kaihui.wang — accepted AI-conference papers

2026

MapDream: Task-Driven Map Learning for Vision-Language Navigation

Guoxin Lian, Shuo Wang, Yucheng Wang, Yongcai Wang, Maiyue Chen, kaihui.wang +4

ICML 2026poster

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing approaches rely on hand-crafted maps constructed independently…

Cited by 0 Source ↗Scholar ↗

2025

Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation

Shuo Wang, Yongcai Wang, Wanting Li, Xudong Cai, Yucheng Wang, Maiyue Chen +4

NeurIPS 2025poster

Vision-Language Navigation is a critical task for developing embodied agents that can follow natural language instructions to navigate in complex real-world environments. Recent advances by finetuning large pretrained models have significantly improved generalization and instruction grounding compa…

Cited by 0 Source ↗Scholar ↗