1
EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
音视频多模态大模型token减少新方法,巧妙抑制混叠问题。
arXiv:2512.10324v2 Announce Type: replace Abstract: Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational costs of processing ma…