# 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding

arXiv: https://arxiv.org/abs/2506.01946 · HTML: https://mlsanity.com/paper/2506.01946/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 58 of its 69 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 58)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness](https://mlsanity.com/paper/2409.18125/) (2024)
- [FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views](https://mlsanity.com/paper/2502.12138/) (2025)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)

## Built on by (most cited first, 30 of 70)

- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [A Pragmatic VLA Foundation Model](https://mlsanity.com/paper/2601.18692/) (2026)
- [Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling](https://mlsanity.com/paper/2507.07982/) (2025)
- [Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views](https://mlsanity.com/paper/2510.18632/) (2025)
- [FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction](https://mlsanity.com/paper/2509.21657/) (2025)
- [Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization](https://mlsanity.com/paper/2510.25616/) (2025)
- [Holistic Evaluation of Multimodal LLMs on Spatial Intelligence](https://mlsanity.com/paper/2508.13142/) (2025)
- [VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving](https://mlsanity.com/paper/2602.20794/) (2026)
- [SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery](https://mlsanity.com/paper/2512.07733/) (2025)
- [GLaD: Geometric Latent Distillation for Vision-Language-Action Models](https://mlsanity.com/paper/2512.09619/) (2025)
- [ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models](https://mlsanity.com/paper/2602.17951/) (2026)
- [Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps](https://mlsanity.com/paper/2601.11442/) (2026)
- [Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding](https://mlsanity.com/paper/2603.19235/) (2026)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning](https://mlsanity.com/paper/2506.09935/) (2025)
- [Vision-Language Memory for Spatial Reasoning](https://mlsanity.com/paper/2511.20644/) (2025)
- [AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment](https://mlsanity.com/paper/2605.17517/) (2026)
- [LARA: Latent Action Representation Alignment for Vision-Language-Action Models](https://mlsanity.com/paper/2606.07100/) (2026)
- [OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning](https://mlsanity.com/paper/2509.09332/) (2025)
- [Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy](https://mlsanity.com/paper/2509.24385/) (2025)
- [Unlocking Dense Metric Depth Estimation in VLMs](https://mlsanity.com/paper/2605.15876/) (2026)
- [Vision-Centric Activation and Coordination for Multimodal Large Language Models](https://mlsanity.com/paper/2510.14349/) (2025)
- [Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling](https://mlsanity.com/paper/2512.01821/) (2025)
- [From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models](https://mlsanity.com/paper/2602.08735/) (2026)
- [EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs](https://mlsanity.com/paper/2604.03318/) (2026)
- [OpenWorldLib: A Unified Codebase and Definition of Advanced World Models](https://mlsanity.com/paper/2604.04707/) (2026)
- [Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views](https://mlsanity.com/paper/2606.23557/) (2026)
- [Reg3D: Reconstructive Geometry Instruction Tuning for 3D Scene Understanding](https://mlsanity.com/paper/2509.03635/) (2025)
- [4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation](https://mlsanity.com/paper/2512.17012/) (2025)
- [MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation](https://mlsanity.com/paper/2602.07082/) (2026)

## Abstract (arXiv)

Recent advances in scene understanding have leveraged multimodal large language models (MLLMs) for 3D reasoning by capitalizing on their strong 2D pretraining. However, the lack of explicit 3D data during MLLM pretraining limits 3D representation capability. In this paper, we investigate the 3D-awareness of MLLMs by evaluating multi-view correspondence and reveal a strong positive correlation between the quality of 3D-aware representation and downstream task performance. Motivated by this, we propose 3DRS, a framework that enhances MLLM 3D representation learning by introducing supervision from pretrained 3D foundation models. Our approach aligns MLLM visual features with rich 3D knowledge distilled from 3D models, effectively improving scene understanding. Extensive experiments across multiple benchmarks and MLLMs -- including visual grounding, captioning, and question answering -- demonstrate consistent performance gains. Project page: https://visual-ai.github.io/3drs