From the 2 of 4 linked papers with an AI index.
4 papers
RLMM-Flow: A Flow-based Mobile Manipulation Framework with Latent-Space Reinforcement Learning
Shuhang Wang, Ziming Li, Hui Cheng
The paper introduces RLMM-Flow, a framework that first learns a flow-based generative policy from expert demonstrations for mobile manipulation and then improves it with latent-spa…
DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning
Shuhang Wang, Ziming Li, Hui Cheng
The paper introduces DHRCL, a reinforcement‑learning framework for code‑focused large language models that uses a hierarchy of dense rewards (syntax, execution, unit‑test pass, and…
Towards Generalizable Robotic Manipulation in Dynamic Environments
Heng Fang, Shangru Li, Shuhan Wang +3
Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap primarily stems from a scarcity of d…
NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation
Yiming Zeng, Hao Ren, Shuhang Wang +2
Visual navigation, a fundamental challenge in mobile robotics, demands versatile policies to handle diverse environments. Classical methods leverage geometric solutions to minimize…