arxiv:2404.09173
Dongseong Hwang
dongseong
ยท
AI & ML interests
Speech, RL, AGI
Recent Activity
published
a model
2 days ago
dongseong/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
upvoted
a
paper
10 months ago
Thermodynamic Natural Gradient Descent
authored
a paper
11 months ago
TransformerFAM: Feedback attention is working memory
Organizations
None yet