Tongya Zheng

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

Tree of Preferences for Diversified Recommendation

SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data

SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater

From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks

Odyssey: Empowering Minecraft Agents with Open-World Skills