PPL
Qi Wang
Papers (7)
Efficient On-policy Visual-RL via Stochastic Decoupled Policy GradientVGGT-CD: Training-Free Robust Registration for 3D Change Detection$φ$-Balancing for Mixture-of-Experts TrainingDoes Your Wildfire Prediction Model Actually Work, or Just Score Well?OrbiSim: World Models as Differentiable Physics Engines for Embodied IntelligenceBioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory ManipulationListwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex