Related papers: KID: Knowledge-Injected Dual-Head Learning for Kno…
Memes are an increasingly prevalent element of online discourse in social networks, especially among young audiences. They carry ideas and messages that range from humorous to hateful, and are widely consumed. Their potentially high impact…
We study the zero-shot Composed Image Retrieval (ZS-CIR) task, which is to retrieve the target image given a reference image and a description without training on the triplet datasets. Previous works generate pseudo-word tokens by…
Metaphorical imagination, the ability to connect seemingly unrelated concepts, is fundamental to human cognition and communication. While understanding linguistic metaphors has advanced significantly, grasping multimodal metaphors, such as…
With a surge in the usage of social media postings to express opinions, emotions, and ideologies, there has been a significant shift towards the calibration of social media as a rapid medium of conveying viewpoints and outlooks over the…
Memes are graphics and text overlapped so that together they present concepts that become dubious if one of them is absent. It is spread mostly on social media platforms, in the form of jokes, sarcasm, motivating, etc. After the success of…
Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources…
Sound event detection (SED) is essential for recognizing specific sounds and their temporal locations within acoustic signals. This becomes challenging particularly for on-device applications, where computational resources are limited. To…
Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning…
With the recent rise of toxicity in online conversations on social media platforms, using modern machine learning algorithms for toxic comment detection has become a central focus of many online applications. Researchers and companies have…
Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…
Cognitive diagnosis model (CDM) is a fundamental and upstream component in intelligent education. It aims to infer students' mastery levels based on historical response logs. However, existing CDMs usually follow the ID-based embedding…
The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL), in which devices collaboratively train on-device Machine…
Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost;…
Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently…
The growing number of Internet users and the prevalence of web applications make it necessary to deal with very complex software and applications in the network. This results in an increasing number of new vulnerabilities in the systems,…
Recent advances in multimodal AI have enabled progress in detecting synthetic and out-of-context content. However, existing efforts largely overlook the intent behind AI-generated images. To fill this gap, we introduce S-HArM, a multimodal…
How can models effectively detect out-of-distribution (OOD) samples in complex, multi-label settings without extensive retraining? Existing OOD detection methods struggle to capture the intricate semantic relationships and label…
The proliferation of harmful online content--e.g., toxicity, spam, and negative sentiment--demands robust and adaptable moderation systems. However, prevailing moderation systems are centralized and task-specific, offering limited…
Memes, which rapidly disseminate personal opinions and positions across the internet, also pose significant challenges in propagating social bias and prejudice. This study presents a novel approach to detecting harmful memes, particularly…
Language Identification (LID) is a challenging task, especially when the input texts are short and noisy such as posts and statuses on social media or chat logs on gaming forums. The task has been tackled by either designing a feature set…