Related papers: PrismAgent: Illuminating Harm in Memes via a Zero-…

Weakly Supervised Semantic Segmentation (WSSS) with image level labels aims to produce pixel level predictions without requiring dense annotations. While recent approaches have leveraged generative models to augment existing data, they…

Social media platforms enable instant and ubiquitous connectivity and are essential to social interaction and communication in our technological society. Apart from its advantages, these platforms have given rise to negative behaviors in…

The prevalence of multi-modal content on social media complicates automated moderation strategies. This calls for an enhancement in multi-modal classification and a deeper understanding of understated meanings in images and memes. Although…

With the increasing prevalence of multimodal content on social media, sentiment analysis faces significant challenges in effectively processing heterogeneous data and recognizing multi-label emotions. Existing methods often lack effective…

Online hate remains a significant societal challenge, especially as multimodal content enables subtle, culturally grounded, and implicit forms of harm. Hateful memes embed hostility through text-image interactions and humor, making them…

Recent advances in image generation gave rise to powerful tools for semantic image editing. However, existing approaches can either operate on a single image or require an abundance of additional information. They are not capable of…

Hallucinations pose critical risks for large language model (LLM)-based agents, often manifesting as hallucinative actions resulting from fabricated or misinterpreted information within the cognitive context. While recent studies have…

Traditional approaches to training agents have generally involved a single, deterministic environment of minimal complexity to solve various tasks such as robot locomotion or computer vision. However, agents trained in static environments…

The rise of disinformation on social media, especially through the strategic manipulation or repurposing of images, paired with provocative text, presents a complex challenge for traditional fact-checking methods. In this paper, we…

Training fair and unbiased machine learning models is crucial for high-stakes applications, yet it presents significant challenges. Effective bias mitigation requires deep expertise in fairness definitions, metrics, data preprocessing, and…

Memes are one of the most popular types of content used in an online disinformation campaign. They are primarily effective on social media platforms since they can easily reach many users. Memes in a disinformation campaign achieve their…

Diffusion models (DMs) are widely used for text-to-image generation, but their strong generative capabilities also raise concerns about unsafe or undesirable content. Concept erasure aims to mitigate these risks by removing specific…

Food image classification plays a vital role in intelligent food quality inspection, dietary assessment, and automated monitoring. However, most existing supervised models rely heavily on large labeled datasets and exhibit limited…

Innovation in nanophotonics currently relies on human experts who synergize specialized knowledge in photonics and coding with simulation and optimization algorithms, entailing design cycles that are time-consuming, computationally…

The increasing use of synthetic media, particularly deepfakes, is an emerging challenge for digital content verification. Although recent studies use both audio and visual information, most integrate these cues within a single model, which…

Artificial intelligence has shown promise in medical imaging, yet most existing systems lack flexibility, interpretability, and adaptability - challenges especially pronounced in ophthalmology, where diverse imaging modalities are…

Accurate detection and classification of online hate is a difficult task. Implicit hate is particularly challenging as such content tends to have unusual syntax, polysemic words, and fewer markers of prejudice (e.g., slurs). This problem is…

Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone…

Multimodal large language models (MLLMs) have shown strong capabilities but remain limited to fixed modality pairs and require costly fine-tuning with large aligned datasets. Building fully omni-capable models that can integrate text,…

Online video understanding requires models to perform continuous perception and long-range reasoning within potentially infinite visual streams. Its fundamental challenge lies in the conflict between the unbounded nature of streaming media…