Related papers: Uncovering Entity Identity Confusion in Multimodal…

Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing…

Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However,…

Composed Image Retrieval (CIR) is an important image retrieval paradigm that enables users to retrieve a target image using a multimodal query that consists of a reference image and modification text. Although research on CIR has made…

Hallucinations in large language models are a widespread problem, yet the mechanisms behind whether models will hallucinate are poorly understood, limiting our ability to solve this problem. Using sparse autoencoders as an interpretability…

Event coreference resolution (ECR) is the task of determining whether distinct mentions of events within a multi-document corpus are actually linked to the same underlying occurrence. Images of the events can help facilitate resolution when…

Knowledge Editing (KE) has emerged as a promising paradigm for updating facts in Large Language Models (LLMs) without retraining. However, progress in Multilingual Knowledge Editing (MKE) is currently hindered by biased evaluation…

Multi-modal stance detection (MSD) aims to determine an author's stance toward a given target using both textual and visual content. While recent methods leverage multi-modal fusion and prompt-based learning, most fail to distinguish…

Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidious and destructive safety risks, namely deception. Unlike…

This paper considers the problem of knowledge inference on large-scale imperfect repositories with incomplete coverage by means of embedding entities and relations at the first attempt. We propose IIKE (Imperfect and Incomplete Knowledge…

Efficient knowledge editing of large language models is crucial for replacing obsolete information or incorporating specialized knowledge on a large scale. However, previous methods implicitly assume that knowledge is localized and isolated…

Whole-body biometric recognition is a challenging multimodal task that integrates various biometric modalities, including face, gait, and body. This integration is essential for overcoming the limitations of unimodal systems. Traditionally,…

Knowledge Graph Embeddings (KGEs) support a wide range of downstream tasks over Knowledge Graphs (KGs). In practice, KGs evolve as new entities and facts are added, motivating Continual Knowledge Graph Embedding (CKGE) methods that update…

Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most existing methods overfit to specific models, causing edited…

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

Emotion recognition based on Electroencephalography (EEG) has gained significant attention and diversified development in fields such as neural signal processing and affective computing. However, the unique brain anatomy of individuals…

The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images. The inherent heterogeneity…

Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. While model editing methods have been developed to address such errors without full re-training, they…

Many machine learning models have been built to tackle information overload issues on Massive Open Online Courses (MOOC) platforms. These models rely on learning powerful representations of MOOC entities. However, they suffer from the…

Large language models (LLMs) are increasingly used as knowledge bases, but keeping them up to date requires targeted knowledge editing (KE). However, it remains unclear how edits are implemented inside the model once applied. In this work,…

Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often…