@inproceedings{Yang26-NIPS,
address = {Sydney, Australia},
author = {Yang Li and Erik Nijkamp and Semih Yavuz and Shafiq Joty},
booktitle = {2026 Conference on Neural Information Processing Systems},
numpages = {9},
series = {NeurIPS'26},
title = {Learning from Language Feedback via Variational Policy Distillation},
url = {https://arxiv.org/abs/2605.15113},
year = {2026}
}