From the 1 of 4 linked papers with an AI index.
4 papers
HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation
Shaopeng Zhai, Qi Zhang, Tianyi Zhang +5
The paper introduces HELP, a pipeline that uses two specialized human operators to supervise a fleet of robots during post‑training of Vision‑Language‑Action models, improving huma…
Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT
Tianyi Zhang, Shaopeng Zhai, Haoran Zhang +2
Unconstrained fine-tuning of flow-matching Vision-Language-Action (VLA) models drives dense parameter overwrites, degrading pre-trained capabilities. We present Conservative Superv…
A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
Shaopeng Zhai, Qi Zhang, Tianyi Zhang +7
Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLA…
Efficient Skill Discovery via Regret-Aware Optimization
He Zhang, Ming Zhou, Shaopeng Zhai +2
Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity throu…