---
title: "Infinite Babble — paper by Sun et al. (2026) — summary and ideas"
description: "The authors present Inflate3D, which they describe as the first attack of this type that works only in the point cloud input space. 48 references."
authors: ["Shuoyang Sun", "Jiaxin Hong", "Yv Zhang", "Kuofeng Gao", "Hao Fang", "Bin Chen", "Shu-Tao Xia"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.259/"
doi: "10.18653/v1/2026.findings-acl.259"
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/sun-2026-infinite-babble-inflating-3d-vision/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2026-infinite-babble-inflating-3d-vision/)

[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/33/) / Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation

# Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation

**Authors:** Shuoyang Sun, Jiaxin Hong, Yv Zhang, [Kuofeng Gao](https://md.research.elamur.ai/free/en/authors/kuofeng-gao/), [Hao Fang](https://md.research.elamur.ai/free/en/authors/hao-fang/), [Bin Chen](https://md.research.elamur.ai/free/en/authors/bin-chen/) and [Shu-Tao Xia](https://md.research.elamur.ai/free/en/authors/shu-tao-xia/) · **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.259/) · [PDF](https://aclanthology.org/2026.findings-acl.259.pdf) · [DOI 10.18653/v1/2026.findings-acl.259](https://doi.org/10.18653/v1/2026.findings-acl.259) · [OpenAlex](https://openalex.org/W7166879341)

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

## Summary

The paper examines a resource-exhaustion threat to 3D Vision-Language Models (3D-VLMs). These models decode text autoregressively and often take in untrusted 3D assets downloaded from the internet. The authors present Inflate3D, which they describe as the first attack of this type that works only in the point cloud input space. It adds small, hard-to-notice noise that makes the model keep generating text far beyond what the prompt requires. This raises latency and battery drain for local systems such as robots, and it inflates token charges for cloud APIs.

The method has two parts:
- **Semantic-aware mask.** It uses the model's hidden states to find the points linked to the most important point tokens, then perturbs only those points.
- **Trajectory disruption objective.** A dispersion loss keeps next-token predictions uncertain, and a persistence loss lowers the probability of EOS. A projection-based scheme balances the two losses.

On Objaverse and ModelNet40, outputs grew up to 6.45× longer and energy use rose up to 6.12×. The work exposes an overlooked efficiency weakness and motivates efficiency-aware defenses.

## Key points

- **Results:** Inflate3D increases generation length by up to 6.45× and inference energy by up to 6.12×, measured on the Objaverse and ModelNet40 benchmarks.
- **Loss ablation:** Combining the dispersion and persistence losses gave the strongest attack, reaching 127.52 tokens and 406.50 J.
- **Masking:** The semantic-aware mask beat a random-masking baseline on ModelNet40, and the appendix extends this comparison to ScanQA.
- **Perturbation ratio:** A 50% ratio was the best trade-off, keeping Chamfer Distance at about 2.6 × 10⁻⁴. Ratios above 50% caused repetitive, low-Distinct-1 outputs, which defenders could easily detect.
- **Limitations and defenses:** The attack assumes white-box gradient access and transfers less well to models with different cross-modal alignment. It was tested only with English prompts. The authors ran a preliminary evaluation of the defenses Dup-Net and SOR.

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

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Shuoyang Sun, Jiaxin Hong, Yv Zhang, Kuofeng Gao, Hao Fang, Bin Chen and Shu-Tao Xia. 2026. Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation. 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{sun2026infinite,
  title = {{Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation}},
  author = {Shuoyang Sun, Jiaxin Hong, Yv Zhang, Kuofeng Gao, Hao Fang, Bin Chen and Shu-Tao Xia},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.259},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.259}
}
```

- [← previous Individual and Combined Effects of English as a Second Language and Typos on LLM Performance](https://md.research.elamur.ai/free/en/papers/liu-2026-individual-combined-effects-english-second/)
- [next → Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts](https://md.research.elamur.ai/free/en/papers/takashiro-2026-infinity-moe-generalizing-mixture-experts/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/33/)

## References

48 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, and 1 others. 2024. [Phi-3 technical report: A highly capable language model locally on your phone](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-3-technical-report-highly/). arXiv preprint arXiv:2404.14219.
2. THH Aldhyani and H Alkahtani. 2023. Cyber security for detecting distributed denial of service attacks in agriculture 4.0: Deep learning model. mathematics, 11 (233). [find](https://scholar.google.com/scholar?q=THH+Aldhyani+and+H+Alkahtani%2E+2023%2E+Cyber+security+for+detecting+distributed+denial+of+service+attacks+in+agriculture+4%2E0%3A+Deep+learning+model%2E+mathematics%2C+11+%28233%29%2E)
3. Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, and Motoaki Kawanabe. 2022. Scanqa: 3d question answering for spatial scene understanding. In proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 19129–19139. [find](https://scholar.google.com/scholar?q=Daichi+Azuma%2C+Taiki+Miyanishi%2C+Shuhei+Kurita%2C+and+Motoaki+Kawanabe%2E+2022%2E+Scanqa%3A+3d+question+answering+for+spatial+scene+understanding%2E+In+proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+an)
4. Sajal Bhatia, Sunny Behal, and Irfan Ahmed. 2018. Distributed denial of service attacks and defense mechanisms: current landscape and future directions. In Versatile Cybersecurity, pages 55–97. Springer. [find](https://scholar.google.com/scholar?q=Sajal+Bhatia%2C+Sunny+Behal%2C+and+Irfan+Ahmed%2E+2018%2E+Distributed+denial+of+service+attacks+and+defense+mechanisms%3A+current+landscape+and+future+directions%2E+In+Versatile+Cybersecurity%2C+pages+55%E2%80%9397%2E+Spring)
5. Simin Chen, Zihe Song, Mirazul Haque, Cong Liu, and Wei Yang. 2022. Nicgslowdown: Evaluating the efficiency robustness of neural image caption generation models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15365–15374. [find](https://scholar.google.com/scholar?q=Simin+Chen%2C+Zihe+Song%2C+Mirazul+Haque%2C+Cong+Liu%2C+and+Wei+Yang%2E+2022%2E+Nicgslowdown%3A+Evaluating+the+efficiency+robustness+of+neural+image+caption+generation+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Confere)
6. Wei-Lin Chiang, Zhuohan Li, Ziqing Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, and 1 others. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See [https://vicuna.lmsys](https://vicuna.lmsys). org (accessed 14 April 2023), 2(3):6. [↗](https://vicuna.lmsys)
7. Matt Deitke, Dustin Schwenk, Jordi Salvador, Luca Weihs, Oscar Michel, Eli VanderBilt, Ludwig Schmidt, Kiana Ehsani, Aniruddha Kembhavi, and Ali Farhadi. 2023. Objaverse: A universe of annotated 3d objects. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1… [find](https://scholar.google.com/scholar?q=Matt+Deitke%2C+Dustin+Schwenk%2C+Jordi+Salvador%2C+Luca+Weihs%2C+Oscar+Michel%2C+Eli+VanderBilt%2C+Ludwig+Schmidt%2C+Kiana+Ehsani%2C+Aniruddha+Kembhavi%2C+and+Ali+Farhadi%2E+2023%2E+Objaverse%3A+A+universe+of+annotated+3d+ob)
8. Jianshuo Dong, Ziyuan Zhang, Qingjie Zhang, Tianwei Zhang, Hao Wang, Hewu Li, Qi Li, Chao Zhang, Ke Xu, and Han Qiu. 2024. An engorgio prompt makes large language model babble on. arXiv preprint arXiv:2412.19394. — [arXiv:2412.19394](https://arxiv.org/abs/2412.19394) [find](https://scholar.google.com/scholar?q=Jianshuo+Dong%2C+Ziyuan+Zhang%2C+Qingjie+Zhang%2C+Tianwei+Zhang%2C+Hao+Wang%2C+Hewu+Li%2C+Qi+Li%2C+Chao+Zhang%2C+Ke+Xu%2C+and+Han+Qiu%2E+2024%2E+An+engorgio+prompt+makes+large+language+model+babble+on%2E+arXiv+preprint+arXiv)
9. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, and 1 others. 2020. [An image is worth 16x16 words: Transformers for image recognition at scale](https://md.research.elamur.ai/free/en/papers/dosovitskiy-2020-image-worth-16x16-words-transformers/). arXiv preprint arXiv:2010.1192…
10. Khaled M Elleithy, Drazen Blagovic, Wang K Cheng, and Paul Sideleau. 2005. Denial of service attack techniques: analysis, implementation and comparison. [find](https://scholar.google.com/scholar?q=Khaled+M+Elleithy%2C+Drazen+Blagovic%2C+Wang+K+Cheng%2C+and+Paul+Sideleau%2E+2005%2E+Denial+of+service+attack+techniques%3A+analysis%2C+implementation+and+comparison%2E)
11. Xiaoning Feng, Xiaohong Han, Simin Chen, and Wei Yang. 2024. Llmeffichecker: Understanding and testing efficiency degradation of large language models. ACM Transactions on Software Engineering and Methodology, 33(7):1–38. [find](https://scholar.google.com/scholar?q=Xiaoning+Feng%2C+Xiaohong+Han%2C+Simin+Chen%2C+and+Wei+Yang%2E+2024%2E+Llmeffichecker%3A+Understanding+and+testing+efficiency+degradation+of+large+language+models%2E+ACM+Transactions+on+Software+Engineering+and+Met)
12. Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, and Wei Liu. 2024a. Inducing high energy-latency of large vision-language models with verbose images. arXiv preprint arXiv:2401.11170. — [arXiv:2401.11170](https://arxiv.org/abs/2401.11170) [find](https://scholar.google.com/scholar?q=Kuofeng+Gao%2C+Yang+Bai%2C+Jindong+Gu%2C+Shu%2DTao+Xia%2C+Philip+Torr%2C+Zhifeng+Li%2C+and+Wei+Liu%2E+2024a%2E+Inducing+high+energy%2Dlatency+of+large+vision%2Dlanguage+models+with+verbose+images%2E+arXiv+preprint+arXiv%3A2401)
13. Kuofeng Gao, Jindong Gu, Yang Bai, Shu-Tao Xia, Philip Torr, Wei Liu, and Zhifeng Li. 2024b. Energy-latency manipulation of multi-modal large language models via verbose samples. arXiv preprint arXiv:2404.16557. — [arXiv:2404.16557](https://arxiv.org/abs/2404.16557) [find](https://scholar.google.com/scholar?q=Kuofeng+Gao%2C+Jindong+Gu%2C+Yang+Bai%2C+Shu%2DTao+Xia%2C+Philip+Torr%2C+Wei+Liu%2C+and+Zhifeng+Li%2E+2024b%2E+Energy%2Dlatency+manipulation+of+multi%2Dmodal+large+language+models+via+verbose+samples%2E+arXiv+preprint+arXiv%3A)
14. Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, and Ishan Misra. 2023. [Imagebind: One embedding space to bind them all](https://md.research.elamur.ai/free/en/papers/girdhar-2023-imagebind-one-embedding-space-bind/). In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15180–15190.
15. Ziyu Guo, Renrui Zhang, Xiangyang Zhu, Yiwen Tang, Xianzheng Ma, Jiaming Han, Kexin Chen, Peng Gao, Xianzhi Li, Hongsheng Li, and 1 others. 2023. Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following. arXiv preprint arXiv:2309.00… — [arXiv:2309.00615](https://arxiv.org/abs/2309.00615) [find](https://scholar.google.com/scholar?q=Ziyu+Guo%2C+Renrui+Zhang%2C+Xiangyang+Zhu%2C+Yiwen+Tang%2C+Xianzheng+Ma%2C+Jiaming+Han%2C+Kexin+Chen%2C+Peng+Gao%2C+Xianzhi+Li%2C+Hongsheng+Li%2C+and+1+others%2E+2023%2E+Point%2Dbind+%26+point%2Dllm%3A+Aligning+point+cloud+with+mult)
16. Jiaming Han, Renrui Zhang, Wenqi Shao, Peng Gao, Peng Xu, Han Xiao, Kaipeng Zhang, Chris Liu, Song Wen, Ziyu Guo, and 1 others. 2023. Imagebind-llm: Multi-modality instruction tuning. arXiv preprint arXiv:2309.03905. — [arXiv:2309.03905](https://arxiv.org/abs/2309.03905) [find](https://scholar.google.com/scholar?q=Jiaming+Han%2C+Renrui+Zhang%2C+Wenqi+Shao%2C+Peng+Gao%2C+Peng+Xu%2C+Han+Xiao%2C+Kaipeng+Zhang%2C+Chris+Liu%2C+Song+Wen%2C+Ziyu+Guo%2C+and+1+others%2E+2023%2E+Imagebind%2Dllm%3A+Multi%2Dmodality+instruction+tuning%2E+arXiv+preprint+a)
17. Warren He, Bo Li, and Dawn Song. 2018. Decision boundary analysis of adversarial examples. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Warren+He%2C+Bo+Li%2C+and+Dawn+Song%2E+2018%2E+Decision+boundary+analysis+of+adversarial+examples%2E+In+International+Conference+on+Learning+Representations%2E)
18. Sanghyun Hong, Yiğitcan Kaya, Ionuţ-Vlad Modoranu, and Tudor Dumitraş. 2020. A panda? no, it’s a sloth: Slowdown attacks on adaptive multi-exit neural network inference. arXiv preprint arXiv:2010.02432. — [arXiv:2010.02432](https://arxiv.org/abs/2010.02432) [find](https://scholar.google.com/scholar?q=Sanghyun+Hong%2C+Yig%CC%86itcan+Kaya%2C+Ionut%CC%A7%2DVlad+Modoranu%2C+and+Tudor+Dumitras%CC%A7%2E+2020%2E+A+panda%3F+no%2C+it%E2%80%99s+a+sloth%3A+Slowdown+attacks+on+adaptive+multi%2Dexit+neural+network+inference%2E+arXiv+preprint+arXiv%3A2010%2E0)
19. Yining Hong, Haoyu Zhen, Peihao Chen, Shuhong Zheng, Yilun Du, Zhenfang Chen, and Chuang Gan. 2023. 3d-llm: Injecting the 3d world into large language models. Advances in Neural Information Processing Systems, 36:20482–20494. [find](https://scholar.google.com/scholar?q=Yining+Hong%2C+Haoyu+Zhen%2C+Peihao+Chen%2C+Shuhong+Zheng%2C+Yilun+Du%2C+Zhenfang+Chen%2C+and+Chuang+Gan%2E+2023%2E+3d%2Dllm%3A+Injecting+the+3d+world+into+large+language+models%2E+Advances+in+Neural+Information+Processing)
20. Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, and Siyuan Huang. 2023. An embodied generalist agent in 3d world. arXiv preprint arXiv:2311.12871. — [arXiv:2311.12871](https://arxiv.org/abs/2311.12871) [find](https://scholar.google.com/scholar?q=Jiangyong+Huang%2C+Silong+Yong%2C+Xiaojian+Ma%2C+Xiongkun+Linghu%2C+Puhao+Li%2C+Yan+Wang%2C+Qing+Li%2C+Song%2DChun+Zhu%2C+Baoxiong+Jia%2C+and+Siyuan+Huang%2E+2023%2E+An+embodied+generalist+agent+in+3d+world%2E+arXiv+preprint+a)
21. Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry. 2019. Adversarial examples are not bugs, they are features. Advances in neural information processing systems, 32. [find](https://scholar.google.com/scholar?q=Andrew+Ilyas%2C+Shibani+Santurkar%2C+Dimitris+Tsipras%2C+Logan+Engstrom%2C+Brandon+Tran%2C+and+Aleksander+Madry%2E+2019%2E+Adversarial+examples+are+not+bugs%2C+they+are+features%2E+Advances+in+neural+information+proces)
22. Mojan Javaheripi, Sébastien Bubeck, Marah Abdin, Jyoti Aneja, Sebastien Bubeck, Caio César Teodoro Mendes, Weizhu Chen, Allie Del Giorno, Ronen Eldan, Sivakanth Gopi, and 1 others. 2023. Phi-2: The surprising power of small language models. Microsoft Research Blog, 1(3):3. [find](https://scholar.google.com/scholar?q=Mojan+Javaheripi%2C+S%C3%A9bastien+Bubeck%2C+Marah+Abdin%2C+Jyoti+Aneja%2C+Sebastien+Bubeck%2C+Caio+C%C3%A9sar+Teodoro+Mendes%2C+Weizhu+Chen%2C+Allie+Del+Giorno%2C+Ronen+Eldan%2C+Sivakanth+Gopi%2C+and+1+others%2E+2023%2E+Phi%2D2%3A+The+su)
23. Leslie Rice, Eric Wong, and Zico Kolter. 2020. Overfitting in adversarially robust deep learning. In International conference on machine learning, pages 8093–8104. PMLR. [find](https://scholar.google.com/scholar?q=Leslie+Rice%2C+Eric+Wong%2C+and+Zico+Kolter%2E+2020%2E+Overfitting+in+adversarially+robust+deep+learning%2E+In+International+conference+on+machine+learning%2C+pages+8093%E2%80%938104%2E+PMLR%2E)
24. Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, and George Drettakis. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph., 42(4):139–1. [find](https://scholar.google.com/scholar?q=Bernhard+Kerbl%2C+Georgios+Kopanas%2C+Thomas+Leimk%C3%BChler%2C+and+George+Drettakis%2E+2023%2E+3d+gaussian+splatting+for+real%2Dtime+radiance+field+rendering%2E+ACM+Trans%2E+Graph%2E%2C+42%284%29%3A139%E2%80%931%2E)
25. Ilia Shumailov, Yiren Zhao, Daniel Bates, Nicolas Papernot, Robert Mullins, and Ross Anderson. 2021. Sponge examples: Energy-latency attacks on neural networks. In 2021 IEEE European symposium on security and privacy (EuroS&P), pages 212–231. IEEE. [find](https://scholar.google.com/scholar?q=Ilia+Shumailov%2C+Yiren+Zhao%2C+Daniel+Bates%2C+Nicolas+Papernot%2C+Robert+Mullins%2C+and+Ross+Anderson%2E+2021%2E+Sponge+examples%3A+Energy%2Dlatency+attacks+on+neural+networks%2E+In+2021+IEEE+European+symposium+on+secu)
26. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. [Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). In International conference on machine learning, pages 19730–19742. PMLR.
27. Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, and Yue Cao. 2023. [Eva-clip: Improved training techniques for clip at scale](https://md.research.elamur.ai/free/en/papers/sun-2023-eva-clip-improved-training-techniques/). arXiv preprint arXiv:2303.15389.
28. Han Liu, Yuhao Wu, Zhiyuan Yu, Yevgeniy Vorobeychik, and Ning Zhang. 2023. Slowlidar: Increasing the latency of lidar-based detection using adversarial examples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5146–5155. [find](https://scholar.google.com/scholar?q=Han+Liu%2C+Yuhao+Wu%2C+Zhiyuan+Yu%2C+Yevgeniy+Vorobeychik%2C+and+Ning+Zhang%2E+2023%2E+Slowlidar%3A+Increasing+the+latency+of+lidar%2Dbased+detection+using+adversarial+examples%2E+In+Proceedings+of+the+IEEE%2FCVF+Confere)
29. Yuan Tang, Xu Han, Xianzhi Li, Qiao Yu, Yixue Hao, Long Hu, and Min Chen. 2024. Minigpt-3d: Efficiently aligning 3d point clouds with large language models using 2d priors. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 6617–6626. [find](https://scholar.google.com/scholar?q=Yuan+Tang%2C+Xu+Han%2C+Xianzhi+Li%2C+Qiao+Yu%2C+Yixue+Hao%2C+Long+Hu%2C+and+Min+Chen%2E+2024%2E+Minigpt%2D3d%3A+Efficiently+aligning+3d+point+clouds+with+large+language+models+using+2d+priors%2E+In+Proceedings+of+the+32nd+)
30. Neil Long and Rob Thomas. 2001. Trends in denial of service attack technology. CERT Coordination Center, 648(651):569. [find](https://scholar.google.com/scholar?q=Neil+Long+and+Rob+Thomas%2E+2001%2E+Trends+in+denial+of+service+attack+technology%2E+CERT+Coordination+Center%2C+648%28651%29%3A569%2E)
31. Yuan Tang, Xu Han, Xianzhi Li, Qiao Yu, Jinfeng Xu, Yixue Hao, Long Hu, and Min Chen. 2025. More text, less point: Towards 3d data-efficient point-language understanding. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 7284–7292. [find](https://scholar.google.com/scholar?q=Yuan+Tang%2C+Xu+Han%2C+Xianzhi+Li%2C+Qiao+Yu%2C+Jinfeng+Xu%2C+Yixue+Hao%2C+Long+Hu%2C+and+Min+Chen%2E+2025%2E+More+text%2C+less+point%3A+Towards+3d+data%2Defficient+point%2Dlanguage+understanding%2E+In+Proceedings+of+the+AAAI+Co)
32. Jiahao Lu, Yifan Zhang, Qiuhong Shen, Xinchao Wang, and Shuicheng Yan. 2024. Poison-splat: Computation cost attack on 3d gaussian splatting. arXiv preprint arXiv:2410.08190. — [arXiv:2410.08190](https://arxiv.org/abs/2410.08190) [find](https://scholar.google.com/scholar?q=Jiahao+Lu%2C+Yifan+Zhang%2C+Qiuhong+Shen%2C+Xinchao+Wang%2C+and+Shuicheng+Yan%2E+2024%2E+Poison%2Dsplat%3A+Computation+cost+attack+on+3d+gaussian+splatting%2E+arXiv+preprint+arXiv%3A2410%2E08190%2E+%E2%80%94+%5BarXiv%3A2410%2E08190%5D%28https)
33. Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2017. [Towards deep learning models resistant to adversarial attacks](https://md.research.elamur.ai/free/en/papers/madry-2017-towards-deep-learning-models-resistant/). arXiv preprint arXiv:1706.06083.
34. Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei Ye, Kuofeng Gao, Yi Huang, and Yuan Yao. 2025. Vlminferslow: Evaluating the efficiency robustness of large vision-language models as a service. In ACL. [find](https://scholar.google.com/scholar?q=Xiasi+Wang%2C+Tianliang+Yao%2C+Simin+Chen%2C+Runqi+Wang%2C+Lei+Ye%2C+Kuofeng+Gao%2C+Yi+Huang%2C+and+Yuan+Yao%2E+2025%2E+Vlminferslow%3A+Evaluating+the+efficiency+robustness+of+large+vision%2Dlanguage+models+as+a+service%2E+I)
35. Jelena Mirkovic and Peter Reiher. 2004. A taxonomy of ddos attack and ddos defense mechanisms. ACM SIG-COMM Computer Communication Review, 34(2):39– 53. [find](https://scholar.google.com/scholar?q=Jelena+Mirkovic+and+Peter+Reiher%2E+2004%2E+A+taxonomy+of+ddos+attack+and+ddos+defense+mechanisms%2E+ACM+SIG%2DCOMM+Computer+Communication+Review%2C+34%282%29%3A39%E2%80%93+53%2E)
36. Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1912–1920. [find](https://scholar.google.com/scholar?q=Zhirong+Wu%2C+Shuran+Song%2C+Aditya+Khosla%2C+Fisher+Yu%2C+Linguang+Zhang%2C+Xiaoou+Tang%2C+and+Jianxiong+Xiao%2E+2015%2E+3d+shapenets%3A+A+deep+representation+for+volumetric+shapes%2E+In+Proceedings+of+the+IEEE+conferen)
37. Artemis Panagopoulou, Le Xue, Ning Yu, Junnan Li, Dongxu Li, Shafiq Joty, Ran Xu, Silvio Savarese, Caiming Xiong, and Juan Carlos Niebles. 2023. X-instructblip: A framework for aligning x-modal instruction-aware representations to llms and emergent cross-modal reasoning. arXiv preprint arXiv:2311.18… — [arXiv:2311.18799](https://arxiv.org/abs/2311.18799) [find](https://scholar.google.com/scholar?q=Artemis+Panagopoulou%2C+Le+Xue%2C+Ning+Yu%2C+Junnan+Li%2C+Dongxu+Li%2C+Shafiq+Joty%2C+Ran+Xu%2C+Silvio+Savarese%2C+Caiming+Xiong%2C+and+Juan+Carlos+Niebles%2E+2023%2E+X%2Dinstructblip%3A+A+framework+for+aligning+x%2Dmodal+instru)
38. Runsen Xu, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang, and Dahua Lin. 2024. Pointllm: Empowering large language models to understand point clouds. In European Conference on Computer Vision, pages 131–147. Springer. [find](https://scholar.google.com/scholar?q=Runsen+Xu%2C+Xiaolong+Wang%2C+Tai+Wang%2C+Yilun+Chen%2C+Jiangmiao+Pang%2C+and+Dahua+Lin%2E+2024%2E+Pointllm%3A+Empowering+large+language+models+to+understand+point+clouds%2E+In+European+Conference+on+Computer+Vision%2C+p)
39. Zekun Qi, Runpei Dong, Shaochen Zhang, Haoran Geng, Chunrui Han, Zheng Ge, Li Yi, and Kaisheng Ma. 2024. Shapellm: Universal 3d object understanding for embodied interaction. In European Conference on Computer Vision, pages 214–238. Springer. [find](https://scholar.google.com/scholar?q=Zekun+Qi%2C+Runpei+Dong%2C+Shaochen+Zhang%2C+Haoran+Geng%2C+Chunrui+Han%2C+Zheng+Ge%2C+Li+Yi%2C+and+Kaisheng+Ma%2E+2024%2E+Shapellm%3A+Universal+3d+object+understanding+for+embodied+interaction%2E+In+European+Conference+on)
40. Runsen Xu, Shuai Yang, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang, and Dahua Lin. 2025. Pointllm-v2: Empowering large language models to better understand point clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence. [find](https://scholar.google.com/scholar?q=Runsen+Xu%2C+Shuai+Yang%2C+Xiaolong+Wang%2C+Tai+Wang%2C+Yilun+Chen%2C+Jiangmiao+Pang%2C+and+Dahua+Lin%2E+2025%2E+Pointllm%2Dv2%3A+Empowering+large+language+models+to+better+understand+point+clouds%2E+IEEE+Transactions+on+P)
41. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–8…
42. Le Xue, Ning Yu, Shu Zhang, Artemis Panagopoulou, Junnan Li, Roberto Martín-Martín, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, and 1 others. 2024. Ulip-2: Towards scalable multimodal pre-training for 3d understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Patte… [find](https://scholar.google.com/scholar?q=Le+Xue%2C+Ning+Yu%2C+Shu+Zhang%2C+Artemis+Panagopoulou%2C+Junnan+Li%2C+Roberto+Mart%C3%ADn%2DMart%C3%ADn%2C+Jiajun+Wu%2C+Caiming+Xiong%2C+Ran+Xu%2C+Juan+Carlos+Niebles%2C+and+1+others%2E+2024%2E+Ulip%2D2%3A+Towards+scalable+multimodal+pre%2Dt)
43. Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. [Gradient surgery for multi-task learning](https://md.research.elamur.ai/free/en/papers/yu-2020-gradient-surgery-multi-task-learning/). Advances in neural information processing systems, 33:5824– 5836.
44. Xumin Yu, Lulu Tang, Yongming Rao, Tiejun Huang, Jie Zhou, and Jiwen Lu. 2022. Point-bert: Pre-training 3d point cloud transformers with masked point modeling. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 19313–19322. [find](https://scholar.google.com/scholar?q=Xumin+Yu%2C+Lulu+Tang%2C+Yongming+Rao%2C+Tiejun+Huang%2C+Jie+Zhou%2C+and+Jiwen+Lu%2E+2022%2E+Point%2Dbert%3A+Pre%2Dtraining+3d+point+cloud+transformers+with+masked+point+modeling%2E+In+Proceedings+of+the+IEEE%2FCVF+conferenc)
45. Duo Zheng, Shijia Huang, and Liwei Wang. 2025. Video-3d llm: Learning position-aware video representation for 3d scene understanding. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 8995–9006. [find](https://scholar.google.com/scholar?q=Duo+Zheng%2C+Shijia+Huang%2C+and+Liwei+Wang%2E+2025%2E+Video%2D3d+llm%3A+Learning+position%2Daware+video+representation+for+3d+scene+understanding%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+Recognition+Conf)
46. Hongyan Zhi, Peihao Chen, Junyan Li, Shuailei Ma, Xinyu Sun, Tianhang Xiang, Yinjie Lei, Mingkui Tan, and Chuang Gan. 2025. Lscenellm: Enhancing large 3d scene understanding using adaptive visual preferences. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 3761– 3771. [find](https://scholar.google.com/scholar?q=Hongyan+Zhi%2C+Peihao+Chen%2C+Junyan+Li%2C+Shuailei+Ma%2C+Xinyu+Sun%2C+Tianhang+Xiang%2C+Yinjie+Lei%2C+Mingkui+Tan%2C+and+Chuang+Gan%2E+2025%2E+Lscenellm%3A+Enhancing+large+3d+scene+understanding+using+adaptive+visual+pref)
47. Hang Zhou, Kejiang Chen, Weiming Zhang, Han Fang, Wenbo Zhou, and Nenghai Yu. 2019. Dup-net: Denoiser and upsampler network for 3d adversarial point clouds defense. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1961–1970. [find](https://scholar.google.com/scholar?q=Hang+Zhou%2C+Kejiang+Chen%2C+Weiming+Zhang%2C+Han+Fang%2C+Wenbo+Zhou%2C+and+Nenghai+Yu%2E+2019%2E+Dup%2Dnet%3A+Denoiser+and+upsampler+network+for+3d+adversarial+point+clouds+defense%2E+In+Proceedings+of+the+IEEE%2FCVF+inte)
48. Junsheng Zhou, Jinsheng Wang, Baorui Ma, Yu-Shen Liu, Tiejun Huang, and Xinlong Wang. 2023. Uni3d: Exploring unified 3d representation at scale. arXiv preprint arXiv:2310.06773. — [arXiv:2310.06773](https://arxiv.org/abs/2310.06773) [find](https://scholar.google.com/scholar?q=Junsheng+Zhou%2C+Jinsheng+Wang%2C+Baorui+Ma%2C+Yu%2DShen+Liu%2C+Tiejun+Huang%2C+and+Xinlong+Wang%2E+2023%2E+Uni3d%3A+Exploring+unified+3d+representation+at+scale%2E+arXiv+preprint+arXiv%3A2310%2E06773%2E+%E2%80%94+%5BarXiv%3A2310%2E06773%5D%28h)

*Updated 1 November 2026*