SOURCE-LINKED INTELLIGENCE

AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses new challenges for safety evaluation, as unsafe content may be conveyed through the audio track or arise only when the visual and audio tracks are interpreted jointly. Existing safety benchmarks largely focus on either generated video or generated audio in isolation and are therefore not designed to capture these risks. To close this gap, we introduce AV-SafetyBench, the first safety benchmark developed specifically for T2AV generation. AV-Safety

Read original source ↗ Open in workspace

recordType

paper

region

Global