相关论文: MULTITEXTEDIT: Benchmarking Cross-Lingual Degradat…

Vision-language models (VLMs) exhibit affirmation bias: a systematic tendency to select positive captions ("X is present") even when the correct description contains negation ("no X"). While prior work has documented this failure mode in…

Typographic attacks exploit the interplay between text and visual content in multimodal foundation models, causing misclassifications when misleading text is embedded within images. Existing datasets are limited in size and diversity,…

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual…

Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient high-quality labeled data…

Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision-language models (LVLMs). Despite their growing importance, these evaluators are almost exclusively assessed on English-centric…

Recent trends in NLP research have raised an interest in linguistic code-switching (CS); modern approaches have been proposed to solve a wide range of NLP tasks on multiple language pairs. Unfortunately, these proposed methods are hardly…

Comprehending text-rich visual content is paramount for the practical application of Multimodal Large Language Models (MLLMs), since text-rich scenarios are ubiquitous in the real world, which are characterized by the presence of extensive…

Large Language Models are essential coding assistants, yet their training is predominantly English-centric. In this study, we evaluate the performance of code language models in non-English contexts, identifying challenges in their adoption…

Existing tampering detection benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are untouched or only trivially modified, while subtle yet consequential edits outside the…

Ensuring that deep learning models are well-calibrated in terms of their predictive uncertainty is essential in maintaining their trustworthiness and reliability, yet despite increasing advances in foundation model research, the…

With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus…

Recent advances in multimodal large language models (MLLMs) have significantly improved medical AI, enabling it to unify the understanding of visual and textual information. However, as medical knowledge continues to evolve, it is critical…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

The generative capabilities of Large Language Models (LLMs) are rapidly expanding from static code to dynamic, interactive visual artifacts. This progress is bottlenecked by a critical evaluation gap: established benchmarks focus on…

Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. We propose a multilingual text detection model to address the issues of…

Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes, where people and landmarks originate from different cultures, remains largely…

Instruction-following benchmarks remain predominantly English-centric, leaving a critical evaluation gap for the hundreds of millions of Indic language speakers. We introduce IndicIFEval, a benchmark evaluating constrained generation of…

Open-source, multilingual medical large language models (LLMs) have the potential to serve linguistically diverse populations across different regions. Adapting generic LLMs for healthcare often requires continual pretraining, but this…

Existing fairness benchmarks for large language models (LLMs) primarily focus on simple tasks, such as multiple-choice questions, overlooking biases that may arise in more complex scenarios like long-text generation. To address this gap, we…

Pretrained language models are promising particularly for low-resource languages as they only require unlabelled data. However, training existing models requires huge amounts of compute, while pretrained cross-lingual models often…