arxiv:2412.04468
Yuxian Gu
t1101675
AI & ML interests
Efficient methods for language models
Recent Activity
upvoted
an
article
1 day ago
Differential Transformer V2
upvoted
a
paper
19 days ago
mHC: Manifold-Constrained Hyper-Connections
upvoted
a
paper
about 2 months ago
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices