Yixuan Wang

LuckyOrz

8 4

·

LuckySJTU

AI & ML interests

LLM pretraining, hierarchical model, efficient LLM

Recent Activity

upvoted a collection 4 days ago

NCP_ArchPreview

upvoted a paper 28 days ago

MemSFT: Mitigating Alignment Tax with an External Parametric Memory

upvoted a paper about 1 month ago

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

View all activity

Organizations

liked a model 4 months ago

XiaomiMiMo/MiMo-V2.5-Pro

Text Generation • 1T • Updated Jul 9 • 47.7k • • 745

liked 2 models 7 months ago

yuliang03181/ConceptLM_Llama3.1_8B

8B • Updated Feb 3 • 6 • 8

yuliang03181/ConceptLM_Pythia_410M

Updated Feb 3 • 9 • 6

liked a Space 12 months ago

KVPress Leaderboard

KVPress leaderboard: benchmark KV Cache compression methods