Zhi-Hua Zhou

A Study on PAVE Specification for Learnware

On Measuring Influence in Avoiding Undesired Future

Expertise Can Be Helpful for Reinforcement Learning-based Macro Placement

Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules

Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality

Provably Efficient Online RLHF with One-Pass Reward Modeling

Discovering Symbolic Partial Differential Equation by Abductive Learning

Variance-Reduced Long-Term Rehearsal Learning with Quadratic Programming Reformulation

Curriculum Abductive Learning

On the Diversity of Adversarial Ensemble Learning

Enabling Optimal Decisions in Rehearsal Learning under CARE Condition

Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update

One-Pass Feature Evolvable Learning with Theoretical Guarantees

TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree