Related papers: REED: Post-Training Representation Editing for Cro…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

We study whether in-domain pretraining of Bidirectional Encoder Representations from Transformer (BERT) model improves subdomain-level detection of exfiltration at low false positive rates. While previous work mostly examines fine-tuned…

Deep transfer learning recently has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer…

Cross-domain sentiment classification has drawn much attention in recent years. Most existing approaches focus on learning domain-invariant representations in both the source and target domains, while few of them pay attention to the…

Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias. Although unsupervised image-to-image translation networks represented by CycleGAN show great potential in dealing with domain gap, it…

This research evaluates a convolutional neural network (CNN) based approach to forensic video steganalysis. A video steganography dataset is created to train a CNN to conduct forensic steganalysis in the spatial domain. We use a noise…

Recently, deep learning-based facial landmark detection for in-the-wild faces has achieved significant improvement. However, there are still challenges in face landmark detection in other domains (e.g. cartoon, caricature, etc). This is due…

Using synthetic data for training neural networks that achieve good performance on real-world data is an important task as it can reduce the need for costly data annotation. Yet, synthetic and real world data have a domain gap. Reducing…

Dense retrieval in multilingual settings often searches over mixed-language collections, yet multilingual embeddings encode language identity alongside semantics. This language signal can inflate similarity for same-language pairs and crowd…

Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applications. This paper systematically investigates domain…

Aspect term extraction is a fundamental task in fine-grained sentiment analysis, which aims at detecting customer's opinion targets from reviews on product or service. The traditional supervised models can achieve promising results with…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Single-cell representation learning (SCRL) from gene expression data offers a way to uncover the complex regulatory logic underlying cellular function. Inspired by large language models in natural language modeling, several single-cell…

Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS). However, existing methods still struggle to preserve…

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to…

Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still…

The major threat in cyber crime for digital forensic examiner is to identify, analyze and interpret the concealed information inside digital medium such as image, audio and video. There are strong indications that hiding information inside…

Reinforcement learning (RL) has shown strong promise for LLM-based machine translation, with recent methods such as GRPO demonstrating notable gains; nevertheless, translation-oriented RL remains challenged by noisy learning signals arising…

Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain shift induced by time-varying land cover changes, including…

In recent years, there has been an increasing number of information hiding techniques based on network streaming media, focusing on how to covertly and efficiently embed secret information into real-time transmitted network media signals to…