Search papers, labs, and topics across Lattice.
3
0
5
0
Current speech deepfake detection systems falter dramatically against emotionally expressive attacks, with performance dropping to near-random levels on the new AffectDF benchmark.
Bridging the reasoning gap, X$^3$-OPD enables audio-language models to outperform their text-based counterparts in logical reasoning tasks.
Horizon-free regret can be achieved with a new algorithm that dramatically outperforms previous methods by eliminating logarithmic horizon dependence.
