# GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond

arXiv: https://arxiv.org/abs/2507.00886 · HTML: https://mlsanity.com/paper/2507.00886/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 46 of its 65 references that are in the map.
- First posted on arXiv 1 Jul 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 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [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)
- [Deep Modular Co-Attention Networks for Visual Question Answering](https://mlsanity.com/paper/1906.10770/) (2019)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023)
- [TidyBot: Personalized Robot Assistance with Large Language Models](https://mlsanity.com/paper/2305.05658/) (2023)
- [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)

## Built on by (most cited first, 12 of 12)

- [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://mlsanity.com/paper/2507.23478/) (2025)
- [GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation](https://mlsanity.com/paper/2512.23180/) (2025)
- [NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction](https://mlsanity.com/paper/2512.01550/) (2025)
- [Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding](https://mlsanity.com/paper/2512.17817/) (2025)
- [SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion](https://mlsanity.com/paper/2508.02261/) (2025)
- [LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2604.01388/) (2026)
- [Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors](https://mlsanity.com/paper/2606.30638/) (2026)
- [TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving](https://mlsanity.com/paper/2605.27038/) (2026)
- [GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2608.14986/) (2026)
- [GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation](https://mlsanity.com/paper/2608.16234/) (2026)
- [GraphWrit3R: End-to-End 3D Scene Graph Writing](https://mlsanity.com/paper/2609.31595/) (2026)
- [Task-Adaptive Grounded 3D-Programmers Using 2D VLMs](https://mlsanity.com/paper/2610.02021/) (2026)

## Abstract (arXiv)

As multimodal language models advance, their application to 3D scene understanding is a fast-growing frontier, driving the development of 3D Vision-Language Models (VLMs). Current methods show strong dependence on object detectors, introducing processing bottlenecks and limitations in taxonomic flexibility. To address these limitations, we propose a scene-centric 3D VLM for 3D Gaussian splat scenes that employs language- and task-aware scene representations. Our approach directly embeds rich linguistic features into the 3D scene representation by associating language with each Gaussian primitive, achieving early modality alignment. To process the resulting dense representations, we introduce a dual sparsifier that distills them into compact, task-relevant tokens via task-guided and location-guided pathways, producing sparse, task-aware global and local scene tokens. Notably, we present the first Gaussian splatting-based VLM, leveraging photorealistic 3D representations derived from standard RGB images, demonstrating strong generalization: it improves performance of prior 3D VLM five folds, in out-of-the-domain settings.