相关论文: What Changed? Detecting and Evaluating Instruction…

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal understanding capabilities, yet they remain prone to object hallucination, where models describe non-existent objects or attribute incorrect factual information,…

Large vision-language models (LVLMs) have shown impressive performance across a broad range of multimodal tasks. However, robust image caption evaluation using LVLMs remains challenging, particularly under domain-shift scenarios. To address…

Natural Language Image Editing (NLIE) aims to use natural language instructions to edit images. Since novices are inexperienced with image editing techniques, their instructions are often ambiguous and contain high-level abstractions that…

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

While real-world applications increasingly demand intricate scene manipulation, existing instruction-guided image editing benchmarks often oversimplify task complexity and lack comprehensive, fine-grained instructions. To bridge this gap,…

Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…

Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by…

Text-based editing diffusion models exhibit limited performance when the user's input instruction is ambiguous. To solve this problem, we propose $\textit{Specify ANd Edit}$ (SANE), a zero-shot inference pipeline for diffusion-based editing…

Large-scale Vision-Language models have achieved remarkable results in various domains, such as image captioning and conditioned image generation. Nevertheless, these models still encounter difficulties in achieving human-like compositional…

Cross-modal retrieval relies on accurate models to retrieve relevant results for queries across modalities such as image, text, and video. In this paper, we build upon previous work by tackling the difficulty of evaluating models both…

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…

General Multimodal Large Language Models (MLLMs) often underperform in capturing domain-specific nuances in medical diagnosis, trailing behind fully supervised baselines. Although fine-tuning provides a remedy, the high costs of expert…

Large vision-language models (LVLMs) frequently suffer from Object Hallucination (OH), wherein they generate descriptions containing objects that are not actually present in the input image. This phenomenon is particularly problematic in…

Understanding visual differences between dynamic scenes requires the comparative perception of compositional, spatial, and temporal changes--a capability that remains underexplored in existing vision-language systems. While prior work on…

With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for ensuring the integrity of digital content. However, generalization remains a core challenge,…

Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning…

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…

Although psycholinguists and psychologists have long studied the tendency of linguistic strings to evoke mental images in hearers or readers, most computational studies have applied this concept of imageability only to isolated words. Using…

We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sentence, where the…

The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs). While LMMs have achieved tremendous success by promoting the synergy between multimodal comprehension and creation,…