Large Audio-Language Models
PulseAugur coverage of Large Audio-Language Models — every cluster mentioning Large Audio-Language Models across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
隐藏音频攻击危及AI语音系统
新研究表明，包括大型音频语言模型（LALMs）在内的AI语音系统容易受到隐藏音频攻击。这些攻击将人耳无法察觉的声音嵌入音频片段，使恶意行为者能够以高成功率操纵AI模型执行未经授权的命令。该技术被称为AudioHijack，即使在用户提供不同指令的情况下，也能欺骗模型执行敏感的网络搜索或发送电子邮件等操作。
-
HeadRouter prunes audio tokens in LLMs by routing attention heads
Researchers have introduced HeadRouter, a novel method for compressing large audio language models by dynamically pruning audio tokens. Unlike previous approaches that assume uniform head importance, HeadRouter recogniz…
-
Audio-language models often answer questions without audio, challenging evaluation methods.
New research indicates that Large Audio-Language Models (LALMs) may not possess true auditory perception despite high benchmark scores. Studies reveal that these models can answer questions using only text and general k…