Search papers, labs, and topics across Lattice.
National Taiwan University
4
0
4
AI agents can generate content but often miss the mark on effective teaching, struggling to adapt lessons to individual learners.
Amplifying just a handful of key neurons in the audio encoder can boost LALM accuracy on non-semantic speech attributes by over 25 points.
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.
Text-derived "nudges" can steer the reasoning of speech-based AI models, boosting accuracy by up to 4.4% without any training.
