zhiqin yang's picture

zhiqin yang

visity

visitworld123

AI & ML interests

None yet

Recent Activity

authored a paper 9 days ago

MemFly: On-the-Fly Memory Optimization via Information Bottleneck

upvoted a paper 13 days ago

MemFly: On-the-Fly Memory Optimization via Information Bottleneck

submitted a paper 13 days ago

MemFly: On-the-Fly Memory Optimization via Information Bottleneck

View all activity

Organizations

None yet

Papers 4

arxiv:2602.07885

arxiv:2506.23329

arxiv:2503.24026

arxiv:2402.14430

models 4

visity/llama-3-instruct-8b-cpo-full-beta-2.5_alpha-0.25_e-version-false-lr-1e-6

Text Generation • 8B • Updated 16 days ago • 11

visity/llama-3-instruct-8b-orpo-full

Text Generation • 8B • Updated 20 days ago • 16

visity/llama-3-instruct-8b-dpo-full

Text Generation • 8B • Updated 21 days ago • 8

visity/Llama-3-Base-8B-SFT

datasets 0

None public yet