相关论文: Human-like Content Analysis for Generative AI with…

Following the universal availability of generative AI systems with the release of ChatGPT, automatic detection of deceptive text created by Large Language Models has focused on domains such as academic plagiarism and "fake news". However,…

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word…

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

Generating longer textual sequences when conditioned on the visual information is an interesting problem to explore. The challenge here proliferate over the standard vision conditioned sentence-level generation (e.g., image or video…

Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low…

Generative Adversarial Networks (GANs) play an increasingly important role in machine learning. However, there is one fundamental issue hindering their practical applications: the absence of capability for encoding real-world samples. The…

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development…

AI-generated content is becoming increasingly prevalent in the real world, leading to serious ethical and societal concerns. For instance, adversaries might exploit large multimodal models (LMMs) to create images that violate ethical or…

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations…

This paper proposes a novel latent semantic learning method for extracting high-level features (i.e. latent semantics) from a large vocabulary of abundant mid-level features (i.e. visual keywords) with structured sparse representation,…

Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize high-quality content at a large scale brings potential risks…

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a sparse autoencoder on text embeddings to…

Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results…

The rapid development of generative artificial intelligence (AI) has introduced significant opportunities for enhancing the efficiency and accuracy of image transmission within semantic communication systems. Despite these advancements,…

Artificial Intelligence Generated Content (AIGC) is leading a new technical revolution for the acquisition of digital content and impelling the progress of visual compression towards competitive performance gains and diverse functionalities…

Does Large Language Model (LLM) technology suggest a meta-semantic picture i.e. a picture of how words and complex expressions come to have the meaning that they do? One modest approach explores the assumptions that seem to be built into…