It does not build a feature hierarchy.

With the emergence of large language models (LLMs), there is an expectation that LLMs can effectively extract explicit information from complex real-world documents (e.g., papers, reports). However, most LLMs generate paragraph-style answers that are chaotic, disorganized, and untraceable. To bridge this gap, we introduce the Arranged and Organized Extraction Benchmark (AOE), a new bilingual benchmark with data and documents of varying lengths designed to systematically evaluate the ability of LLMs to comprehend fragmented documents and reconstruct isolated information into one organized table. Unlike conventional text-to-table tasks, which rely on fixed schema and narrow task domains, AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries. In the experiment, we evaluated both open-source and closed-source state-of-the-art LLMs. The results show that even the most advanced models struggled significantly. The benchmark is available at https://anonymous.4open.science/r/AOE-Benchmark/.

DM-Count and investigate the robustness of different methods to noisy annotations. Assume for all x D and g G we have |g ( x) | B . We propose the following five lemmas which are essential for proving the proposed theorems. Lemmas A, B, C and D give the Lipschitz constants of different loss functions. Consider the dual form of Eq. (15) W ( µ, ν) = max α The first inequality in Eq. (20) is achieved because The second equality in Eq. (20) is achieved because We restate Theorem 1 in the main paper below.

Neural Information Processing Systems http://nips.cc/

Life expectancy is a fundamental indicator of population health and socio-economic well-being, yet accurately forecasting it remains challenging due to the interplay of demographic, environmental, and healthcare factors. Thi s study evaluates three machine learning models--Linear Regression (LR), Regression Decision Tree (RDT), and Random Forest (RF), using a real -world da-taset drawn from World Health Organization (WHO) and United N ations (UN) sources. After extensive preprocessing to address missing v alues and inconsistencies, each model's performance was assessed with R, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). Results show tha t RF achieves the highest predictive accuracy (R = 0.9423), significantly outperforming LR and RDT. Interpretability was prioritized through p -values for LR and feature - importance metrics for the tree -based models, revealing immunization rates (diphtheria, measles) and demographic attributes (HIV/AIDS, adult mortality) as critical drivers of life-expectancy predictions. These insights underscore the synergy between ensemble methods and transparency in addressing public -health challenges. Future research should explore advanced imputation strategies, alternative algorithms (e.g., neural networks), and updated data to further refine predictive accuracy and support evidence-based policymaking in global health contexts.

In the active learning paradigm, using an oracle to label data has always been a complex and expensive task, and with the emersion of large unlabeled data pools, it would be highly beneficial If we could achieve better results without relying on an oracle. This research introduces OFAL, an oracle-free active learning scheme that utilizes neural network uncertainty. OFAL uses the model's own uncertainty to transform highly confident unlabeled samples into informative uncertain samples. First, we start with separating and quantifying different parts of uncertainty and introduce Monte Carlo Dropouts as an approximation of the Bayesian Neural Network model. Secondly, by adding a variational autoencoder, we go on to generate new uncertain samples by stepping toward the uncertain part of latent space starting from a confidence seed sample. By generating these new informative samples, we can perform active learning and enhance the model's accuracy. Lastly, we try to compare and integrate our method with other widely used active learning sampling methods.

We consider the following classification problem: Given a population of individuals characterized by a set of attributes represented as a vector in ${\mathbb R}^N$, the goal is to find a hyperplane in ${\mathbb R}^N$ that separates two sets of points corresponding to two distinct classes. This problem, with a history dating back to the perceptron model, remains central to machine learning. In this paper we propose a novel approach by searching for a vector of parameters in a bounded $N$-dimensional hypercube centered at the origin and a positive vector in ${\mathbb R}^M$, obtained through the minimization of an entropy-based function defined over the space of unknown variables. The method extends to polynomial surfaces, allowing the separation of data points by more complex decision boundaries. This provides a robust alternative to traditional linear or quadratic optimization techniques, such as support vector machines and gradient descent. Numerical experiments demonstrate the efficiency and versatility of the method in handling diverse classification tasks, including linear and non-linear separability.

We present a deep learning approach for forecasting short-term employment changes and assessing long-term industry health using labor market data from the U.S. Bureau of Labor Statistics. Our system leverages a Long- and Short-Term Time-series Network (LSTNet) to process multivariate time series data, including employment levels, wages, turnover rates, and job openings. The model outputs both 7-day employment forecasts and an interpretable Industry Employment Health Index (IEHI). Our approach outperforms baseline models across most sectors, particularly in stable industries, and demonstrates strong alignment between IEHI rankings and actual employment volatility. We discuss error patterns, sector-specific performance, and future directions for improving interpretability and generalization.

The hardware ecosystem is rapidly evolving, with increasing interest in translating low-level programs across different instruction set architectures (ISAs) in a quick, flexible, and correct way to enhance the portability and longevity of existing code. A particularly challenging class of this transpilation problem is translating between complex- (CISC) and reduced- (RISC) hardware architectures, due to fundamental differences in instruction complexity, memory models, and execution paradigms. In this work, we introduce GG (Guaranteed Guess), an ISA-centric transpilation pipeline that combines the translation power of pre-trained large language models (LLMs) with the rigor of established software testing constructs. Our method generates candidate translations using an LLM from one ISA to another, and embeds such translations within a software-testing framework to build quantifiable confidence in the translation. We evaluate our GG approach over two diverse datasets, enforce high code coverage (>98%) across unit tests, and achieve functional/semantic correctness of 99% on HumanEval programs and 49% on BringupBench programs, respectively. Further, we compare our approach to the state-of-the-art Rosetta 2 framework on Apple Silicon, showcasing 1.73x faster runtime performance, 1.47x better energy efficiency, and 2.41x better memory usage for our transpiled code, demonstrating the effectiveness of GG for real-world CISC-to-RISC translation tasks. We will open-source our codes, data, models, and benchmarks to establish a common foundation for ISA-level code translation research.