Seungjin Kim

promotion

AI & ML interests

None yet

Recent Activity

updated a model about 1 month ago

promotion/UW1-PROSPER

published a model about 1 month ago

promotion/UW1-PROSPER

updated a model about 1 month ago

promotion/UW1-SPPO

View all activity

Organizations

None yet

promotion 's models 88

promotion/UW1-PROSPER

Text Generation • 8B • Updated Sep 17 • 147

promotion/UW1-SPPO

Text Generation • 8B • Updated Sep 17 • 182

promotion/UW1-INPO-soft

Text Generation • 8B • Updated Sep 17 • 174

promotion/UW1-DPO-soft

Text Generation • 8B • Updated Sep 17 • 177

promotion/UW1-FixedRefNash-PW

Text Generation • 8B • Updated Sep 17 • 178

promotion/UW1-NBPO-PW

Text Generation • 8B • Updated Sep 17 • 175

promotion/FixedRefNash-Qwen2.5-7B-WildChecklists-2ep

Text Generation • 8B • Updated Sep 16 • 149

promotion/PROSPER-Qwen2.5-7B-WildChecklists-2ep

Text Generation • 8B • Updated Sep 16 • 150

promotion/NBPO-Qwen2.5-7B-WildChecklists-2ep

Text Generation • 8B • Updated Sep 16 • 153

promotion/nbpo-policy-diagnostics

promotion/nbpo-saferlhf-preference-models

promotion/Llama-3.1-8B-SafeRLHF-NBPO-600updates

Text Generation • 8B • Updated Sep 7 • 83

promotion/Llama-3.1-8B-TLDR-NBPO-600updates

Text Generation • 8B • Updated Sep 7 • 62

promotion/Llama-3.1-8B-NBPO-UltraFeedback-600updates

Text Generation • 8B • Updated Sep 7 • 82

promotion/Llama-3.1-8B-SafeRLHF-NBPO-stage2

Text Generation • 8B • Updated Sep 7 • 66

promotion/Llama-3.1-8B-NBPO-finitepool

Text Generation • 8B • Updated Sep 6 • 102

promotion/Qwen3-8B-Panacea-baseline

Text Generation • 8B • Updated Sep 6 • 28

promotion/Qwen3-8B-RewardedSoups-baseline

Text Generation • 8B • Updated Sep 6 • 25

promotion/Qwen3-8B-MaxMinRLHF-baseline

Text Generation • 8B • Updated Sep 6 • 21

promotion/Llama-3.1-8B-SafeRLHF-NBPO-eta0.1

Text Generation • 8B • Updated Sep 6 • 15

promotion/Llama-3.1-8B-TLDR-NBPO-eta0.05

Text Generation • 8B • Updated Sep 6 • 16

promotion/Llama-3.1-8B-NBPO-UltraFeedback-eta0.05

Text Generation • 8B • Updated Sep 6 • 16

promotion/Llama-3.1-8B-NBPO-UltraFeedback-clean

Text Generation • 8B • Updated Sep 6 • 16

promotion/Llama-3.1-8B-TLDR-MaxMinRLHF-baseline

Text Generation • 8B • Updated Sep 5 • 97

promotion/Llama-3.1-8B-MaxMinRLHF-baseline

Text Generation • 8B • Updated Sep 5 • 90

promotion/Llama-3.1-8B-SafeRLHF-SurplusMaxMin-baseline

Text Generation • 8B • Updated Sep 5 • 61

promotion/Llama-3.1-8B-SafeRLHF-AbsoluteMaxMin-baseline

Text Generation • 8B • Updated Sep 5 • 50

promotion/Llama-3.1-8B-SafeRLHF-Utilitarian-baseline

Text Generation • 8B • Updated Sep 5 • 69

promotion/Llama-3.1-8B-SafeRLHF-NBPO-finitepool

Text Generation • 8B • Updated Sep 5 • 64

promotion/Llama-3.1-8B-SafeRLHF-RewardedSoups-baseline

Text Generation • 8B • Updated Sep 5 • 46