Bolian Li's picture

Bolian Li

lblaoke

·

https://lblaoke.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 19 days ago

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

authored a paper 19 days ago

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

authored a paper 19 days ago

Learning Self-Correction in Vision-Language Models via Rollout Augmentation

View all activity

Organizations

lblaoke 's papers 14

arxiv:2604.26326

arxiv:2602.08503

arxiv:2601.22311

arxiv:2510.02341

arxiv:2504.02193

arxiv:2502.18300

arxiv:2501.14090

arxiv:2410.06625

arxiv:2406.16306

arxiv:2310.05401

arxiv:2303.06075

arxiv:2111.09030

arxiv:2110.14863

arxiv:2110.08030