AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering

Kaixuan Jiang, Yang Liu, Weixing Chen, Jingzhou Luo, Ziliang Chen, Ling Pan, Guanbin Li, Liang Lin

ICCV 2025 · Vision-language and multimodal › Visual question answering · approach: Visual reasoning diagnostics · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add frontier-based exploration (ablation)Fine-EQA · EXPRESS-BenchC: 38.54 -> 40.55Improved
add frontier-based exploration (ablation)Fine-EQA · EXPRESS-BenchE_path: 12.74 -> 16.22Improved
add goal-oriented exploration (ablation)Fine-EQA · EXPRESS-BenchC: 39.63 -> 40.55Improved
add goal-oriented exploration (ablation)Fine-EQA · EXPRESS-BenchC*: 60.74 -> 63.95Improved
add goal-oriented exploration (ablation)Fine-EQA · EXPRESS-BenchE_path: 14.64 -> 16.22Improved
use GPT-4o-mini instead of Janus-Pro-7B as VLM (ablation)Fine-EQA · EXPRESS-BenchC: 39.88 -> 40.55Mixed
use GPT-4o-mini instead of Janus-Pro-7B as VLM (ablation)Fine-EQA · EXPRESS-BenchE_path: 20.86 -> 16.22Mixed
use GPT-4o-mini instead of Qwen-Vl-Plus as VLM (ablation)Fine-EQA · EXPRESS-BenchC: 40.02 -> 40.55Improved
replace random exploration with Fine-EQA strategyexploring agent · EXPRESS-BenchE_path: 12.06 -> 16.22Improved
replace frontier-only exploration with Fine-EQA strategyexploring agent · EXPRESS-BenchC: 38.60 -> 40.55Improved
use multiple frames directly instead of captions plus LLM (Socratic)VLM baseline · EXPRESS-BenchC*: 62.60 -> 58.37Hurt
add captioned visual frames to blind LLM DeepSeek-V3DeepSeek-V3 · EXPRESS-BenchC*: 59.15 -> 62.60Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy