Search papers, labs, and topics across Lattice.
3
0
4
3
Amplifying just a handful of key neurons in the audio encoder can boost LALM accuracy on non-semantic speech attributes by over 25 points.
Decompilers might produce readable code, but good luck getting it to actually *work* – a new benchmark reveals a massive gap between recompilability and functional correctness.
Text-only LLMs already contain surprisingly diverse levels of auditory knowledge, and this pre-existing knowledge strongly predicts their performance when adapted for audio-language tasks.
