Bolian Li
lblaoke
AI & ML interests
None yet
Recent Activity
authored a paper about 6 hours ago
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in
DPO Safety Alignment authored a paper about 6 hours ago
DRIFT: Learning from Abundant User Dissatisfaction in Real-World
Preference Learning authored a paper about 6 hours ago
Learning Self-Correction in Vision-Language Models via Rollout AugmentationOrganizations
models 44
lblaoke/opt-350m-hh-rlhf-rm-trl-v5
0.3B • Updated • 5
lblaoke/opt-350m-hh-rlhf-dpo-trl-v5
0.3B • Updated • 2
lblaoke/opt-350m-hh-rlhf-chosen-sft-trl-v5
0.3B • Updated • 1
lblaoke/opt-125m-hh-rlhf-rm-trl-v5
0.1B • Updated • 4
lblaoke/opt-125m-hh-rlhf-dpo-trl-v5
0.1B • Updated • 4
lblaoke/opt-125m-hh-rlhf-chosen-sft-trl-v5
0.1B • Updated • 6
lblaoke/qwama-0.5b-hh-rlhf-sft-chosen-trl-v4
0.5B • Updated • 1
lblaoke/qwama-0.5b-skywork-pref-sft-chosen-dpo-trl-v3
0.5B • Updated • 2
lblaoke/qwama-0.5b-skywork-pref-sft-rejected-chosen-trl-v3
0.5B • Updated • 2
lblaoke/qwama-0.5b-skywork-pref-sft-chosen-trl-v3
0.5B • Updated • 4
datasets 0
None public yet