Related papers: VLM as Policy: Common-Law Content Moderation Frame…

Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, particularly generating not-safe-for-work (NSFW) content, such…

This work explores the impact of moderation on users' enjoyment of conversational AI systems. While recent advancements in Large Language Models (LLMs) have led to highly capable conversational AIs that are increasingly deployed in…

Digital video is central to communication, education, and entertainment, but without audio description (AD), blind and low-vision users are excluded. While crowdsourced platforms and vision-language models (VLMs) expand AD production,…

AI models capable of comprehending humor hold real-world promise -- for example, enhancing engagement in human-machine interactions. To gauge and diagnose the capacity of multimodal large language models (MLLMs) for humor understanding, we…

There has been growing sentiment recently that modern large multimodal models (LMMs) have addressed most of the key challenges related to short video comprehension. As a result, both academia and industry are gradually shifting their…

The exponential growth of social media platforms, such as Facebook and TikTok, has revolutionized communication and content publication in human society. Users on these platforms can publish multimedia content that delivers information via…

Short-video platforms are closed-loop, human-in-the-loop ecosystems where platform policy, creator incentives, and user behavior co-evolve. This feedback structure makes counterfactual policy evaluation difficult in production, especially…

Video-sharing social media platforms, such as TikTok, YouTube, and Instagram, implement content moderation policies aimed at reducing exposure to harmful videos among minor users. As video has become the dominant and most immersive form of…

Video Large Language Models (VideoLLMs) are increasingly deployed on numerous critical applications, where users rely on auto-generated summaries while casually skimming the video stream. We show that this interaction hides a critical…

Large vision-language models (LVLMs) are increasingly used for tasks where detecting multimodal harmful content is crucial, such as online content moderation. However, real-world harmful content is often camouflaged, relying on nuanced…

Research into community content moderation often assumes that moderation teams govern with a single, unified voice. However, recent work has found that moderators disagree with one another at modest, but concerning rates. The problem is not…

Social media platforms have implemented automated content moderation tools to preserve community norms and mitigate online hate and harassment. Recently, these platforms have started to offer Personalized Content Moderation (PCM), granting…

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…

As Vision-Language Models (VLMs) demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models (LLMs),…

The proliferation of harmful content on online platforms is a major societal problem, which comes in many different forms including hate speech, offensive language, bullying and harassment, misinformation, spam, violence, graphic content,…

E-commerce short videos represent a high-revenue segment of the online video industry characterized by a goal-driven format and dense multi-modal signals. Current models often struggle with these videos because existing benchmarks focus…

Content moderation is the process of flagging content based on pre-defined platform rules. There has been a growing need for AI moderators to safeguard users as well as protect the mental health of human moderators from traumatic content.…

With the prevalence of large-scale pretrained vision-language models (VLMs), such as CLIP, soft-prompt tuning has become a popular method for adapting these models to various downstream tasks. However, few works delve into the inherent…

Driven by the wave of large language models, Video-Language Models (VLMs) have become a significant yet challenging technology to bridge the gap between videos and texts. Although previous VLM works have made significant progress, almost…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…