Peilin Zhao

5 papers Tencent

• Continual Optimization with Symmetry Teleportation for Multi-Task Learning
• Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning
• Geometric Algebra-Enhanced Bayesian Flow Network for RNA Inverse Design
• Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
• Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization