相关论文: Towards Unified Multimodal Editing with Enhanced K…

Real-world multimodal knowledge graphs (MKGs) are inherently heterogeneous, modeling entities that are associated with diverse modalities. Traditional knowledge graph embedding (KGE) methods excel at learning continuous representations of…

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…

Large Language Models (LLMs) excel in various natural language processing tasks, but leveraging them for dense passage embedding remains challenging. This is due to their causal attention mechanism and the misalignment between their…

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs…

Current Large Language Models (LLMs) face inherent limitations due to their pre-defined context lengths, which impede their capacity for multi-hop reasoning within extensive textual contexts. While existing techniques like…

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on simple link structure between a finite set of entities, ignoring…

Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often struggle to capture…

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…

Model editing aims to efficiently update a pre-trained model's knowledge without the need for time-consuming full retraining. While existing pioneering editing methods achieve promising results, they primarily focus on editing single-modal…

Recent works have attempted to integrate external knowledge into LLMs to address the limitations and potential factual errors in LLM-generated content. However, how to retrieve the correct knowledge from the large amount of external…

Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I), whether instantiated as assembled unified frameworks which couple powerful vision-language model (VLM) with…

Current instruction-based editing methods, such as InstructPix2Pix, often fail to produce satisfactory results in complex scenarios due to their dependence on the simple CLIP text encoder in diffusion models. To rectify this, this paper…

Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues by retrieving related knowledge from knowledge graphs or…

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenarios where edits must…

In this paper, we propose \textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This…

Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is…

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs)…

We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual embeddings via learnable query tokens, which subsequently…

Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. A key challenge is to keep these models updated with latest available information, which limits the true potential of these models…