Dantong Niu

About

Dantong Niu is a rising researcher at the intersection of robotics and large language models (LLMs), with a focus on enabling embodied intelligence through in-context learning. Their most notable contribution is the introduction of **RoboPrompt**, a framework that leverages the in-context learning capabilities of LLMs to directly predict robot actions—a novel approach that bridges the gap between language understanding and physical task execution. This work, published in 2025, has already garnered early citations, signaling its growing influence in the robotics and AI communities. Niu’s research addresses a critical challenge: how to make LLMs not just conversational but actionable in real-world robotic systems. By demonstrating that LLMs can generalize to novel manipulation tasks without fine-tuning, they have opened new pathways for zero-shot robot control. Their work is particularly impactful for students and researchers exploring the synergy between foundation models and embodied AI, offering a practical blueprint for integrating language-driven reasoning into autonomous systems. With a focus on scalable, data-efficient solutions, Niu is shaping the future of human-robot collaboration.

Research Focus

Key Achievements

Top Papers

1. 1
   In-Context Learning Enables Robot Action Prediction in LLMs

   3 citations · 2025

Key Collaborators

Contact & Links