arxiv:2404.03214
Walid Bousselham
WalidBouss
AI & ML interests
Computer Vision, Multi-modal learning and Zero-shot adaptation.
Recent Activity
upvoted
an
article
about 12 hours ago
Deriving the PPO Loss from First Principles
upvoted
a
paper
22 days ago
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models