Search papers, labs, and topics across Lattice.
3
0
6
Leading audio LLMs suffer up to a 41-percentage-point performance drop when prompted in native Southeast Asian languages compared to English, exposing severe blind spots in acoustic temporal grounding and paralinguistics.
Singing deepfakes are a surprisingly effective attack vector, and this paper introduces a new benchmark and detection method to address the resulting security gap.
Maximizing reward entropy by targeting a 50% pass rate in binary-reward RL unlocks significant speedups and performance gains in agentic tasks.
