10 citations · 10 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
A Generalization Theory of Cross-Modality Distillation with Contrastive Learning
Hangyu Lin, Chen Liu, Chengming Xu +3
Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great…
cs.LG2023★ 10 cited
Mitigating the Alignment Tax of RLHF
Yong Lin, Hangyu Lin, Wei Xiong +14
LLMs acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, w…