Jiang

Dongwei

·

Some-random

AI & ML interests

None yet

Recent Activity

upvoted a paper 6 days ago

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

upvoted a paper 12 months ago

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety

upvoted a paper about 1 year ago

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning

View all activity

Organizations

Dongwei 's papers 4

arxiv:2506.11930

arxiv:2410.01044

arxiv:2409.12183

arxiv:2407.09007