Research map / Vision-language and multimodal / Visual question answering
Extending Embodied Question Answering from Perception to Decision
Xicheng Gong, Qiwei Li, Peiran Xu, Yadong Mu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add CoT-SFT stage (ablation) | RoboDecision-8B · EQA-Decision overall | score: 54.52 -> 68.06 | Improved |
| add GRPO stage (ablation) | RoboDecision-8B · EQA-Decision overall | score: 59.85 -> 68.06 | Improved |
| add spatial data (ablation) | RoboDecision-8B · EQA-Decision overall | score: 59.16 -> 68.06 | Improved |
| add task dynamics data (ablation) | RoboDecision-8B · EQA-Decision overall | score: 60.74 -> 68.06 | Improved |
| add instant decision data (ablation) | RoboDecision-8B · EQA-Decision overall | score: 64.61 -> 68.06 | Improved |
| add static scene data (ablation) | RoboDecision-8B · EQA-Decision overall | score: 66.18 -> 68.06 | Improved |
| add instant decision data (ablation) | RoboDecision-8B · EQA-Decision Spatial-Depth | score: 71.74 -> 70.82 | No clear effect |
| add static scene data (ablation) | RoboDecision-8B · EQA-Decision Planning Reasoning | score: 65.24 -> 65.02 | No clear effect |
| train RoboDecision-8B (SFT+CoT-SFT+GRPO) from Qwen3-VL-8B-Instruct | Qwen3-VL-8B-Instruct · EQA-Decision overall | score: 48.84 -> 68.06 | Improved |
| train RoboDecision-8B on EQA-Decision | Qwen3-VL-8B-Instruct · RoboVQA / ERQA / Where2Place | BLEU-1 / accuracy: 82.34 -> 86.97 (RoboVQA BLEU-1) | Improved |
Closest papers by meaning
- OpenEQA: Embodied Question Answering in the Era of Foundation Models (CVPR 2024 · similarity 0.92)
- Multi-modal Situated Reasoning in 3D Scenes (NeurIPS 2024 · similarity 0.90)
- ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark (CVPR 2025 · similarity 0.89)
- IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios (NeurIPS 2025 · similarity 0.89)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.89)
- Embodied Scene Understanding for Vision Language Models via MetaVQA (CVPR 2025 · similarity 0.88)
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.
