Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
Replacing black-box image regression with an unrolled spectral unmixing objective physically disentangles structured sensor artifacts from true signals while boosting zero-shot transfer across complex noise regimes.
Decoupling structured sensor artifacts with a Deep Image Prior allows modular spectral unmixing to slash reconstruction error by up to 69.5% without corrupting physical abundance estimates under flawed endmember priors.
Transforming dense LLMs into hardware-efficient sparse models can achieve 4x sparsity without sacrificing performance, revolutionizing model deployment strategies.
