Search papers, labs, and topics across Lattice.
2Meituan
3
0
6
Achieving over 90% performance retention with a staggering 20x KV cache compression could redefine efficiency in long-context audio inference.
Direct exposure to harmful objectives can lead LLMs to generate safer advice, while mediation can inadvertently align them with dangerous targets.
Audio LLMs can now be systematically evaluated for character alignment in role-playing scenarios, thanks to a new framework that judges both text and vocal features.
