Search papers, labs, and topics across Lattice.
City University of Macau
3
5
6
19
Inverted self-attention reveals hidden causal relationships in multivariate time series, outperforming traditional methods by reducing spurious correlations.
Dualin achieves state-of-the-art image fidelity by simultaneously recovering semantic prompts and latent noise, overcoming the limitations of traditional prompt inversion methods.
A shockingly small number of poisoned, synthetically distilled data points can completely hijack a model during transfer learning, turning it into an unwitting accomplice.
