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

Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibiting strong instantaneous learning and generalization…

In the era of Large Language Models (LLMs), tremendous strides have been made in the field of multimodal understanding. However, existing advanced algorithms are limited to effectively utilizing the immense representation capabilities and…

In this paper, we introduce ILLUME, a unified multimodal large language model (MLLM) that seamlessly integrates multimodal understanding and generation capabilities within a single large language model through a unified next-token…

Knowledge editing emerges as a crucial technique for efficiently correcting incorrect or outdated knowledge in large language models (LLM). Existing editing methods rely on a rigid mapping from parameter or module modifications to output,…

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language…

Knowledge editing (KE) enables precise modifications to factual content in large language models (LLMs). Existing KE methods are largely designed for dense architectures, limiting their applicability to the increasingly prevalent sparse…

Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the…

Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora. Consequently, ensuring the reliability and malleability of these internal…

Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability…

Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.…

Large language models (LLMs) excel at factual recall yet still propagate stale or incorrect knowledge. In-context knowledge editing offers a gradient-free remedy suitable for black-box APIs, but current editors rely on static demonstration…

Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal tasks, but their performance is often constrained by the lack of external knowledge integration, limiting their ability to handle…

Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by relying on low-similarity or random inputs, obscure overfitting.…

In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating outputs in any interleaved multimedia form. This capability defines the goal…

Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challenges in real-world queries and targets involving diverse modality combinations, as existing…

With the rapid increase of multimedia data, a large body of literature has emerged to work on multimodal summarization, the majority of which target at refining salient information from textual and visual modalities to output a pictorial…

Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new facts into Large Language Models (LLMs). Two mainstream ME methods exist: parameter-modifying ME and parameter-preserving ME (integrating extra…

Multimodal entity linking plays a crucial role in a wide range of applications. Recent advances in large language model-based methods have become the dominant paradigm for this task, effectively leveraging both textual and visual modalities…

Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all knowledge of a specific entity while preserving the model's…

Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world developments, which hinders continuous knowledge acquisition.…