4 papers
TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading
Yudong Pan, Yintao He, Tianhua Han +7
To deploy large Mixture-of-Experts (MoE) models cost-effectively, offloading-based single-GPU heterogeneous inference is crucial. While GPU-CPU architectures that offload cold expe…
ANNIE: Be Careful of Your Robots
Yiyang Huang, Zixuan Wang, Zishen Wan +4
The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric envir…
DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline
Wenhao Sun, Sai Hou, Zixuan Wang +6
Performing complex tasks in open environments remains challenging for robots, even when using large language models (LLMs) as the core planner. Many LLM-based planners are ineffici…
KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
Zixuan Wang, Bo Yu, Junzhe Zhao +6
Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in t…