# 3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering

arXiv: https://arxiv.org/abs/2507.12026 · HTML: https://mlsanity.com/paper/2507.12026/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation](https://mlsanity.com/paper/2504.12636/) (2025)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding](https://mlsanity.com/paper/2401.03201/) (2024)
- [Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks](https://mlsanity.com/paper/2405.18831/) (2024)
- [RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation](https://mlsanity.com/paper/2505.01709/) (2025)
- [PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly](https://mlsanity.com/paper/2506.08708/) (2025)
- [InstruGen: Automatic Instruction Generation for Vision-and-Language Navigation Via Large Multimodal Models](https://mlsanity.com/paper/2411.11394/) (2024)
- [Generating Context-Aware Natural Answers for Questions in 3D Scenes](https://mlsanity.com/paper/2310.19516/) (2023)
- [AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge](https://mlsanity.com/paper/2406.19271/) (2024)

## Built on by (most cited first, 5 of 5)

- [A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model](https://mlsanity.com/paper/2604.05672/) (2026)
- [SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition](https://mlsanity.com/paper/2509.25723/) (2025)
- [Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion](https://mlsanity.com/paper/2510.13198/) (2025)
- [CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs](https://mlsanity.com/paper/2609.08345/) (2026)
- [GeoThinker-F: Endogenous Predictive World Representations for Fast Spatial Intelligence](https://mlsanity.com/paper/2610.20592/) (2026)

## Abstract (arXiv)

With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generate large-scale 3D-language datasets by leveraging the strengths of foundational models. The framework integrates key components, including multi-modal embedding, cross-modal interaction, and a language model decoder, to process natural language instructions and 3D scene data. This approach facilitates enhanced reasoning and response generation in complex 3D environments. Using the ScanNet 3D scene dataset, along with text annotations from ScanQA and ScanRefer, 3D-MoRe generates 62,000 question-answer (QA) pairs and 73,000 object descriptions across 1,513 scenes. We also employ various data augmentation techniques and implement semantic filtering to ensure high-quality data. Experiments on ScanQA demonstrate that 3D-MoRe significantly outperforms state-of-the-art baselines, with the CIDEr score improving by 2.15%. Similarly, on ScanRefer, our approach achieves a notable increase in CIDEr@0.5 by 1.84%, highlighting its effectiveness in both tasks. Our code and generated datasets will be publicly released to benefit the community, and both can be accessed on the https://3D-MoRe.github.io.