← Search

Zhekai Duan

2 accepted papers

2026

Fast ECoT: Efficient Embodied Chain-Of-Thought Via Thoughts Reuse

ICRA 2026poster

Embodied Chain-of-Thought (ECoT) reasoning enhances vision-language-action (VLA) models by improving performance and interpretability through intermediate reasoning steps. However, its sequential autoregressive token generation introduces significant inference latency, limiting real-time deployment.…

2024

Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities

ECCV 2024poster

"Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce , a novel framework that bridges this gap by seamlessly integrati…