Xicheng Gong

2 accepted papers

2026

Extending Embodied Question Answering from Perception to Decision

Xicheng Gong, Qiwei Li, Peiran Xu, Yadong Mu

CVPR 2026

Embodied Question Answering (EQA) connects perception, reasoning, and interaction within embodied environments. However, existing datasets and benchmarks remain fragmented, each focusing on a limited subset of reasoning skills such as spatial understanding or procedural reasoning, without offering a

Cited by 0 Source ↗Scholar ↗

2025

NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation

Peiran Xu, Xicheng Gong, Yadong Mu

ICCV 2025poster

In this work we concentrate on the task of goal-oriented Vision-and-Language Navigation (VLN). Existing methods often make decisions based on historical information, overlooking the future implications and long-term outcomes of the actions. In contrast, we aim to develop a foresighted agent. Specifi…

Cited by 0 Source ↗PDF ↗Scholar ↗