← Search

Michael Santacroce

2 accepted papers

2025

Adapting LLM Agents with Universal Communication Feedback

NAACL 2025findings

Recent advances in large language models (LLMs) have demonstrated potential for LLM agents. To facilitate the training for these agents with both linguistic feedback and non-linguistic reward signals, we introduce Learning through Communication (LTC). We design a universal buffer to store all the fe…

2022

Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features

ICLR 2022poster

While a popular limit of infinite-width neural networks, the Neural Tangent Kernel (NTK) often exhibits performance gaps from finite-width neural networks on standard datasets, due to lack of feature learning. Although the feature learning *maximal update limit*, or *μ-limit* (Yang and Hu, 2020) of…