Search papers, labs, and topics across Lattice.
TU Dortmund University, Lamarr Institute for Machine Learning and Artificial Intelligence
4
0
7
Compressing tabular models by 85% without sacrificing performance could revolutionize how we deploy foundation models in resource-constrained environments.
Automated prompt optimization can boost LLM performance in complex tasks, achieving up to 72.5% success where traditional methods fail completely.
Adaptive coalition selection in ShaplEIG boosts Shapley value estimation efficiency, slashing computational complexity and enhancing performance in resource-constrained settings.
Questioning the common practice of interpreting data through a single model class, this work reveals the existence of alternative well-performing models across multiple model classes and their hyperparameters.
