5 papers
Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning
Jinhu Qi, Minda Hu, Wentao Zhang +4
Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output schema for a series of questio…
A Glimpse into Long-term Physical Coexistence with Intelligent Robots
Weiqi Jin, Peijun Tang, Kuncheng Luo +5
Long-term physical coexistence with intelligent robots requires more than capable robot policies. A persistent robotic assistant must support diverse user-facing interfaces, mainta…
Towards Predictive, Aligned, and Scalable Robot Learning
Peijun Tang, Shangjin Xie, Baifu Huang +6
Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities. We introduce Lumo-2, a latent world-act…
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…
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…