Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
Paper • 2605.26895 • Published • 8
Mingwu Zheng
MuonZ
AI & ML interests
Neural Rendering
Recent Activity
upvoted a paper about 8 hours ago
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models authored a paper about 1 year ago
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers updated a collection over 2 years ago
TransformersOrganizations
None yet