Awesome Papers
LLMs
Quantum
SimSearch
AI4Code
Agents
CV
Robotics
Cyber
AI4Sci
Speech
RL
MM
GenAI
Graph
TS
RecSys
FL
☾
☀
← authors
·
overview
Ahmed Awadallah
11
papers ·
2668
citations
Most-cited papers
Direct Nash Optimization: Teaching Language Models To Self-improve With General Preferences
2024 · 173 citations
Topics
Reinforcement Learning
Fine-Tuning
Safety & Alignment
Training Techniques
🤖
Ask AI