Xu Zhihao's picture

2 21

Xu Zhihao

naiweizi

·

AI & ML interests

Trustworthy AI

Recent Activity

upvoted a paper 5 days ago

LongCat-Flash-Omni Technical Report

liked a dataset 14 days ago

Rubbisheep/InteractComp

upvoted a paper 15 days ago

ReCode: Unify Plan and Action for Universal Granularity Control

View all activity

Organizations

None yet

Collections 1

models 10

naiweizi/R1-Qwen-1_5B-Cold_Start-OpenR1_Math-priority

2B • Updated Jul 18 • 3

naiweizi/dpo-harmless_saferlhf

naiweizi/mistral-dpo-helpful-vanilla-1e-4

naiweizi/mistral-dpo-harmless-vanilla-2e-4

naiweizi/test

Text Generation • 8B • Updated Apr 21

naiweizi/dpo-harmless_helpful-vanilla

naiweizi/dpo-harmless_helpful-rc_armo

naiweizi/dpo-harmless_helpful-mixed

naiweizi/dpo-harmless_helpful-rc_armo_mistral

naiweizi/qwen2.5-instruct-sft_helpsteer2

8B • Updated Mar 14

datasets 2

naiweizi/RC_single_objective

Preview • Updated Jun 4 • 3

naiweizi/pref_dataset

Preview • Updated Apr 14 • 1