3 papers
cs.RO2026
Q-VGM: Q-Value-Gradient Matching for Offline-to-Online Reinforcement Learning of Flow-Matching VLA
Ziqian Wang, Jiayu Sun, Yitian Liu +3
We propose Q-Guided Value-Gradient Matching (Q-VGM), an offline-to-online reinforcement learning (RL) method for fine-tuning flow-matching vision-language-action (VLA) policies wit…
cs.LG2026
DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables
Ziqian Wang, Chenxi Fang, Zhen Zhang
Enforcing nonlinear inequality constraints in neural networks remains challenging, especially when the output is subject to many coupled constraints. Existing hard constraint metho…
cs.RO2026
Self-Supervised Path Planning in Unstructured Environments via Global-Guided Differentiable Hard Constraint Projection
Ziqian Wang, Chenxi Fang, Zhen Zhang
Deploying deep learning agents for autonomous navigation in unstructured environments faces critical challenges regarding safety, data scarcity, and limited computational resources…