Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Multi-branch of Attention Yields Accurate Results for Tabular Data
Xuechen Li, Yupeng Li, Jian Liu +2
Tabular data inherently exhibits significant feature heterogeneity, but existing transformer-based methods lack specialized mechanisms to handle this property. To bridge the gap, w…
cs.LG2024
Scalable Ensembling For Mitigating Reward Overoptimisation
Ahmed M. Ahmed, Rafael Rafailov, Stepan Sharkov +2
Reinforcement Learning from Human Feedback (RLHF) has enabled significant advancements within language modeling for powerful, instruction-following models. However, the alignment o…