Related papers: Seeing is Fixing: Cross-Modal Reasoning with Multi…

Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations are truly aligned across modalities. To investigate this…

We introduce VisualQuest, a novel dataset designed to rigorously evaluate multimodal large language models (MLLMs) on abstract visual reasoning tasks that require the integration of symbolic, cultural, and linguistic knowledge. Unlike…

Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing MLLMs necessitates high-quality vision-language datasets with carefully curated task complexities,…

Large language models (LLMs) show promise in medical diagnosis, but real-world deployment remains challenging due to high-stakes clinical decisions and imperfect reasoning reliability. As a result, careful inspection of model behavior is…

Large Language Models (LLMs) have emerged as promising tools in software development, enabling automated code generation and analysis. However, their knowledge is limited to a fixed cutoff date, making them prone to generating code…

Existing Multimodal Large Language Models (MLLMs) are predominantly trained and tested on consistent visual-textual inputs, leaving open the question of whether they can handle inconsistencies in real-world, layout-rich content. To bridge…

Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

High-quality textual training data is essential for the success of multimodal data processing tasks, yet outputs from image captioning models like BLIP and GIT often contain errors and anomalies that are difficult to rectify using…

Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on…

Automated generation of feedback on programming assignments holds significant benefits for programming education, especially when it comes to advanced assignments. Automated Program Repair techniques, especially Large Language Model based…

Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly…

Geometric Problem Solving (GPS) poses a unique challenge for Multimodal Large Language Models (MLLMs), requiring not only the joint interpretation of text and diagrams but also iterative visuospatial reasoning. While existing approaches…

Automatic program repair (APR) is crucial to improve software reliability. Recently, neural machine translation (NMT) techniques have been used to fix software bugs automatically. While promising, these approaches have two major…

Humans possess multimodal literacy, allowing them to actively integrate information from various modalities to form reasoning. Faced with challenges like lexical ambiguity in text, we supplement this with other modalities, such as thumbnail…

Current learning-based Automated Vulnerability Repair (AVR) approaches, while promising, often fail to generalize effectively in real-world scenarios. Our diagnostic analysis reveals three fundamental weaknesses in state-of-the-art AVR…

In the context of Synthetic Aperture Radar (SAR) image recognition, traditional methods often struggle with the intrinsic limitations of SAR data, such as weak texture, high noise, and ambiguous object boundaries. This work explores a novel…

With the rapid development of web technology, more and more software applications have become web-based in the past decades. To ensure software quality and user experience, various techniques have been proposed to automatically test web…

With the rapid advancement of Large Language Models (LLMs), traditional Automated Program Repair (APR) techniques have undergone significant transformation. Training-free approaches, such as zero-shot and few-shot prompting, are…

Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple…