3 papers
cs.RO2026
Co-design of Neural and Muscle Network based on Embodied Perceptron Representation
Siyuan Tao, Yoichi Masuda, Hiroyuki Nabae +1
Recent advances in AI technologies have enabled the advanced design of complex control policies. In contrast, focusing on the body, many robots still employ simple bodies that can…
cs.CL2026
XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation
Qili Zhang, Qianren Mao, Yangyifei Luo +15
Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs), ensuring that the generated output…
cs.CL2026
Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric
Ruipeng Jia, Yunyi Yang, Wen Wang +7
Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to brittleness and reward hacking…