The Attention Triangle in Audio-Video Models
- 类型：arxiv
- 标识：2609.03586
- 链接：https://arxiv.org/abs/2609.03586
- 主分类：multimodal
- 形态：method
- TLDR：Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual content, yet this same mechanism can introduce subtle and systematic semantic leakage. We study these models by probing and analyzing the ``attention triangle,'' comprising the three cross-attention edges connecting the text, audio, and video streams, and examine how semantic information is routed across modalities during generation. Our analysis reveals that routing along the audio-video edge is bidirectional: audio can influence video generation, while video can influence audio generation. This e
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-07-agent-rag-longcontext-candidates.json