IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Paper
•
2411.06208
•
Published
•
20
Yongbin Li
Yongbin-Li
AI & ML interests
None yet
Recent Activity
authored
a paper
6 days ago
Think on your Feet: Adaptive Thinking via Reinforcement Learning for
Social Agents
authored
a paper
2 months ago
DeepSolution: Boosting Complex Engineering Solution Design via
Tree-based Exploration and Bi-point Thinking
authored
a paper
4 months ago
Debate Helps Weak-to-Strong Generalization
Organizations
None yet