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

We introduce VideoComp, a benchmark and learning framework for advancing video-text compositionality understanding, aimed at improving vision-language models (VLMs) in fine-grained temporal alignment. Unlike existing benchmarks focused on…

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to…

We evaluate multimodal large language models (MLLMs) for topic-aligned captioning in financial short-form videos (SVs) by testing joint reasoning over transcripts (T), audio (A), and video (V). Using 624 annotated YouTube SVs, we assess all…

The task of cultivating healthy communication in online communities becomes increasingly urgent, as gaming and social media experiences become progressively more immersive and life-like. We approach the challenge of moderating online…

As Artificial General Intelligence (AGI) becomes increasingly integrated into various facets of human life, ensuring the safety and ethical alignment of such systems is paramount. Previous studies primarily focus on single-modality threats,…

Short-video platforms like Douyin and Kwai have become central to adolescent digital life, but they also risk exposing teens to algorithmically amplified harmful content. Despite its societal importance, the scale, mechanisms, and…

Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a systematic benchmark remains lacking. This paper addresses…

The integration of vision-language models into robotic systems constitutes a significant advancement in enabling machines to interact with their surroundings in a more intuitive manner. While VLMs offer rich multimodal reasoning, existing…

Understanding surveillance video content remains a critical yet underexplored challenge in vision-language research, particularly due to its real-world complexity, irregular event dynamics, and safety-critical implications. In this work, we…

In recent years, with the significant evolution of multi-modal large models, many recommender researchers realized the potential of multi-modal information for user interest modeling. In industry, a wide-used modeling architecture is a…

Detecting harmful memes is crucial for safeguarding the integrity and harmony of online environments, yet existing detection methods are often resource-intensive, inflexible, and lacking explainability, limiting their applicability in…

Illegal content reporting mechanisms are a key technical and organizational measure through which online platforms address illegal content under the European Union Digital Services Act (DSA). Article 16 requires user notices to be…

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess…

Multi-modal large language models (MLLMs) have demonstrated considerable potential across various downstream tasks that require cross-domain knowledge. MLLMs capable of processing videos, known as Video-MLLMs, have attracted broad interest…

Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically…

Existing multilingual vision-language (VL) benchmarks often only cover a handful of languages. Consequently, evaluations of large vision-language models (LVLMs) predominantly target high-resource languages, underscoring the need for…

Large language models' (LLMs') outputs are shaped by opaque and frequently-changing company content moderation policies and practices. LLM moderation often takes the form of refusal; models' refusal to produce text about certain topics both…

Content moderation (removing or limiting the distribution of posts based on their contents) is one tool social networks use to fight problems such as harassment and disinformation. Manually screening all content is usually impractical given…

This paper focuses to detect the fake news on the short video platforms. While significant research efforts have been devoted to this task with notable progress in recent years, current detection accuracy remains suboptimal due to the rapid…

As Vision-Language Models (VLMs) move into interactive, multi-turn use, safety concerns intensify for multimodal multi-turn dialogue, which is characterized by concealment of malicious intent, contextual risk accumulation, and cross-modal…