academic and industry practitioners rely on popular handcrafted benchmarks. However, prior benchmarks contain only a very limited set of problems, both in quantity and variety. Further, due to popularity and age, many benchmarks are prone to data leakage where example solutions can be readily found on the web and thus potentially in training data. Such limitations inevitably lead us to inquire: Is the leaderboard performance on existing benchmarks reliable and comprehensive enough to measure the program synthesis ability of LLMs? To address this, we introduce EvoEval -- a program synthesis benchmark suite created by evolving existing benchmarks into different targeted domains for a comprehensive evaluation of LLM coding abilities. Our study on 51 LLMs shows that compared to the high performance obtained on standard benchmarks like HumanEval, there is a significant drop in performance (on average 39.4%) when using EvoEval. Additionally, the decrease in performance can range from 19.6% to 47.7%, leading to drastic ranking changes amongst LLMs and showing potential overfitting of existing benchmarks. Furthermore, we showcase various insights, including the brittleness of instruction-following models when encountering rewording or subtle changes as well as the importance of learning problem composition and decomposition. EvoEval not only provides comprehensive benchmarks, but can be used to further evolve arbitrary problems to keep up with advances and the ever-changing landscape of LLMs for code. We have open-sourced our benchmarks, tools, and complete LLM generations at https://github.com/evo-eval/evoeval