相关论文: SAVE: Sparse Autoencoder-Driven Visual Information…

Large Vision-Language Models (LVLMs) excel in diverse cross-modal tasks. However, object hallucination, where models produce plausible but inaccurate object descriptions, remains a significant challenge. In contrast to previous work…

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper…

Despite the significant advancements in Large Vision-Language Models (LVLMs), their tendency to generate hallucinations undermines reliability and restricts broader practical deployment. Among the hallucination mitigation methods, feature…

Most research on hallucinations in Large Vision-Language Models (LVLMs) focuses on factual description tasks that prohibit any output absent from the image. However, little attention has been paid to hallucinations in voluntary imagination…

Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images. While current benchmarks for object hallucination primarily concentrate on the presence of a single object class…

Spatial relation hallucinations pose a persistent challenge in large vision-language models (LVLMs), leading to generate incorrect predictions about object positions and spatial configurations within an image. To address this issue, we…

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable…

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…

Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to…

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-text data into vectors, but current encoders either lack…

Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the…

Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning. Such a success of contrastive learning relies on two conditions, a sufficient number of positive pairs and adequate…

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…

Large vision-language models (LVLMs) have demonstrated remarkable multimodal comprehension and reasoning capabilities, but they still suffer from severe object hallucination. Previous studies primarily attribute the flaw to linguistic prior…

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…

Object hallucination in Large Vision-Language Models (LVLMs) significantly hinders their reliable deployment. Existing methods struggle to balance efficiency and accuracy: they often require expensive reference models and multiple forward…

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient…

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…