UNIVID: Unified Vision-Language Model for Video Moderation
Global-scale video moderation faces a dual challenge: the need for fine-grained multi-modal reasoning and the demand for interpretable outputs to support downstream enforcement. Traditional moderation systems often rely on fragmented black-box classifiers that are difficult to maintain and lack transparency. In this paper, we present UNIVID, a UNIfied VIsion-language model for video moDeration. Unlike standard classification models, UNIVID generates policy-aware captions that serve as an interpr
Record details
Published: 4 June 2026
Source: arXiv
Category: Research
Topics: Regulation · Transparency
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Explainable AI-Driven Cyber Risk Analytics and Model Reliability Assessment for Intelligent Governance of U.S. Critical Infrastructure: An XGBoost and SHAP-Based Intrusion Detection Framework
arXiv · 4 June 2026
Sustainability by Design in Decentralized Autonomous Organizations: An Empirical Review of Governance, Innovation, and Institutional Design
arXiv · 4 June 2026
Didact: A Cross-Domain Capability Discovery System for Defence
arXiv · 5 June 2026
The Digital Apprentice: A Framework for Human-Directed Agentic AI Development
arXiv · 3 June 2026
The Violation Situation Pattern: A Knowledge-Graph Pattern for Compliance Violations
arXiv · 2 June 2026
Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach
arXiv · 2 June 2026
How to cite this record
ethics.ai (4 June 2026), “UNIVID: Unified Vision-Language Model for Video Moderation,” evidence record 1448, https://ethics.ai/record/1448 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.