Award

Best Paper Award

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs

Jonas Hübotter, Sascha Bongni, Ido Hakimi, Andreas Krause

Best Paper Runner-up

Entropic Distribution Matching for Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity

Ziniu Li, Congliang Chen, Tian Xu, Zeyu Qin, Jiancong Xiao, Ruoyu Sun, Zhi-Quan Luo