GenSI: Generative Symbolic Intelligence

AI & ML interests

Our long-term goal is to achieve AGI by creating AI scientists. Specifically, our research directions include deeply unlocking intelligence through LLM, providing a favorable intelligent environment through AI4S foundational models, as well as exploring the in-depth interaction between these two aspects.

Recent Activity

Eric-Guoxy  submitted a paper 13 days ago

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

fdu-lcz  authored a paper 2 months ago

Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation

fdu-lcz  authored a paper 2 months ago

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

View all activity

Papers

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

View all Papers

Team members 11