YijuGuo
YijuGuo
AI & ML interests
LLM Alignment
Recent Activity
authored
a paper
1 day ago
Controllable Preference Optimization: Toward Controllable
Multi-Objective Alignment
authored
a paper
1 day ago
LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
authored
a paper
1 day ago
Learning to Focus: Causal Attention Distillation via Gradient-Guided
Token Pruning
Organizations