← Search

Lorenz Wolf

2 accepted papers

2026

Post-training Large Language Models for Diverse High-Quality Responses

ICLR 2026poster

Reinforcement learning has emerged as a popular method for post-training large language models (LLMs). While improving the model's performance on downstream tasks, it often reduces the model's output diversity, leading to narrow, canonical responses. Existing methods to enhance diversity are limited…

Cited by 0SourceScholar
2023

Energy-Based Models for Functional Data using Path Measure Tilting

AISTATS 2023poster

Energy-Based Models (EBMs) have proven to be a highly effective approach for modelling densities on finite-dimensional spaces. Their ability to incorporate domain-specific choices and constraints into the structure of the model through composition make EBMs an appealing candidate for applications in…