From the 2 of 4 linked papers with an AI index.
4 papers
A Glimpse into Long-term Physical Coexistence with Intelligent Robots
Weiqi Jin, Peijun Tang, Kuncheng Luo +5
The paper presents PHILIA, a modular multi‑robot system that separates high‑level reasoning from low‑level robot execution via a robot‑gateway interface, enabling long‑term, person…
Towards Predictive, Aligned, and Scalable Robot Learning
Peijun Tang, Shangjin Xie, Baifu Huang +6
The paper introduces Lumo-2, a latent world-action model that reasons about future physical dynamics in a shared latent space to generate robot actions, using a multi‑stage alignme…
Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage
Weiqiang Jin, Yang Liu, Shixiang Tang +5
Multi-agent reinforcement learning (MARL) has reached competitive performance on cooperative tasks against scripted adversaries, yet most methods train agents at a single fixed dif…
Mind to Hand: Purposeful Robotic Control via Embodied Reasoning
Peijun Tang, Shangjin Xie, Binyan Sun +5
Humans act with context and intention, with reasoning playing a central role. While internet-scale data has enabled broad reasoning capabilities in AI systems, grounding these abil…