Related papers: GALA: Multimodal Graph Alignment for Bug Localizat…

Multimodal Attributed Graph Learning (MAGL) integrates intrinsic node attributes with structural topology via graph aggregation. However, as pretrained encoders evolve into Large Foundation Models (LFMs), the landscape of MAGL fundamentally…

The rapid pace of large-scale software development places increasing demands on traditional testing methodologies, often leading to bottlenecks in efficiency, accuracy, and coverage. We propose a novel perspective on software testing by…

The gap between the trepidation of program reliability and the expense of repairs underscores the indispensability of Automated Program Repair (APR). APR is instrumental in transforming vulnerable programs into more robust ones, bolstering…

We introduce Groma, a Multimodal Large Language Model (MLLM) with grounded and fine-grained visual perception ability. Beyond holistic image understanding, Groma is adept at region-level tasks such as region captioning and visual grounding.…

Highly automated driving functions currently often rely on a-priori knowledge from maps for planning and prediction in complex scenarios like cities. This makes map-relative localization an essential skill. In this paper, we address the…

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to image-level anomaly detection and textual reasoning, while…

Recent advancements in retrieval-augmented generation (RAG) have enhanced large language models in question answering by integrating external knowledge. However, challenges persist in achieving global understanding and aligning responses…

Given the remarkable success that large visual language models (LVLMs) have achieved in image perception tasks, the endeavor to make LVLMs perceive the world like humans is drawing increasing attention. Current multi-modal benchmarks…

Vision-language models (VLMs) such as CLIP demonstrate strong generalization in zero-shot classification but remain highly vulnerable to adversarial perturbations. Existing methods primarily focus on adversarial fine-tuning or prompt…

Retrieval-augmented generation (RAG) has shown impressive capability in providing reliable answer predictions and addressing hallucination problems. A typical RAG implementation uses powerful retrieval models to extract external information…

Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools or image generators. However, existing methods usually follow an output-as-input latent…

Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most research focuses on improving single-task performance, practical scenarios often involve…

Retrieval-Augmented Generation (RAG) has emerged as the dominant paradigm for grounding large language model outputs in verifiable evidence. However, as modern AI agents transition from static knowledge bases to continuous multimodal…

LLM-integrated software, which embeds or interacts with large language models (LLMs) as functional components, exhibits probabilistic and context-dependent behaviors that fundamentally differ from those of traditional software. This shift…

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as…

Large Language Models are increasingly used in robotics for task planning, but their reliance on textual inputs limits their adaptability to real-world changes and failures. To address these challenges, we propose LERa - Look, Explain,…

Large language models (LLMs) have been proposed as powerful tools for detecting software vulnerabilities, where task-specific fine-tuning is typically employed to provide vulnerability-specific knowledge to the LLMs. However, existing…

Text-image alignment constitutes a foundational challenge in multimedia content understanding, where effective modeling of cross-modal semantic correspondences critically enhances retrieval system performance through joint embedding space…

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

Domain adaptation remains a challenge when there is significant manifold discrepancy between source and target domains. Although recent methods leverage manifold-aware adversarial perturbations to perform data augmentation, they often…