Yike Wu
Papers
2
Total Citations
17
H-Index
2
About
Yike Wu is a rising researcher at the forefront of integrating large language models (LLMs) with robotic task planning, a field poised to redefine autonomous systems. Their key research areas center on multi-level decomposition and complex long-horizon planning, addressing a critical bottleneck in robotics: breaking down intricate, multi-step tasks into manageable subtasks that open-source LLMs can reliably execute. Wu’s major contribution, the MLDT (Multi-Level Decomposition for Task Planning) framework, introduces a hierarchical approach that enables open-source LLMs to tackle problems previously reserved for proprietary models, democratizing access to advanced AI-driven robotics. This work has already garnered over 17 citations in its first year, signaling rapid adoption by the community. Notably, Wu’s research bridges the gap between theoretical AI and practical robotics, offering a scalable solution for real-world applications like warehouse automation and domestic assistance. By leveraging open-source models, Wu not only reduces dependency on costly proprietary systems but also fosters reproducibility and collaboration. For students and researchers, Wu’s work exemplifies how innovative decomposition strategies can unlock the full potential of LLMs in robotics, making complex task planning more accessible and efficient.
Research Focus
Key Achievements
Top Papers
- 1
- 2