David Limpus
TheRealPilot638
ยท
AI & ML interests
HW/SW Co-design for efficient AI inference & training | RL & Control
Recent Activity
upvoted
a
collection
29 days ago
TraDo Series
upvoted
a
paper
about 1 month ago
Recursive Language Models
upvoted
a
paper
about 1 month ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Organizations
