PPL
Hao Cheng
Papers (5)
GRIN: GRadient-INformed MoELatent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling BehaviorBridging Control with Neural Network Verifier alpha-beta-CROWN: A TutorialOrchard: An Open-Source Agentic Modeling FrameworkCRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies