Search papers, labs, and topics across Lattice.
University of Illinois Urbana-Champaign
3
0
6
Augmenting LLMs with targeted molecular context can boost prediction accuracy dramatically, achieving up to 28 percentage points improvement in classification tasks.
Personalizing LLMs just got a whole lot better: VRF's uncertainty-aware approach crushes existing methods, especially when data is scarce.
Dataset distillation for time series can now be done efficiently and scalably by operating in the frequency domain, sidestepping the limitations of prior methods.
