Hao Zhu

7 papers Stanford University

• CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning
• Machine Unlearning via Task Simplex Arithmetic
• Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
• Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models
• SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
• SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
• SpatialLM: Training Large Language Models for Structured Indoor Modeling