An RL-central Framework for Language and Vision Assistant, which decouples algorithm logic from distributed execution, enables modular customization.
ZiHao Ma
mzh12345
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening liked
a dataset about 2 months ago
UnipatAI/BabyVision updated
a model about 2 months ago
mzh12345/RLLaVA_search_grpo_3b