Understanding and reasoning over text within visual contexts poses a significant challenge for Vision-Language Models (VLMs), given the complexity and diversity of real-world scenarios. To address this challenge, text-rich Visual Question Answering (VQA) datasets and benchmarks have emerged for high-resource languages like English. However, a critical gap persists for low-resource languages such as Korean, where the lack of comprehensive benchmarks hinders robust model evaluation and comparison. To bridge this gap, we introduce KRETA, a benchmark for Korean Reading and rEasoning in Text-rich VQA Attuned to diverse visual contexts. KRETA facilitates an in-depth evaluation of both visual text understanding and reasoning capabilities, while also supporting a multifaceted assessment across 15 domains and 26 image types. Additionally, we introduce a semi-automated VQA generation pipeline specifically optimized for text-rich settings, leveraging refined stepwise image decomposition and a rigorous seven-metric evaluation protocol to ensure data quality. While KRETA is tailored for Korean, we hope our adaptable and extensible pipeline will facilitate the development of similar benchmarks in other languages, thereby accelerating multilingual VLM research. The code and dataset for KRETA are available at https://github.com/tabtoyou/KRETA.

In Large Language Models (LLMs) generation, there exist knowledge conflicts and scenarios where parametric knowledge contradicts knowledge provided in the context. Previous works studied tuning, decoding algorithms, or locating and editing context-aware neurons to adapt LLMs to be faithful to new contextual knowledge. However, they are usually inefficient or ineffective for large models, not workable for black-box models, or unable to continuously adjust LLMs' sensitivity to the knowledge provided in the context. To mitigate these problems, we propose CSKS (Continuously Steering Knowledge Sensitivity), a simple framework that can steer LLMs' sensitivity to contextual knowledge continuously at a lightweight cost. Specifically, we tune two small LMs (i.e. proxy models) and use the difference in their output distributions to shift the original distribution of an LLM without modifying the LLM weights. In the evaluation process, we not only design synthetic data and fine-grained metrics to measure models' sensitivity to contextual knowledge but also use a real conflict dataset to validate CSKS's practical efficacy. Extensive experiments demonstrate that our framework achieves continuous and precise control over LLMs' sensitivity to contextual knowledge, enabling both increased sensitivity and reduced sensitivity, thereby allowing LLMs to prioritize either contextual or parametric knowledge as needed flexibly. Our data and code are available at https://github.com/OliveJuiceLin/CSKS.

Preparing high-quality instructional materials remains a labor-intensive process that often requires extensive coordination among teaching faculty, instructional designers, and teaching assistants. In this work, we present Instructional Agents, a multi-agent large language model (LLM) framework designed to automate end-to-end course material generation, including syllabus creation, lecture scripts, LaTeX-based slides, and assessments. Unlike existing AI-assisted educational tools that focus on isolated tasks, Instructional Agents simulates role-based collaboration among educational agents to produce cohesive and pedagogically aligned content. The system operates in four modes: Autonomous, Catalog-Guided, Feedback-Guided, and Full Co-Pilot mode, enabling flexible control over the degree of human involvement. We evaluate Instructional Agents across five university-level computer science courses and show that it produces high-quality instructional materials while significantly reducing development time and human workload. By supporting institutions with limited instructional design capacity, Instructional Agents provides a scalable and cost-effective framework to democratize access to high-quality education, particularly in underserved or resource-constrained settings.

Large language models (LLMs) have revolutionized AI applications, yet their enormous computational demands severely limit deployment and real-time performance. Quantization methods can help reduce computational costs, however, attaining the extreme efficiency associated with ultra-low-bit quantized LLMs at arbitrary precision presents challenges on GPUs. This is primarily due to the limited support for GPU Tensor Cores, inefficient memory management, and inflexible kernel optimizations. To tackle these challenges, we propose a comprehensive acceleration scheme for arbitrary precision LLMs, namely APT-LLM. Firstly, we introduce a novel data format, bipolar-INT, which allows for efficient and lossless conversion with signed INT, while also being more conducive to parallel computation. We also develop a matrix multiplication (MatMul) method allowing for arbitrary precision by dismantling and reassembling matrices at the bit level. This method provides flexible precision and optimizes the utilization of GPU Tensor Cores. In addition, we propose a memory management system focused on data recovery, which strategically employs fast shared memory to substantially increase kernel execution speed and reduce memory access latency. Finally, we develop a kernel mapping method that dynamically selects the optimal configurable hyperparameters of kernels for varying matrix sizes, enabling optimal performance across different LLM architectures and precision settings. In LLM inference, APT-LLM achieves up to a 3.99$\times$ speedup compared to FP16 baselines and a 2.16$\times$ speedup over NVIDIA CUTLASS INT4 acceleration on RTX 3090. On RTX 4090 and H800, APT-LLM achieves up to 2.44$\times$ speedup over FP16 and 1.65$\times$ speedup over CUTLASS integer baselines.

This study evaluates deep neural networks for forecasting probability distributions of financial returns. 1D convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) architectures are used to forecast parameters of three probability distributions: Normal, Student's t, and skewed Student's t. Using custom negative log-likelihood loss functions, distribution parameters are optimized directly. The models are tested on six major equity indices (S\&P 500, BOVESPA, DAX, WIG, Nikkei 225, and KOSPI) using probabilistic evaluation metrics including Log Predictive Score (LPS), Continuous Ranked Probability Score (CRPS), and Probability Integral Transform (PIT). Results show that deep learning models provide accurate distributional forecasts and perform competitively with classical GARCH models for Value-at-Risk estimation. The LSTM with skewed Student's t distribution performs best across multiple evaluation criteria, capturing both heavy tails and asymmetry in financial returns. This work shows that deep neural networks are viable alternatives to traditional econometric models for financial risk assessment and portfolio management.

Sepsis is a life threatening condition that requires timely detection in intensive care settings. Traditional machine learning approaches, including Naive Bayes, Support Vector Machine (SVM), Random Forest, and XGBoost, often rely on manual feature engineering and struggle with irregular, incomplete time-series data commonly present in electronic health records. We introduce an end-to-end deep learning framework integrating an unsupervised autoencoder for automatic feature extraction with a multilayer perceptron classifier for binary sepsis risk prediction. To enhance clinical applicability, we implement a customized down sampling strategy that extracts high information density segments during training and a non-overlapping dynamic sliding window mechanism for real-time inference. Preprocessed time series data are represented as fixed dimension vectors with explicit missingness indicators, mitigating bias and noise. We validate our approach on three ICU cohorts. Our end-to-end model achieves accuracies of 74.6 percent, 80.6 percent, and 93.5 percent, respectively, consistently outperforming traditional machine learning baselines. These results demonstrate the framework's superior robustness, generalizability, and clinical utility for early sepsis detection across heterogeneous ICU environments.

Drug discovery is a complex and resource-intensive process, making early prediction of approval outcomes critical for optimizing research investments. While classical machine learning and deep learning methods have shown promise in drug approval prediction, their limited interpretability constraints their impact. Here, we present DrugReasoner, a reasoning-based large language model (LLM) built on the LLaMA architecture and fine-tuned with group relative policy optimization (GRPO) to predict the likelihood of small-molecule approval. DrugReasoner integrates molecular descriptors with comparative reasoning against structurally similar approved and unapproved compounds, generating predictions alongside step-by-step rationales and confidence scores. DrugReasoner achieved robust performance with an AUC of 0.732 and an F1 score of 0.729 on the validation set and 0.725 and 0.718 on the test set, respectively. These results outperformed conventional baselines, including logistic regression, support vector machine, and k-nearest neighbors and had competitive performance relative to XGBoost. On an external independent dataset, DrugReasoner outperformed both baseline and the recently developed ChemAP model, achieving an AUC of 0.728 and an F1-score of 0.774, while maintaining high precision and balanced sensitivity, demonstrating robustness in real-world scenarios. These findings demonstrate that DrugReasoner not only delivers competitive predictive accuracy but also enhances transparency through its reasoning outputs, thereby addressing a key bottleneck in AI-assisted drug discovery. This study highlights the potential of reasoning-augmented LLMs as interpretable and effective tools for pharmaceutical decision-making.

Data-driven approaches have emerged as a powerful alternative to traditional numerical methods for forecasting physical systems, offering fast inference and reduced computational costs. However, for complex systems and those without prior knowledge, the accuracy of long-term predictions frequently deteriorates due to error accumulation. Existing solutions often adopt an autoregressive approach that unrolls multiple time steps during each training iteration; although effective for long-term forecasting, this method requires storing entire unrolling sequences in GPU memory, leading to high resource demands. Moreover, optimizing for long-term accuracy in autoregressive frameworks can compromise short-term performance. To address these challenges, we introduce the Stochastic PushForward (SPF) training framework in this paper. SPF preserves the one-step-ahead training paradigm while still enabling multi-step-ahead learning. It dynamically constructs a supplementary dataset from the model's predictions and uses this dataset in combination with the original training data. By drawing inputs from both the ground truth and model-generated predictions through a stochastic acquisition strategy, SPF naturally balances short-and long-term predictive performance and further reduces overfitting and improves generalization. Furthermore, the training process is executed in a one-step-ahead manner, with multi-step-ahead predictions precomputed between epochs--thus eliminating the need to retain entire unrolling sequences in memory, thus keeping memory usage stable. We demonstrate the effectiveness of SPF on the Burgers' equation and the Shallow Water benchmark. Experimental results demonstrated that SPF delivers superior long-term accuracy compared to autoregressive approaches while reducing memory consumption. Supplementary dataset update interval Test cases V Flow speed for Burgers' equation h Total water depth including the undisturbed water depth u, v Velocity components in the x (horizontal) and y (vertical) directions g Gravitational acceleration r Spatial euclidean distance ϵ Balgovind type of correlation function L Typical correlation length scale 2 1. Introduction Over many years, scientific research has produced highly detailed mathematical models of physical phenomena[1]. These models are frequently and naturally expressed in the form of differential equations [2], most commonly as time-dependent Partial differential equation (PDE)s.

This article presents a practitioner's reflection on applying declarative, 5th generation, problem formulation language (5GL) to de novo imaging system design, informed by experiences across the interdisciplinary research in academia and cross-functional product development within the private sector. Using the 96-Eyes project: 96-camera parallel multi-modal imager for high-throughput drug discovery as a representative case, I illustrate how project requirements, ranging from hardware constraints to life sciences needs, can be formalized into machine-readable problem statements to preserve mission-critical input from diverse domain stakeholders. This declarative approach enhances transparency, ensures design traceability, and minimizes costly misalignment across optical, algorithmic, hardware-accelerated compute, and life sciences teams. Alongside the technical discussion of 5GL with real-world code examples, I reflect on the practical barriers to adopting 5GL in environments where imperative, 3rd-generation languages (3GL) remain the default medium for inter-team collaboration. Rather than offering an one-size-fits-all solution, these learned lessons highlight how programming paradigms implicitly shapes research workflows through existing domain hierarchies. The discussion aims to invite further explorations into how declarative problem formulations can facilitate innovation in settings where concurrent R\&{}D workflows are gaining traction, as opposed to environments where sequential, phase-driven workflows remain the norm.

Suicide is one of the leading causes of death among adolescents. Previous suicide risk prediction studies have primarily focused on either textual or acoustic information in isolation, the integration of multimodal signals, such as speech and text, offers a more comprehensive understanding of an individual's mental state. Motivated by this, and in the context of the 1st SpeechWellness detection challenge, we explore a lightweight multi-branch multimodal system based on a dynamic fusion mechanism for speechwellness detection. To address the limitation of prior approaches that rely on time-domain waveforms for acoustic analysis, our system incorporates both time-domain and time-frequency (TF) domain acoustic features, as well as semantic representations. In addition, we introduce a dynamic fusion block to adaptively integrate information from different modalities. Specifically, it applies learnable weights to each modality during the fusion process, enabling the model to adjust the contribution of each modality. To enhance computational efficiency, we design a lightweight structure by simplifying the original baseline model. Experimental results demonstrate that the proposed system exhibits superior performance compared to the challenge baseline, achieving a 78% reduction in model parameters and a 5% improvement in accuracy.