Siqi Shen

MAGE: Multi-scale Autoregressive Generation for Offline Reinforcement Learning

Getting Your LLMs Ready for Reinforcement Learning with Lightweight SFT

L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery

DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement Learning

PlanU: Large Language Model Reasoning through Planning under Uncertainty

GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning