Related papers: $\mathbf{S^2LM}$: Towards Semantic Steganography v…

Understanding human instructions to identify the target objects is vital for perception systems. In recent years, the advancements of Large Language Models (LLMs) have introduced new possibilities for image segmentation. In this work, we…

Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprisingly, we show that…

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…

Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing…

AI-powered malware increasingly exploits cloud-hosted generative-AI services and large language models (LLMs) as analysis engines for reconnaissance and code generation. Simultaneously, enterprise uploads expose sensitive documents to…

Recent advances on text-to-image generation have witnessed the rise of diffusion models which act as powerful generative models. Nevertheless, it is not trivial to exploit such latent variable models to capture the dependency among discrete…

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the…

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task.…

Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art…

Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains. However, their application to remote sensing (RS) remains underexplored due to significant domain…

This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks. It is capable of learning…

Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…

With the widespread applications of the deep neural network (DNN), how to covertly transmit the DNN models in public channels brings us the attention, especially for those trained for secret-learning tasks. In this paper, we propose deep…

Semantic communication has recently attracted significant interest from both industry and academia due to its potential to transform the existing data-focused communication architecture towards a more generally intelligent and goal-oriented…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present…

Sentence embeddings are crucial in measuring semantic similarity. Most recent studies employed large language models (LLMs) to learn sentence embeddings. Existing LLMs mainly adopted autoregressive architecture without explicit backward…

In this paper, an effective method was introduced to steganography of text document in the host image. In the available steganography methods, the message has a random form. Therefore, the embedding capacity is generally low. In the…

All the existing image steganography methods use manually crafted features to hide binary payloads into cover images. This leads to small payload capacity and image distortion. Here we propose a convolutional neural network based…

This paper introduces SignAgent, a novel agentic framework that utilises Large Language Models (LLMs) for scalable, linguistically-grounded Sign Language (SL) annotation and dataset curation. Traditional computational methods for SLs often…