Your Transformer is Secretly Linear
Paper
•
2405.12250
•
Published
•
159
Nguyễn Minh Phúc
DatPySci
·
AI & ML interests
Reinforcement learning, NLP
Recent Activity
published
a model
about 2 hours ago
DatPySci/DeepSeek-Qwen-1.5B-GRPO
published
a model
about 2 hours ago
DatPySci/Qwen-1.5B-Math-GRPO
published
a model
about 15 hours ago
DatPySci/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Organizations
DatPySci's activity
upvoted
a
paper
11 months ago
upvoted
3
papers
about 1 year ago
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper
•
2404.03715
•
Published
•
62
Weak-to-Strong Jailbreaking on Large Language Models
Paper
•
2401.17256
•
Published
•
16
WARM: On the Benefits of Weight Averaged Reward Models
Paper
•
2401.12187
•
Published
•
20