Search papers, labs, and topics across Lattice.
2
0
4
1
Diffusion models can achieve fairness and diversity simultaneously without sensitive attribute labels by using a frozen model adapter and a vision-language embedding space.
Forget general-purpose ecoacoustic models: task-oriented, region-specific training with DeepForestSound boosts detection performance to near-perfect AP scores (0.96+) for primates and elephants in African rainforests.
