4 citations · 4 across the 4 of their papers we have counts for
4 papers
BALAR : A Bayesian Agentic Loop for Active Reasoning
Aymen Echarghaoui, Dongxia Wu, Emily B. Fox
Large language models increasingly operate in interactive settings where solving a task requires multiple rounds of information exchange with a user. However, most current systems…
Univariate-Guided Interaction Modeling
Aymen Echarghaoui, Robert Tibshirani
We propose a procedure for sparse regression with pairwise interactions, by generalizing the Univariate Guided Sparse Regression (UniLasso) methodology. A central contribution is o…
Intelligently Weighting Multiple Reference Models for Direct Preference Optimization of LLMs
Skyler Wu, Aymen Echarghaoui
Fine-tuning is integral for aligning large language models (LLMs) with human preferences. Multiple-Reference Preference Optimization (MRPO) builds on Direct Preference Optimization…
Lasting Diversity and Superior Runtime Guarantees for the Genetic Algorithm
Benjamin Doerr, Aymen Echarghaoui, Mohammed Jamal +1
Most evolutionary algorithms (EAs) used in practice employ crossover. In contrast, only for few and mostly artificial examples a runtime advantage from crossover could be proven wi…