Related papers: FailureMem: A Failure-Aware Multimodal Framework f…

Ensuring the safety, quality, and timely completion of construction projects is paramount, with construction inspections serving as a vital instrument towards these goals. Nevertheless, the predominantly manual approach of present-day…

Automatic program repair holds the potential of dramatically improving the productivity of programmers during the software development process and correctness of software in general. Recent advances in machine learning, deep learning, and…

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale…

Large Language Models (LLMs) often produce code with subtle implementation-level bugs despite strong benchmark performance. These errors are hard for LLMs to spot and can have large behavioural effects; yet when asked to summarise code,…

With the rapid development of cloud computing systems and the increasing complexity of their infrastructure, intelligent mechanisms to detect and mitigate failures in real time are becoming increasingly important. Traditional methods of…

Existing instruction-based image editing models perform well with simple, single-step instructions but degrade in realistic scenarios that involve multiple, lengthy, and interdependent directives. A main cause is the scarcity of training…

Recent advancements in medical Large Language Models (LLMs) have showcased their powerful reasoning and diagnostic capabilities. Despite their success, current unified multimodal medical LLMs face limitations in knowledge update costs,…

In cable driven parallel robots (CDPRs), a single cable malfunction usually induces complete failure of the entire robot. However, the lost static workspace (due to failure) can often be recovered through reconfiguration of the cable…

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture…

Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a key paradigm for grounding MLLMs with external knowledge. While query pre-processing (e.g., rewriting) is standard in text-based RAG, existing MRAG pipelines predominantly…

Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps across models. To address this, we introduce AuditDM, an automated framework that…

Security vulnerability repair is a difficult task that is in dire need of automation. Two groups of techniques have shown promise: (1) large code language models (LLMs) that have been pre-trained on source code for tasks such as code…

AI inference at the edge is becoming increasingly common for low-latency services. However, edge environments are power- and resource-constrained, and susceptible to failures. Conventional failure resilience approaches, such as cloud…

Automatic Program Repair (APR) is a core technology in software development and maintenance, with aims to enable automated defect repair with minimal human intervention. In recent years, the substantial advancements in Large Language Models…

Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to support various network applications. However, real-world graphs are often isolated due to…

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…

This study explores the potential of Large Language Models (LLMs) in automating the repair of C programs. We present a framework that integrates spectrum-based fault localization (SBFL), runtime feedback, and Chain-of-Thought-structured…

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance…

Humans build viewpoint-independent cognitive maps through navigation, enabling intuitive reasoning about object permanence and spatial relations. We argue that multimodal large language models (MLLMs), despite extensive video training, lack…