# Embodied and 3D vision-language models

Area: [Multimodal LLMs / vision-language models](https://mlsanity.com/mllm/index.md). HTML: https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/

## Key facts

- Embodied and 3D vision-language models: 2,288 papers on arXiv since 2021 (data through 14 Oct 2026).
- 256 of its 2,288 mapped papers (11%) cite “SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities” (2024, arXiv 2401.12168).
- 190 of its 2,288 mapped papers (8%) cite “Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces” (2024, arXiv 2412.14171).
- 125 new papers 17 Sep–14 Oct.

## Most cited here

- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024), cited by 256 papers here
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024), cited by 190 papers here
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024), cited by 161 papers here
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023), cited by 157 papers here
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023), cited by 148 papers here
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025), cited by 119 papers here
- [3D-LLM: Injecting the 3D World into Large Language Models](https://mlsanity.com/paper/2307.12981/) (2023), cited by 117 papers here
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025), cited by 105 papers here
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023), cited by 102 papers here
- [SpatialBot: Precise Spatial Understanding with Vision Language Models](https://mlsanity.com/paper/2406.13642/) (2024), cited by 84 papers here

## New (17 Sep–14 Oct)

- [Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models](https://mlsanity.com/paper/2610.20989/) (2026-10-14)
- [GeoThinker-F: Endogenous Predictive World Representations for Fast Spatial Intelligence](https://mlsanity.com/paper/2610.20592/) (2026-10-14)
- [Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence](https://mlsanity.com/paper/2610.20312/) (2026-10-14)
- [Integrating Simulation and Chain-of-thought Reasoning in Multimodal-Language Models For Physical Reasoning](https://mlsanity.com/paper/2610.19441/) (2026-10-14)
- [Write Once, Plan Many: Building Reusable Visual Planning Systems from One Scene](https://mlsanity.com/paper/2610.19234/) (2026-10-13)
- [Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2610.19108/) (2026-10-13)
- [The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding](https://mlsanity.com/paper/2610.19102/) (2026-10-13)
- [Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?](https://mlsanity.com/paper/2610.18836/) (2026-10-13)
- [Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?](https://mlsanity.com/paper/2610.18834/) (2026-10-13)
- [GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2610.18694/) (2026-10-13)
- [MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation](https://mlsanity.com/paper/2610.18478/) (2026-10-13)
- [ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensing](https://mlsanity.com/paper/2610.18388/) (2026-10-13)
- [Learning How to Remember: Memory Modality Selection for GUI Agents](https://mlsanity.com/paper/2610.17928/) (2026-10-13)
- [What Makes a Good Visual Representation for Spatial Understanding in MLLMs?](https://mlsanity.com/paper/2610.17844/) (2026-10-13)
- [RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment](https://mlsanity.com/paper/2610.17665/) (2026-10-13)
- [From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction](https://mlsanity.com/paper/2610.17630/) (2026-10-13)
- [Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?](https://mlsanity.com/paper/2610.17350/) (2026-10-12)
- [Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models](https://mlsanity.com/paper/2610.16769/) (2026-10-12)
- [PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation](https://mlsanity.com/paper/2610.16355/) (2026-10-12)
- [ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning](https://mlsanity.com/paper/2610.16315/) (2026-10-12)
- [Geometric Parrots: Rule Absence vs. Rule Fragility in Spatial and Physical Reasoning for Vision-Language Models](https://mlsanity.com/paper/2610.16170/) (2026-10-12)
- [SurgiCLAW: An Interpretable Atomic-Skill Agent for Precision Robotic Micromanipulation](https://mlsanity.com/paper/2610.15766/) (2026-10-11)
- [PRISM: Precision Forcing for Generalist Vision-Language-Action Policies](https://mlsanity.com/paper/2610.14704/) (2026-10-10)
- [GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models](https://mlsanity.com/paper/2610.14541/) (2026-10-10)
- [SceneForesee: Learning Scene Evolution for Spatiotemporal Reasoning](https://mlsanity.com/paper/2610.14439/) (2026-10-10)
- [RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work](https://mlsanity.com/paper/2610.14397/) (2026-10-09)
- [CoPlanVLM: Coordinated Path Planning for a Robot Team using Vision Language Models](https://mlsanity.com/paper/2610.14341/) (2026-10-09)
- [S-Space: Exploring Spatial Workspace in Multimodal Language Models](https://mlsanity.com/paper/2610.13527/) (2026-10-09)
- [Forward Dynamics Models](https://mlsanity.com/paper/2610.13117/) (2026-10-09)
- [VLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space Grounding](https://mlsanity.com/paper/2610.12832/) (2026-10-09)