---
title: "SceneLM — paper by Yao et al. (2026) — summary and ideas"
description: "SceneLM addresses the problem of building an editable 3D scene from one RGB image. 38 references."
authors: ["Xingbo Yao", "Xiaoyu Chen", "Doudou Zhang", "Mingzhi Sheng", "Boyuan Cao", "Ying-Cong Chen", "Hui Xiong"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.2116/"
doi: "10.18653/v1/2026.findings-acl.2116"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yao-2026-scenelm-3d-aware-language-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yao-2026-scenelm-3d-aware-language-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/48/) / SceneLM: 3D-Aware Language Models for Editable 3D Scene Synthesis

# SceneLM: 3D-Aware Language Models for Editable 3D Scene Synthesis

**Authors:** Xingbo Yao, Xiaoyu Chen, Doudou Zhang, Mingzhi Sheng, Boyuan Cao, [Ying-Cong Chen](https://md.research.elamur.ai/free/en/authors/ying-cong-chen/) and [Hui Xiong](https://md.research.elamur.ai/free/en/authors/hui-xiong/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.2116/) · [PDF](https://aclanthology.org/2026.findings-acl.2116.pdf) · [DOI 10.18653/v1/2026.findings-acl.2116](https://doi.org/10.18653/v1/2026.findings-acl.2116) · [OpenAlex](https://openalex.org/W7166891470)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
SceneLM addresses the problem of building an editable 3D scene from one RGB image. Geometry-based pipelines give good quality but usually have to be rerun to fix errors. LLM tool-using systems are interactive but work mainly from text and lack metric 3D understanding. SceneLM reframes the task as two steps. First, a vision-language model reads the image, plus camera intrinsics when available, and writes a JSON layout. For each object it gives the category, 3D center and size in millimetres, and a yaw value discretized into 15° bins. Second, a deterministic tool suite turns this layout into an actual scene. Users edit by changing layout fields and re-running only the affected tool calls.

The model combines a SigLIP-2 encoder, a Qwen 2B-scale LLM and an extra geometry head. It is trained with a mix of token cross-entropy and a geometric loss, on five curated indoor, outdoor and tabletop datasets converted into one instruction-tuning format. The authors report better layout estimation than open and proprietary MLLMs, and more complete, physically plausible generated scenes.

## Key points
- **Output format:** a JSON list of objects, each with class, center_mm, size_mm and yaw_bin. Yaw is treated as a 24-way classification target.
- **Ablation results** (1,000 test images, F1 at 3D IoU 0.25 / 0.5):
  - Full SceneLM: 58.5 / 36.1
  - Without GeomHead and dual supervision: 47.6 / 28.4
  - Without yaw discretization: 44.1 / 25.1
  - Plain Qwen3-VL-2B trained only with JSON cross-entropy: 18.2 / 12.4
- **Fine-tuning:** full fine-tuning (58.5 / 36.1) beats LoRA (51.3 / 32.7).
- **Scene generation versus SceneGen:**
  - SceneLM's collided-pairs rate is 0.37, versus 0.23 for SceneGen.
  - SceneGen's lower rate comes partly from producing fewer objects and dropping small items.
  - Qwen3-VL-30B-A3B-Instruct, run through the same tools, often produced incomplete JSON and boxes with wrong scale.
- **Limitations:**
  - When intrinsics are missing, default values are used, which can skew absolute scale.
  - Output quality depends on the external asset generator.
  - In complex scenes the model may still emit invalid or incomplete JSON.
  - Planned future work includes export to Habitat.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/) — University, Shanghai, China · 202 works · 22,509 citations
- [Hong Kong University of Science and Technology](https://md.research.elamur.ai/free/en/universities/hong-kong-university-of-science-and-technology/) — University, Hong Kong, China · 170 works · 26,341 citations
- [The Hong Kong University of Science and Technology (Guangzhou)](https://md.research.elamur.ai/free/en/universities/the-hong-kong-university-of-science-and-technology-guangzhou/) — University, Guangzhou, China · 67 works · 1,765 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 188 works · [⚙️ Computational Mechanics](https://md.research.elamur.ai/free/en/shelves/engineering/computational-mechanics/) · 5 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Xingbo Yao, Xiaoyu Chen, Doudou Zhang, Mingzhi Sheng, Boyuan Cao, Ying-Cong Chen and Hui Xiong. 2026. SceneLM: 3D-Aware Language Models for Editable 3D Scene Synthesis. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yao2026scenelm,
  title = {{SceneLM: 3D-Aware Language Models for Editable 3D Scene Synthesis}},
  author = {Xingbo Yao, Xiaoyu Chen, Doudou Zhang, Mingzhi Sheng, Boyuan Cao, Ying-Cong Chen and Hui Xiong},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2116},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2116}
}
```

- [← previous SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes](https://md.research.elamur.ai/free/en/papers/wang-2026-scenealign-aligning-multimodal-reasoning-scene/)
- [next → SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases](https://md.research.elamur.ai/free/en/papers/safdarian-2026-schemagraphsql-efficient-schema-linking-pathfinding/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/48/)

## References

38 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Adel Ahmadyan, Liangkai Zhang, Artsiom Ablavatski, Jianing Wei, and Matthias Grundmann. 2021. Objectron: A large scale dataset of object-centric videos in the wild with pose annotations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7822–7831. [find](https://scholar.google.com/scholar?q=Adel+Ahmadyan%2C+Liangkai+Zhang%2C+Artsiom+Ablavatski%2C+Jianing+Wei%2C+and+Matthias+Grundmann%2E+2021%2E+Objectron%3A+A+large+scale+dataset+of+object%2Dcentric+videos+in+the+wild+with+pose+annotations%2E+In+Proceeding)
2. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, and 1 others. 2023. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609.
3. Gilad Baruch, Zhuoyuan Chen, Afshin Dehghan, Tal Dimry, Yuri Feigin, Peter Fu, Thomas Gebauer, Brandon Joffe, Daniel Kurz, Arik Schwartz, and 1 others. 2021. Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data. arXiv preprint arXiv:2111.08897. — [arXiv:2111.08897](https://arxiv.org/abs/2111.08897) [find](https://scholar.google.com/scholar?q=Gilad+Baruch%2C+Zhuoyuan+Chen%2C+Afshin+Dehghan%2C+Tal+Dimry%2C+Yuri+Feigin%2C+Peter+Fu%2C+Thomas+Gebauer%2C+Brandon+Joffe%2C+Daniel+Kurz%2C+Arik+Schwartz%2C+and+1+others%2E+2021%2E+Arkitscenes%3A+A+diverse+real%2Dworld+dataset+)
4. Aleksey Bokhovkin, Quan Meng, Shubham Tulsiani, and Angela Dai. 2025. Scenefactor: Factored latent 3d diffusion for controllable 3d scene generation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 628–639. [find](https://scholar.google.com/scholar?q=Aleksey+Bokhovkin%2C+Quan+Meng%2C+Shubham+Tulsiani%2C+and+Angela+Dai%2E+2025%2E+Scenefactor%3A+Factored+latent+3d+diffusion+for+controllable+3d+scene+generation%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+)
5. Garrick Brazil, Abhinav Kumar, Julian Straub, Nikhila Ravi, Justin Johnson, and Georgia Gkioxari. 2023. Omni3d: A large benchmark and model for 3d object detection in the wild. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13154–13164. [find](https://scholar.google.com/scholar?q=Garrick+Brazil%2C+Abhinav+Kumar%2C+Julian+Straub%2C+Nikhila+Ravi%2C+Justin+Johnson%2C+and+Georgia+Gkioxari%2E+2023%2E+Omni3d%3A+A+large+benchmark+and+model+for+3d+object+detection+in+the+wild%2E+In+Proceedings+of+the+I)
6. Martin J.J. Bucher and Iro Armeni. 2025. Respace: Text-driven 3d indoor scene synthesis and editing with preference alignment. arXiv preprint arXiv:2506.02459. — [arXiv:2506.02459](https://arxiv.org/abs/2506.02459) [find](https://scholar.google.com/scholar?q=Martin+J%2EJ%2E+Bucher+and+Iro+Armeni%2E+2025%2E+Respace%3A+Text%2Ddriven+3d+indoor+scene+synthesis+and+editing+with+preference+alignment%2E+arXiv+preprint+arXiv%3A2506%2E02459%2E+%E2%80%94+%5BarXiv%3A2506%2E02459%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
7. Jang Hyun Cho, B. Ivanovic, Yulong Cao, Edward Schmerling, Yue Wang, Xinshuo Weng, Boyi Li, Yurong You, Philipp Krahenbuhl, Yan Wang, and Marco Pavone. 2024. Language-image models with 3d understanding. arXiv preprint arXiv:2405.03685. — [arXiv:2405.03685](https://arxiv.org/abs/2405.03685) [find](https://scholar.google.com/scholar?q=Jang+Hyun+Cho%2C+B%2E+Ivanovic%2C+Yulong+Cao%2C+Edward+Schmerling%2C+Yue+Wang%2C+Xinshuo+Weng%2C+Boyi+Li%2C+Yurong+You%2C+Philipp+Krahenbuhl%2C+Yan+Wang%2C+and+Marco+Pavone%2E+2024%2E+Language%2Dimage+models+with+3d+understandin)
8. Wei Deng, Mengshi Qi, and Huadong Ma. 2025. Global-local tree search in vlms for 3d indoor scene generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8975–8984. [find](https://scholar.google.com/scholar?q=Wei+Deng%2C+Mengshi+Qi%2C+and+Huadong+Ma%2E+2025%2E+Global%2Dlocal+tree+search+in+vlms+for+3d+indoor+scene+generation%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29)
9. Chuan Fang, Heng Li, Yixun Liang, Jia Zheng, Yongsen Mao, Yuan Liu, Rui Tang, Zihan Zhou, and Ping Tan. 2025. Spatialgen: Layout-guided 3d indoor scene generation. arXiv preprint arXiv:2509.14981. — [arXiv:2509.14981](https://arxiv.org/abs/2509.14981) [find](https://scholar.google.com/scholar?q=Chuan+Fang%2C+Heng+Li%2C+Yixun+Liang%2C+Jia+Zheng%2C+Yongsen+Mao%2C+Yuan+Liu%2C+Rui+Tang%2C+Zihan+Zhou%2C+and+Ping+Tan%2E+2025%2E+Spatialgen%3A+Layout%2Dguided+3d+indoor+scene+generation%2E+arXiv+preprint+arXiv%3A2509%2E14981%2E+%E2%80%94+%5B)
10. Weitao Feng, Hang Zhou, Jing Liao, Li Cheng, and Wenbo Zhou. 2025. Casagpt: cuboid arrangement and scene assembly for interior design. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 29173–29182. [find](https://scholar.google.com/scholar?q=Weitao+Feng%2C+Hang+Zhou%2C+Jing+Liao%2C+Li+Cheng%2C+and+Wenbo+Zhou%2E+2025%2E+Casagpt%3A+cuboid+arrangement+and+scene+assembly+for+interior+design%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+Recognition+Con)
11. Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. 2013. Vision meets robotics: The kitti dataset. The international journal of robotics research, 32(11):1231–1237. [find](https://scholar.google.com/scholar?q=Andreas+Geiger%2C+Philip+Lenz%2C+Christoph+Stiller%2C+and+Raquel+Urtasun%2E+2013%2E+Vision+meets+robotics%3A+The+kitti+dataset%2E+The+international+journal+of+robotics+research%2C+32%2811%29%3A1231%E2%80%931237%2E)
12. Jinkun Hao, Naifu Liang, Zhen Luo, Xudong Xu, Weipeng Zhong, Ran Yi, Yichen Jin, Zhaoyang Lyu, Feng Zheng, Lizhuang Ma, and Jiangmiao Pang. 2025. Mesatask: Towards task-driven tabletop scene generation via 3d spatial reasoning. arXiv preprint arXiv:2509.22281. — [arXiv:2509.22281](https://arxiv.org/abs/2509.22281) [find](https://scholar.google.com/scholar?q=Jinkun+Hao%2C+Naifu+Liang%2C+Zhen+Luo%2C+Xudong+Xu%2C+Weipeng+Zhong%2C+Ran+Yi%2C+Yichen+Jin%2C+Zhaoyang+Lyu%2C+Feng+Zheng%2C+Lizhuang+Ma%2C+and+Jiangmiao+Pang%2E+2025%2E+Mesatask%3A+Towards+task%2Ddriven+tabletop+scene+generatio)
13. Xiaolu Hou, Mingcheng Li, Dingkang Yang, Jiawei Chen, Ziyun Qian, Xiao Zhao, Yue Jiang, Jinjie Wei, Qingyao Xu, and Lihua Zhang. 2025. Bloomscene: Lightweight structured 3d gaussian splatting for crossmodal scene generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39… [find](https://scholar.google.com/scholar?q=Xiaolu+Hou%2C+Mingcheng+Li%2C+Dingkang+Yang%2C+Jiawei+Chen%2C+Ziyun+Qian%2C+Xiao+Zhao%2C+Yue+Jiang%2C+Jinjie+Wei%2C+Qingyao+Xu%2C+and+Lihua+Zhang%2E+2025%2E+Bloomscene%3A+Lightweight+structured+3d+gaussian+splatting+for+cros)
14. Yukun Huang, Yanning Zhou, Jianan Wang, Kaiyi Huang, and Xihui Liu. 2025. Dreamcube: 3d panorama generation via multi-plane synchronization. [find](https://scholar.google.com/scholar?q=Yukun+Huang%2C+Yanning+Zhou%2C+Jianan+Wang%2C+Kaiyi+Huang%2C+and+Xihui+Liu%2E+2025%2E+Dreamcube%3A+3d+panorama+generation+via+multi%2Dplane+synchronization%2E)
15. Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Philipp Henzler, Konrad Schindler, and Federico Tombari. 2025. Cubediff: Repurposing diffusion-based image models for panorama generation. [find](https://scholar.google.com/scholar?q=Nikolai+Kalischek%2C+Michael+Oechsle%2C+Fabian+Manhardt%2C+Philipp+Henzler%2C+Konrad+Schindler%2C+and+Federico+Tombari%2E+2025%2E+Cubediff%3A+Repurposing+diffusion%2Dbased+image+models+for+panorama+generation%2E)
16. Yuheng Liu, Xinke Li, Yuning Zhang, Lu Qi, Xin Li, Wenping Wang, Chongshou Li, Xueting Li, and Ming-Hsuan Yang. 2025. Controllable 3d outdoor scene generation via scene graphs. arXiv preprint arXiv:2503.07152. — [arXiv:2503.07152](https://arxiv.org/abs/2503.07152) [find](https://scholar.google.com/scholar?q=Yuheng+Liu%2C+Xinke+Li%2C+Yuning+Zhang%2C+Lu+Qi%2C+Xin+Li%2C+Wenping+Wang%2C+Chongshou+Li%2C+Xueting+Li%2C+and+Ming%2DHsuan+Yang%2E+2025%2E+Controllable+3d+outdoor+scene+generation+via+scene+graphs%2E+arXiv+preprint+arXiv%3A25)
17. Yunze Man, Shihao Wang, Guowen Zhang, Johan Bjorck, Zhiqi Li, Liang-Yan Gui, Jim Fan, Jan Kautz, Yu-Xiong Wang, and Zhiding Yu. 2025. Locateany-thing3d: Vision-language 3d detection with chain-of-sight. arXiv preprint arXiv:2511.20648. — [arXiv:2511.20648](https://arxiv.org/abs/2511.20648) [find](https://scholar.google.com/scholar?q=Yunze+Man%2C+Shihao+Wang%2C+Guowen+Zhang%2C+Johan+Bjorck%2C+Zhiqi+Li%2C+Liang%2DYan+Gui%2C+Jim+Fan%2C+Jan+Kautz%2C+Yu%2DXiong+Wang%2C+and+Zhiding+Yu%2E+2025%2E+Locateany%2Dthing3d%3A+Vision%2Dlanguage+3d+detection+with+chain%2Dof%2Dsigh)
18. Yongsen Mao, Junhao Zhong, Chuan Fang, Jia Zheng, Rui Tang, Hao Zhu, Ping Tan, and Zihan Zhou. 2025. Spatiallm: Training large language models for structured indoor modeling. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Yongsen+Mao%2C+Junhao+Zhong%2C+Chuan+Fang%2C+Jia+Zheng%2C+Rui+Tang%2C+Hao+Zhu%2C+Ping+Tan%2C+and+Zihan+Zhou%2E+2025%2E+Spatiallm%3A+Training+large+language+models+for+structured+indoor+modeling%2E+In+Advances+in+Neural+Inf)
19. Yanxu Meng, Haoning Wu, Ya Zhang, and Weidi Xie. 2026. Scenegen: Single-image 3d scene generation in one feedforward pass. In International Conference on 3D Vision 2026. [find](https://scholar.google.com/scholar?q=Yanxu+Meng%2C+Haoning+Wu%2C+Ya+Zhang%2C+and+Weidi+Xie%2E+2026%2E+Scenegen%3A+Single%2Dimage+3d+scene+generation+in+one+feedforward+pass%2E+In+International+Conference+on+3D+Vision+2026%2E)
20. Mike Roberts, Jason Ramapuram, Anurag Ranjan, At-ulit Kumar, Miguel Angel Bautista, Nathan Paczan, Russ Webb, and Joshua M Susskind. 2021. Hypersim: A photorealistic synthetic dataset for holistic indoor scene understanding. In Proceedings of the IEEE/CVF international conference on computer vision,… [find](https://scholar.google.com/scholar?q=Mike+Roberts%2C+Jason+Ramapuram%2C+Anurag+Ranjan%2C+At%2Dulit+Kumar%2C+Miguel+Angel+Bautista%2C+Nathan+Paczan%2C+Russ+Webb%2C+and+Joshua+M+Susskind%2E+2021%2E+Hypersim%3A+A+photorealistic+synthetic+dataset+for+holistic+ind)
21. Katja Schwarz, Denis Rozumny, Samuel Rota Bulò, Lorenzo Porzi, and Peter Kontschieder. 2025. A recipe for generating 3d worlds from a single image. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3520–3530. [find](https://scholar.google.com/scholar?q=Katja+Schwarz%2C+Denis+Rozumny%2C+Samuel+Rota+Bul%C3%B2%2C+Lorenzo+Porzi%2C+and+Peter+Kontschieder%2E+2025%2E+A+recipe+for+generating+3d+worlds+from+a+single+image%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Confere)
22. Shuran Song, Samuel P Lichtenberg, and Jianxiong Xiao. 2015. Sun rgb-d: A rgb-d scene understanding benchmark suite. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 567–576. [find](https://scholar.google.com/scholar?q=Shuran+Song%2C+Samuel+P+Lichtenberg%2C+and+Jianxiong+Xiao%2E+2015%2E+Sun+rgb%2Dd%3A+A+rgb%2Dd+scene+understanding+benchmark+suite%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition%2C+p)
23. SongTang SongTang, Kaiyong Zhao, Lei Wang, Yuliang Li, Xuebo Liu, Junyi Zou, Qiang Wang, and Xiaowen Chu. 2025. Unrealllm: Towards highly controllable and interactable 3d scene generation by llm-powered procedural content generation. In Findings of the Association for Computational Linguistics: ACL… [find](https://scholar.google.com/scholar?q=SongTang+SongTang%2C+Kaiyong+Zhao%2C+Lei+Wang%2C+Yuliang+Li%2C+Xuebo+Liu%2C+Junyi+Zou%2C+Qiang+Wang%2C+and+Xiaowen+Chu%2E+2025%2E+Unrealllm%3A+Towards+highly+controllable+and+interactable+3d+scene+generation+by+llm%2Dpower)
24. Fan-Yun Sun, Shengguang Wu, Christian Jacobsen, Thomas Yim, Haoming Zou, Alex Zook, Shangru Li, Yu-Hsin Chou, Ethem Can, Xunlei Wu, and 1 others. 2025a. 3d-generalist: Self-improving vision-language-action models for crafting 3d worlds. arXiv preprint arXiv:2507.06484. — [arXiv:2507.06484](https://arxiv.org/abs/2507.06484) [find](https://scholar.google.com/scholar?q=Fan%2DYun+Sun%2C+Shengguang+Wu%2C+Christian+Jacobsen%2C+Thomas+Yim%2C+Haoming+Zou%2C+Alex+Zook%2C+Shangru+Li%2C+Yu%2DHsin+Chou%2C+Ethem+Can%2C+Xunlei+Wu%2C+and+1+others%2E+2025a%2E+3d%2Dgeneralist%3A+Self%2Dimproving+vision%2Dlanguage%2Da)
25. Weilin Sun, Xinran Li, Manyi Li, Kai Xu, Xiangxu Meng, and Lei Meng. 2025b. Hierarchically-structured open-vocabulary indoor scene synthesis with pre-trained large language model. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 7122–7130. [find](https://scholar.google.com/scholar?q=Weilin+Sun%2C+Xinran+Li%2C+Manyi+Li%2C+Kai+Xu%2C+Xiangxu+Meng%2C+and+Lei+Meng%2E+2025b%2E+Hierarchically%2Dstructured+open%2Dvocabulary+indoor+scene+synthesis+with+pre%2Dtrained+large+language+model%2E+In+Proceedings+of+th)
26. Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, and 1 others. 2025. [Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense feat…](https://md.research.elamur.ai/free/en/papers/tschannen-2025-siglip-2-multilingual-vision-language/)
27. Xiping Wang, Yuxi Wang, Mengqi Zhou, Junsong Fan, and Zhaoxiang Zhang. 2025a. Hlg: Comprehensive 3d room construction via hierarchical layout generation. arXiv preprint arXiv:2508.17832. — [arXiv:2508.17832](https://arxiv.org/abs/2508.17832) [find](https://scholar.google.com/scholar?q=Xiping+Wang%2C+Yuxi+Wang%2C+Mengqi+Zhou%2C+Junsong+Fan%2C+and+Zhaoxiang+Zhang%2E+2025a%2E+Hlg%3A+Comprehensive+3d+room+construction+via+hierarchical+layout+generation%2E+arXiv+preprint+arXiv%3A2508%2E17832%2E+%E2%80%94+%5BarXiv%3A2508)
28. Yuxin Wang, Lei Ke, Boqiang Zhang, Tianyuan Qu, Hanxun Yu, Zhenpeng Huang, Meng Yu, Dan Xu, and Dong Yu. 2025b. N3d-vlm: Native 3d grounding enables accurate spatial reasoning in vision-language models. arXiv preprint arXiv:2512.16561. — [arXiv:2512.16561](https://arxiv.org/abs/2512.16561) [find](https://scholar.google.com/scholar?q=Yuxin+Wang%2C+Lei+Ke%2C+Boqiang+Zhang%2C+Tianyuan+Qu%2C+Hanxun+Yu%2C+Zhenpeng+Huang%2C+Meng+Yu%2C+Dan+Xu%2C+and+Dong+Yu%2E+2025b%2E+N3d%2Dvlm%3A+Native+3d+grounding+enables+accurate+spatial+reasoning+in+vision%2Dlanguage+model)
29. Yuanbo Yang, Yujun Shen, Yue Wang, Andreas Geiger, and Yiyi Liao. 2025c. Urbangen: Urban generation with compositional and controllable neural fields. IEEE Transactions on Pattern Analysis and Machine Intelligence. [find](https://scholar.google.com/scholar?q=Yuanbo+Yang%2C+Yujun+Shen%2C+Yue+Wang%2C+Andreas+Geiger%2C+and+Yiyi+Liao%2E+2025c%2E+Urbangen%3A+Urban+generation+with+compositional+and+controllable+neural+fields%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine)
30. Zhifei Yang, Keyang Lu, Chao Zhang, Jiaxing Qi, Hanqi Jiang, Ruifei Ma, Shenglin Yin, Yifan Xu, Mingzhe Xing, Zhen Xiao, and 1 others. 2025d. Mmgdreamer: Mixed-modality graph for geometry-controllable 3d indoor scene generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volum… [find](https://scholar.google.com/scholar?q=Zhifei+Yang%2C+Keyang+Lu%2C+Chao+Zhang%2C+Jiaxing+Qi%2C+Hanqi+Jiang%2C+Ruifei+Ma%2C+Shenglin+Yin%2C+Yifan+Xu%2C+Mingzhe+Xing%2C+Zhen+Xiao%2C+and+1+others%2E+2025d%2E+Mmgdreamer%3A+Mixed%2Dmodality+graph+for+geometry%2Dcontrollable)
31. Xingbo Yao, Xuanmin Wang, Hao Wu, Chengliang Ping, Doudou Zhang, and Hui Xiong. 2025a. Magicc-ity: Geometry-aware 3d city generation from satellite imagery with multi-view consistency. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 25325–25334. [find](https://scholar.google.com/scholar?q=Xingbo+Yao%2C+Xuanmin+Wang%2C+Hao+Wu%2C+Chengliang+Ping%2C+Doudou+Zhang%2C+and+Hui+Xiong%2E+2025a%2E+Magicc%2Dity%3A+Geometry%2Daware+3d+city+generation+from+satellite+imagery+with+multi%2Dview+consistency%2E+In+Proceedings+)
32. Xingbo Yao, Xuanmin Wang, and Hui Xiong. 2025b. Citysculpt: 3d city generation from satellite imagery with uv diffusion. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 9813– 9821. [find](https://scholar.google.com/scholar?q=Xingbo+Yao%2C+Xuanmin+Wang%2C+and+Hui+Xiong%2E+2025b%2E+Citysculpt%3A+3d+city+generation+from+satellite+imagery+with+uv+diffusion%2E+In+Proceedings+of+the+33rd+ACM+International+Conference+on+Multimedia%2C+pages+98)
33. Hong-Xing Yu, Haoyi Duan, Charles Herrmann, William T Freeman, and Jiajun Wu. 2025. Wonderworld: Interactive 3d scene generation from a single image. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 5916–5926. [find](https://scholar.google.com/scholar?q=Hong%2DXing+Yu%2C+Haoyi+Duan%2C+Charles+Herrmann%2C+William+T+Freeman%2C+and+Jiajun+Wu%2E+2025%2E+Wonderworld%3A+Interactive+3d+scene+generation+from+a+single+image%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+)
34. Yunzhi Zhang, Zizhang Li, Matt Zhou, Shangzhe Wu, and Jiajun Wu. 2025. The scene language: Representing scenes with programs, words, and embeddings. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 24625–24634. [find](https://scholar.google.com/scholar?q=Yunzhi+Zhang%2C+Zizhang+Li%2C+Matt+Zhou%2C+Shangzhe+Wu%2C+and+Jiajun+Wu%2E+2025%2E+The+scene+language%3A+Representing+scenes+with+programs%2C+words%2C+and+embeddings%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+R)
35. Chong Xia, Shengjun Zhang, Fangfu Liu, Chang Liu, Khodchaphun Hirunyaratsameewong, and Yueqi Duan. 2025. Scenepainter: Semantically consistent perpetual 3d scene generation with concept relation alignment. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 28808– 28817… [find](https://scholar.google.com/scholar?q=Chong+Xia%2C+Shengjun+Zhang%2C+Fangfu+Liu%2C+Chang+Liu%2C+Khodchaphun+Hirunyaratsameewong%2C+and+Yueqi+Duan%2E+2025%2E+Scenepainter%3A+Semantically+consistent+perpetual+3d+scene+generation+with+concept+relation+align)
36. Fan Yang, Sicheng Zhao, Yanhao Zhang, Hui Chen, Haonan Lu, Jungong Han, and Guiguang Ding. 2024. Llmi3d: Mllm-based 3d perception from a single 2d image. arXiv preprint arXiv:2408.07422. — [arXiv:2408.07422](https://arxiv.org/abs/2408.07422) [find](https://scholar.google.com/scholar?q=Fan+Yang%2C+Sicheng+Zhao%2C+Yanhao+Zhang%2C+Hui+Chen%2C+Haonan+Lu%2C+Jungong+Han%2C+and+Guiguang+Ding%2E+2024%2E+Llmi3d%3A+Mllm%2Dbased+3d+perception+from+a+single+2d+image%2E+arXiv+preprint+arXiv%3A2408%2E07422%2E+%E2%80%94+%5BarXiv%3A2408)
37. Yandan Yang, Baoxiong Jia, Shujie Zhang, and Siyuan Huang. 2025a. Sceneweaver: All-in-one 3d scene synthesis with an extensible and self-reflective agent. arXiv preprint arXiv:2509.20414. — [arXiv:2509.20414](https://arxiv.org/abs/2509.20414) [find](https://scholar.google.com/scholar?q=Yandan+Yang%2C+Baoxiong+Jia%2C+Shujie+Zhang%2C+and+Siyuan+Huang%2E+2025a%2E+Sceneweaver%3A+All%2Din%2Done+3d+scene+synthesis+with+an+extensible+and+self%2Dreflective+agent%2E+arXiv+preprint+arXiv%3A2509%2E20414%2E+%E2%80%94+%5BarXiv%3A250)
38. Yandan Yang, Baoxiong Jia, Shujie Zhang, and Siyuan Huang. 2025b. Sceneweaver: All-in-one 3d scene synthesis with an extensible and self-reflective agent. In Advances in Neural Information Processing Systems (NeurIPS). [find](https://scholar.google.com/scholar?q=Yandan+Yang%2C+Baoxiong+Jia%2C+Shujie+Zhang%2C+and+Siyuan+Huang%2E+2025b%2E+Sceneweaver%3A+All%2Din%2Done+3d+scene+synthesis+with+an+extensible+and+self%2Dreflective+agent%2E+In+Advances+in+Neural+Information+Processing+)

*Updated 2 November 2026*