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

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…

Fine-tuning Large Language Models (LLMs) with multimodal encoders on modality-specific data expands the modalities that LLMs can handle, leading to the formation of Multimodal LLMs (MLLMs). However, this paradigm heavily relies on…

The automated repair of C++ compilation errors presents a significant challenge, the resolution of which is critical for developer productivity. Progress in this domain is constrained by two primary factors: the scarcity of large-scale,…

Students often make mistakes on their introductory programming assignments as part of their learning process. Unfortunately, providing custom repairs for these mistakes can require a substantial amount of time and effort from class…

Real-world License Plate Recognition (LPR) faces significant challenges from severe degradations such as motion blur, low resolution, and complex illumination. The prevailing "restoration-then-recognition" two-stage paradigm suffers from a…

Large Language Models (LLMs) have shown high capabilities in several software development-related tasks such as program repair, documentation, code refactoring, debugging, and testing. However, training these models requires massive amount…

Software vulnerabilities continue to be ubiquitous, even in the era of AI-powered code assistants, advanced static analysis tools, and the adoption of extensive testing frameworks. It has become apparent that we must not simply prevent…

The advances of deep learning (DL) have paved the way for automatic software vulnerability repair approaches, which effectively learn the mapping from the vulnerable code to the fixed code. Nevertheless, existing DL-based vulnerability…

Robotic systems often face execution failures due to unexpected obstacles, sensor errors, or environmental changes. Traditional failure recovery methods rely on predefined strategies or human intervention, making them less adaptable. This…

Software vulnerability management has become increasingly critical as modern systems scale in size and complexity. However, existing automated approaches remain insufficient. Traditional static analysis methods struggle to precisely capture…

Large Language Models (LLMs) have revolutionized automated program repair (APR) but current benchmarks like SWE-Bench predominantly focus on userspace applications and overlook the complexities of kernel-space debugging and repair. The…

In text-to-image person retrieval tasks, the diversity of natural language expressions and the implicitness of visual semantics often lead to the problem of Expression Drift, where semantically equivalent texts exhibit significant feature…

Learning-based automated vulnerability repair (AVR) techniques that utilize fine-tuned language models have shown promise in generating vulnerability patches. However, questions remain about their ability to repair unseen vulnerabilities.…

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations--cases where…

Textual descriptions for multimodal inputs entail recurrent refinement of queries to produce relevant output images. Despite efforts to address challenges such as scaling model size and data volume, the cost associated with pre-training and…

Recognizing failures during task execution and implementing recovery procedures is challenging in robotics. Traditional approaches rely on the availability of extensive data or a tight set of constraints, while more recent approaches…

We report a flexible multi-modal mechanics language model, MeLM, applied to solve various nonlinear forward and inverse problems, that can deal with a set of instructions, numbers and microstructure data. The framework is applied to various…

Property graphs are widely used in domains such as healthcare, finance, and social networks, but they often contain errors due to inconsistencies, missing data, or schema violations. Traditional rule-based and heuristic-driven graph repair…

Multimodal emotion recognition utilizes complete multimodal information and robust multimodal joint representation to gain high performance. However, the ideal condition of full modality integrity is often not applicable in reality and…

Implementing new features across an entire codebase presents a formidable challenge for Large Language Models (LLMs). This proactive task requires a deep understanding of the global system architecture to prevent unintended disruptions to…