---
title: "I2E — paper by Yu et al. (2026) — summary and ideas"
description: "The authors also release I2E-Bench, which targets multi-instance spatial reasoning and precise edits. 41 references."
authors: ["Jinghan Yu", "Junhao Xiao", "Chenyu Zhu", "Jiaming Li", "Jia Li", "HanMing Deng", "Xirui Wang", "Guoli Jia", "Jianjun Li", "Xiang Bai", "Bowen Zhou", "Zhiyuan Ma"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.2076/"
doi: "10.18653/v1/2026.acl-long.2076"
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/yu-2026-i2e-image-pixels-actionable-interactive/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2026-i2e-image-pixels-actionable-interactive/)

[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/36/) / I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing

# I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing

**Authors:** Jinghan Yu, Junhao Xiao, [Chenyu Zhu](https://md.research.elamur.ai/free/en/authors/chenyu-zhu/), Jiaming Li, [Jia Li](https://md.research.elamur.ai/free/en/authors/jia-li/), HanMing Deng, Xirui Wang, Guoli Jia, [Jianjun Li](https://md.research.elamur.ai/free/en/authors/jianjun-li/), [Xiang Bai](https://md.research.elamur.ai/free/en/authors/xiang-bai/), [Bowen Zhou](https://md.research.elamur.ai/free/en/authors/bowen-zhou/) and [Zhiyuan Ma](https://md.research.elamur.ai/free/en/authors/zhiyuan-ma/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.2076/) · [PDF](https://aclanthology.org/2026.acl-long.2076.pdf) · [DOI 10.18653/v1/2026.acl-long.2076](https://doi.org/10.18653/v1/2026.acl-long.2076) · [OpenAlex](https://openalex.org/W7166846442)

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

## Summary
Most text-guided image editors repaint pixels end to end. This works for simple requests but fails on compositional instructions that need precise local control and reasoning about several objects. The authors trace the failures to three causes: planning and execution happen in one generation pass, there is no object-level granularity, and images are modelled as flat pixel grids. As a result, edits leak into non-target regions, objects end up floating, and quality drifts over repeated edits.

I2E ("Image-to-Environment") instead treats an image as a scene that can be acted upon:
- **Decomposer:** splits the picture into complete, depth-ordered object layers plus a restored background, recovering occluded parts of objects.
- **VLA Editor:** a physics-aware Vision-Language-Action agent uses Chain-of-Thought reasoning to turn an instruction into atomic actions and run them in sequence.

The authors also release I2E-Bench, which targets multi-instance spatial reasoning and precise edits. On I2E-Bench, MagicBrush and EmuEdit, I2E beats state-of-the-art baselines on compositional instructions, physical plausibility and multi-turn stability. Because later edits append actions rather than regenerating the whole image, iterative editing becomes more controllable.

## Key points
- **Pipeline and actions:** the Decomposer builds on SAM 2 segmentation and Flux-based repair. The agent emits atomic actions such as REMOVE, FALL (gravity-induced motion) and EDIT (e.g., colour change).
- **Ablation on I2E-Bench:**
  - Removing action reasoning drops IC from 0.8645 to 0.3151 and MS from 0.8074 to 0.3449.
  - Removing physical reasoning lowers PC from 0.9210 to 0.8360.
  - Removing DAG-based spatial constraint propagation reduces CSR from 0.87 to 0.77.
- **Human evaluation:** in a blind study, 30 participants each rated 10 cases on a 0–10 scale, comparing I2E with five baselines. I2E received the highest preference.
- **Multi-turn and commercial comparisons:** in four-round editing, I2E keeps Saturation and PixDiff stable, while end-to-end models (e.g., OmniGen, Step1X, IP2P) steadily degrade. Qualitative comparisons also favour I2E over GPT5.1, Seedream4.5, FLUX.1-Kontext-dev, Qwen3-Max and Nano Banana.
- **Limitations:** results depend on the underlying foundation models, which struggle with transparent objects (glass, water) and complex occlusions. Soft-body, fluid and fine lighting effects are not simulated.

*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 (2): [🖥️ 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

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Jinghan Yu, Junhao Xiao, Chenyu Zhu, Jiaming Li, Jia Li, HanMing Deng, Xirui Wang, Guoli Jia, Jianjun Li, Xiang Bai, Bowen Zhou and Zhiyuan Ma. 2026. I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{yu2026i2e,
  title = {{I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing}},
  author = {Jinghan Yu, Junhao Xiao, Chenyu Zhu, Jiaming Li, Jia Li, HanMing Deng, Xirui Wang, Guoli Jia, Jianjun Li, Xiang Bai, Bowen Zhou and Zhiyuan Ma},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.2076},
  url = {https://doi.org/10.18653/v1/2026.acl-long.2076}
}
```

- [← previous I2C At MultiPRIDE: Transformers And Generative LLMs For Multilingual Reclamation Classification](https://md.research.elamur.ai/free/en/papers/ramos-2026-i2c-multipride-transformers-generative-llms/)
- [next → ICDAGENT: Empowering Agentic Large Language Models for Explainable Medical Coding](https://md.research.elamur.ai/free/en/papers/yin-2026-icdagent-empowering-agentic-large-language/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/)

## References

41 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jiayang Ao, Yanbei Jiang, Qiuhong Ke, and Krista A Ehinger. 2025. Open-world amodal appearance completion. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 6490–6499. [find](https://scholar.google.com/scholar?q=Jiayang+Ao%2C+Yanbei+Jiang%2C+Qiuhong+Ke%2C+and+Krista+A+Ehinger%2E+2025%2E+Open%2Dworld+amodal+appearance+completion%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+Recognition+Conference%2C+pages+6490%E2%80%936499%2E)
2. James Betker, Gabriel Goh, Li Jing, Tim Brooks, Jianfeng Wang, Linjie Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Yufei Guo, Wesam Manassra, Prafulla Dhariwal, Casey Chu, Yunxin Jiao, and Aditya Ramesh. 2023. Improving image generation with better captions. Computer Science. [https://cdn.openai](https://cdn.openai). com… [↗](https://cdn.openai)
3. Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, Pete Florence, Chuyuan Fu, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Kehang Han, Karol Hausman, Alexander Herzog, Jasmine Hsu, Brian Ichter,… [find](https://scholar.google.com/scholar?q=Anthony+Brohan%2C+Noah+Brown%2C+Justice+Carbajal%2C+Yevgen+Chebotar%2C+Xi+Chen%2C+Krzysztof+Choromanski%2C+Tianli+Ding%2C+Danny+Driess%2C+Avinava+Dubey%2C+Chelsea+Finn%2C+Pete+Florence%2C+Chuyuan+Fu%2C+Montse+Gonzalez+Arenas)
4. Tim Brooks, Aleksander Holynski, and Alexei A Efros. 2023. Instructpix2pix: Learning to follow image editing instructions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 18392–18402. [find](https://scholar.google.com/scholar?q=Tim+Brooks%2C+Aleksander+Holynski%2C+and+Alexei+A+Efros%2E+2023%2E+Instructpix2pix%3A+Learning+to+follow+image+editing+instructions%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+reco)
5. Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. 2021. [Emerging properties in self-supervised vision transformers](https://md.research.elamur.ai/free/en/papers/caron-2021-emerging-properties-self-supervised-vision/). In Proceedings of the IEEE/CVF international conference on computer vision, pages 9650–9660.
6. Ruihan Chen, Qiming Li, Xiaocheng Feng, Xiaoliang Yang, Weihong Zhong, Yuxuan Gu, Zekun Zhou, and Bing Qin. 2025. Mpr-gui: Benchmarking and enhancing multilingual perception and reasoning in gui agents. Preprint, arXiv:2512.00756. [find](https://scholar.google.com/scholar?q=Ruihan+Chen%2C+Qiming+Li%2C+Xiaocheng+Feng%2C+Xiaoliang+Yang%2C+Weihong+Zhong%2C+Yuxuan+Gu%2C+Zekun+Zhou%2C+and+Bing+Qin%2E+2025%2E+Mpr%2Dgui%3A+Benchmarking+and+enhancing+multilingual+perception+and+reasoning+in+gui+agent)
7. Danny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, and 3 ot… [find](https://scholar.google.com/scholar?q=Danny+Driess%2C+Fei+Xia%2C+Mehdi+S%2E+M%2E+Sajjadi%2C+Corey+Lynch%2C+Aakanksha+Chowdhery%2C+Brian+Ichter%2C+Ayzaan+Wahid%2C+Jonathan+Tompson%2C+Quan+Vuong%2C+Tianhe+Yu%2C+Wenlong+Huang%2C+Yevgen+Chebotar%2C+Pierre+Sermanet%2C+Dani)
8. Kunyu Feng, Yue Ma, Bingyuan Wang, Chenyang Qi, Haozhe Chen, Qifeng Chen, and Zeyu Wang. 2025. Dit4edit: Diffusion transformer for image editing. [find](https://scholar.google.com/scholar?q=Kunyu+Feng%2C+Yue+Ma%2C+Bingyuan+Wang%2C+Chenyang+Qi%2C+Haozhe+Chen%2C+Qifeng+Chen%2C+and+Zeyu+Wang%2E+2025%2E+Dit4edit%3A+Diffusion+transformer+for+image+editing%2E)
9. Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626. [find](https://scholar.google.com/scholar?q=Amir+Hertz%2C+Ron+Mokady%2C+Jay+Tenenbaum%2C+Kfir+Aberman%2C+Yael+Pritch%2C+and+Daniel+Cohen%2DOr%2E+2022%2E+Prompt%2Dto%2Dprompt+image+editing+with+cross+attention+control%2E+arXiv+preprint+arXiv%3A2208%2E01626%2E)
10. Yujia Hu, Songhua Liu, Zhenxiong Tan, Xingyi Yang, and Xinchao Wang. 2025. Image editing as programs with diffusion models. arXiv preprint arXiv:2506.04158. — [arXiv:2506.04158](https://arxiv.org/abs/2506.04158) [find](https://scholar.google.com/scholar?q=Yujia+Hu%2C+Songhua+Liu%2C+Zhenxiong+Tan%2C+Xingyi+Yang%2C+and+Xinchao+Wang%2E+2025%2E+Image+editing+as+programs+with+diffusion+models%2E+arXiv+preprint+arXiv%3A2506%2E04158%2E+%E2%80%94+%5BarXiv%3A2506%2E04158%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F)
11. Yuzhou Huang, Liangbin Xie, Xintao Wang, Ziyang Yuan, Xiaodong Cun, Yixiao Ge, Jiantao Zhou, Chao Dong, Rui Huang, Ruimao Zhang, and Ying Shan. 2024. Smartedit: Exploring complex instruction-based image editing with multimodal large language models. In Proceedings of the IEEE/CVF Conference on Compu… [find](https://scholar.google.com/scholar?q=Yuzhou+Huang%2C+Liangbin+Xie%2C+Xintao+Wang%2C+Ziyang+Yuan%2C+Xiaodong+Cun%2C+Yixiao+Ge%2C+Jiantao+Zhou%2C+Chao+Dong%2C+Rui+Huang%2C+Ruimao+Zhang%2C+and+Ying+Shan%2E+2024%2E+Smartedit%3A+Exploring+complex+instruction%2Dbased+ima)
12. Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Foster, Grace Lam, Pannag Sanketi, Quan Vuong, Thomas Kollar, Benjamin Burchfiel, Russ Tedrake, Dorsa Sadigh, Sergey Levine, Percy Liang, and Chelsea Finn. 2024. Openvla: An open-source… [find](https://scholar.google.com/scholar?q=Moo+Jin+Kim%2C+Karl+Pertsch%2C+Siddharth+Karamcheti%2C+Ted+Xiao%2C+Ashwin+Balakrishna%2C+Suraj+Nair%2C+Rafael+Rafailov%2C+Ethan+Foster%2C+Grace+Lam%2C+Pannag+Sanketi%2C+Quan+Vuong%2C+Thomas+Kollar%2C+Benjamin+Burchfiel%2C+Russ)
13. Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, and Ross Girshick. 2023. [Segment anything](https://md.research.elamur.ai/free/en/papers/kirillov-2023-segment-anything/). In Proceedings of the IEEE/CVF international conference on computer vision, pages 4015–4026.
14. Black Forest Labs, Stephen Batifol, Andreas Blattmann, Frederic Boesel, Saksham Consul, Cyril Diagne, Tim Dockhorn, Jack English, Zion English, Patrick Esser, Sumith Kulal, Kyle Lacey, Yam Levi, Cheng Li, Dominik Lorenz, Jonas Müller, Dustin Podell, Robin Rombach, Harry Saini, and 2 others. 2025. Fl… — [arXiv:2506.15742](https://arxiv.org/abs/2506.15742) [find](https://scholar.google.com/scholar?q=Black+Forest+Labs%2C+Stephen+Batifol%2C+Andreas+Blattmann%2C+Frederic+Boesel%2C+Saksham+Consul%2C+Cyril+Diagne%2C+Tim+Dockhorn%2C+Jack+English%2C+Zion+English%2C+Patrick+Esser%2C+Sumith+Kulal%2C+Kyle+Lacey%2C+Yam+Levi%2C+Cheng)
15. Hyunmin Lee and Jaesik Park. 2022. Instance-wise Occlusion and Depth Orders in Natural Scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [find](https://scholar.google.com/scholar?q=Hyunmin+Lee+and+Jaesik+Park%2E+2022%2E+Instance%2Dwise+Occlusion+and+Depth+Orders+in+Natural+Scenes%2E+In+Proceedings+of+the+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition%2E)
16. Qiming Li, Xiaocheng Feng, Yixuan Ma, Zekai Ye, Ruihan Chen, Xiachong Feng, and Bing Qin. 2025. [Unlocking multilingual reasoning capability of llms and lvlms through representation engineering](https://md.research.elamur.ai/free/en/papers/li-2026-unlocking-multilingual-reasoning-capability-llms/). arXiv preprint arXiv:2511.23231.
17. Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, and Lei Zhang. 2023. [Grounding dino: Marrying dino with grounded pre-training for open-set object detection](https://md.research.elamur.ai/free/en/papers/liu-2023-grounding-dino-marrying-dino-grounded/). arXiv preprint arXiv:2303.05499.
18. Shelly Sheynin, Adam Polyak, Uriel Singer, Yuval Kirstain, Amit Zohar, Oron Ashual, Devi Parikh, and Yaniv Taigman. 2024. Emu edit: Precise image editing via recognition and generation tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8871–8879. [find](https://scholar.google.com/scholar?q=Shelly+Sheynin%2C+Adam+Polyak%2C+Uriel+Singer%2C+Yuval+Kirstain%2C+Amit+Zohar%2C+Oron+Ashual%2C+Devi+Parikh%2C+and+Yaniv+Taigman%2E+2024%2E+Emu+edit%3A+Precise+image+editing+via+recognition+and+generation+tasks%2E+In+Proce)
19. Shiyu Liu, Yucheng Han, Peng Xing, Fukun Yin, Rui Wang, Wei Cheng, Jiaqi Liao, Yingming Wang, Honghao Fu, Chunrui Han, Guopeng Li, Yuang Peng, Quan Sun, Jingwei Wu, Yan Cai, Zheng Ge, Ranchen Ming, Lei Xia, Xianfang Zeng, and 5 others. 2025a. [Step1x-edit: A practical framework for general image edit…](https://md.research.elamur.ai/free/en/papers/liu-2025-step1x-edit-practical-framework/)
20. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, Ioannis Antonoglou, Julian Schrittwieser, Amelia Glaese, Jilin Chen, Emily Pitler, Timothy Lillicrap, Angeliki Lazari… — [Gemini: A Family of Highly Capable Multimodal Models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/)
21. Zhaochen Liu, Limeng Qiao, Xiangxiang Chu, Lin Ma, and Tingting Jiang. 2025b. Towards efficient foundation model for zero-shot amodal segmentation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 20254–20264. [find](https://scholar.google.com/scholar?q=Zhaochen+Liu%2C+Limeng+Qiao%2C+Xiangxiang+Chu%2C+Lin+Ma%2C+and+Tingting+Jiang%2E+2025b%2E+Towards+efficient+foundation+model+for+zero%2Dshot+amodal+segmentation%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+Re)
22. Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073. [find](https://scholar.google.com/scholar?q=Chenlin+Meng%2C+Yutong+He%2C+Yang+Song%2C+Jiaming+Song%2C+Jiajun+Wu%2C+Jun%2DYan+Zhu%2C+and+Stefano+Ermon%2E+2021%2E+Sdedit%3A+Guided+image+synthesis+and+editing+with+stochastic+differential+equations%2E+arXiv+preprint+arX)
23. Sunung Mun, Jinhwan Nam, Sunghyun Cho, and Jungseul Ok. 2025. Addressing text embedding leakage in diffusion-based image editing. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16451–16460. [find](https://scholar.google.com/scholar?q=Sunung+Mun%2C+Jinhwan+Nam%2C+Sunghyun+Cho%2C+and+Jungseul+Ok%2E+2025%2E+Addressing+text+embedding+leakage+in+diffusion%2Dbased+image+editing%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Conference+on+Computer+Vi)
24. Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal Dave, Pavel Tokmakov, and Carl Vondrick. 2024. pix2gestalt: Amodal segmentation by synthesizing wholes. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3931–3940. IEEE Computer Society. [find](https://scholar.google.com/scholar?q=Ege+Ozguroglu%2C+Ruoshi+Liu%2C+D%C3%ADdac+Sur%C3%ADs%2C+Dian+Chen%2C+Achal+Dave%2C+Pavel+Tokmakov%2C+and+Carl+Vondrick%2E+2024%2E+pix2gestalt%3A+Amodal+segmentation+by+synthesizing+wholes%2E+In+2024+IEEE%2FCVF+Conference+on+Computer)
25. Xingang Pan, Ayush Tewari, Thomas Leimkühler, Lingjie Liu, Abhimitra Meka, and Christian Theobalt. 2023. Drag your gan: Interactive point-based manipulation on the generative image manifold. In ACM SIGGRAPH 2023 conference proceedings, pages 1– 11. [find](https://scholar.google.com/scholar?q=Xingang+Pan%2C+Ayush+Tewari%2C+Thomas+Leimk%C3%BChler%2C+Lingjie+Liu%2C+Abhimitra+Meka%2C+and+Christian+Theobalt%2E+2023%2E+Drag+your+gan%3A+Interactive+point%2Dbased+manipulation+on+the+generative+image+manifold%2E+In+ACM+SI)
26. Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollár, and Christoph Feichtenhofer. 2024. Sam 2: Segm… [find](https://scholar.google.com/scholar?q=Nikhila+Ravi%2C+Valentin+Gabeur%2C+Yuan%2DTing+Hu%2C+Ronghang+Hu%2C+Chaitanya+Ryali%2C+Tengyu+Ma%2C+Haitham+Khedr%2C+Roman+R%C3%A4dle%2C+Chloe+Rolland%2C+Laura+Gustafson%2C+Eric+Mintun%2C+Junting+Pan%2C+Kalyan+Vasudev+Alwala%2C+Nicol)
27. Team Seedream, :, Yunpeng Chen, Yu Gao, Lixue Gong, Meng Guo, Qiushan Guo, Zhiyao Guo, Xiaoxia Hou, Weilin Huang, Yixuan Huang, Xiaowen Jian, Huafeng Kuang, Zhichao Lai, Fanshi Li, Liang Li, Xiaochen Lian, Chao Liao, Liyang Liu, and 32 others. 2025. Seedream 4.0: Toward next-generation multimodal im… — [arXiv:2509.20427](https://arxiv.org/abs/2509.20427) [find](https://scholar.google.com/scholar?q=Team+Seedream%2C+%3A%2C+Yunpeng+Chen%2C+Yu+Gao%2C+Lixue+Gong%2C+Meng+Guo%2C+Qiushan+Guo%2C+Zhiyao+Guo%2C+Xiaoxia+Hou%2C+Weilin+Huang%2C+Yixuan+Huang%2C+Xiaowen+Jian%2C+Huafeng+Kuang%2C+Zhichao+Lai%2C+Fanshi+Li%2C+Liang+Li%2C+Xiaochen+)
28. Qwen Team. 2025. Qwen3-max: Just scale it. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2025%2E+Qwen3%2Dmax%3A+Just+scale+it%2E)
29. Yuhan Wang, Siwei Yang, Bingchen Zhao, Letian Zhang, Qing Liu, Yuyin Zhou, and Cihang Xie. 2025. Gpt-image-edit-1.5m: A million-scale, gpt-generated image dataset. Preprint, arXiv:2507.21033. — [arXiv:2507.21033](https://arxiv.org/abs/2507.21033) [find](https://scholar.google.com/scholar?q=Yuhan+Wang%2C+Siwei+Yang%2C+Bingchen+Zhao%2C+Letian+Zhang%2C+Qing+Liu%2C+Yuyin+Zhou%2C+and+Cihang+Xie%2E+2025%2E+Gpt%2Dimage%2Dedit%2D1%2E5m%3A+A+million%2Dscale%2C+gpt%2Dgenerated+image+dataset%2E+Preprint%2C+arXiv%3A2507%2E21033%2E+%E2%80%94+%5BarXiv)
30. Runpu Wei, Zijin Yin, Shuo Zhang, Lanxiang Zhou, Xueyi Wang, Chao Ban, Tianwei Cao, Hao Sun, Zhongjiang He, Kongming Liang, and Zhanyu Ma. 2025. Omnieraser: Remove objects and their effects in images with paired video-frame data. arXiv preprint arXiv:2501.07397. — [arXiv:2501.07397](https://arxiv.org/abs/2501.07397) [find](https://scholar.google.com/scholar?q=Runpu+Wei%2C+Zijin+Yin%2C+Shuo+Zhang%2C+Lanxiang+Zhou%2C+Xueyi+Wang%2C+Chao+Ban%2C+Tianwei+Cao%2C+Hao+Sun%2C+Zhongjiang+He%2C+Kongming+Liang%2C+and+Zhanyu+Ma%2E+2025%2E+Omnieraser%3A+Remove+objects+and+their+effects+in+images+)
31. Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xingrun Xing, Ruiran Yan, Chaofan Li, Shuting Wang, Tiejun Huang, and Zheng Liu. 2025. Omnigen: Unified image generation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 13294–13304. [find](https://scholar.google.com/scholar?q=Shitao+Xiao%2C+Yueze+Wang%2C+Junjie+Zhou%2C+Huaying+Yuan%2C+Xingrun+Xing%2C+Ruiran+Yan%2C+Chaofan+Li%2C+Shuting+Wang%2C+Tiejun+Huang%2C+and+Zheng+Liu%2E+2025%2E+Omnigen%3A+Unified+image+generation%2E+In+Proceedings+of+the+Comp)
32. Hongshen Xu, Zihan Wang, Zichen Zhu, Lei Pan, Xingyu Chen, Shuai Fan, Lu Chen, and Kai Yu. 2025. [Alignment for efficient tool calling of large language models](https://md.research.elamur.ai/free/en/papers/xu-2025-alignment-efficient-tool-calling-large/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 17787–17803.
33. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
34. Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas S Huang. 2019. Free-form image inpainting with gated convolution. In Proceedings of the IEEE/CVF international conference on computer vision, pages 4471–4480. [find](https://scholar.google.com/scholar?q=Jiahui+Yu%2C+Zhe+Lin%2C+Jimei+Yang%2C+Xiaohui+Shen%2C+Xin+Lu%2C+and+Thomas+S+Huang%2E+2019%2E+Free%2Dform+image+inpainting+with+gated+convolution%2E+In+Proceedings+of+the+IEEE%2FCVF+international+conference+on+computer+v)
35. Qifan Yu, Wei Chow, Zhongqi Yue, Kaihang Pan, Yang Wu, Xiaoyang Wan, Juncheng Li, Siliang Tang, Hanwang Zhang, and Yueting Zhuang. 2025. Anyedit: Mastering unified high-quality image editing for any idea. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 26125–26135. [find](https://scholar.google.com/scholar?q=Qifan+Yu%2C+Wei+Chow%2C+Zhongqi+Yue%2C+Kaihang+Pan%2C+Yang+Wu%2C+Xiaoyang+Wan%2C+Juncheng+Li%2C+Siliang+Tang%2C+Hanwang+Zhang%2C+and+Yueting+Zhuang%2E+2025%2E+Anyedit%3A+Mastering+unified+high%2Dquality+image+editing+for+any+i)
36. Hao Zhang, Mengsi Lyu, Chenrui He, Yulong Ao, and Yonghua Lin. 2025a. [Trimtokenator: Towards adaptive visual token pruning for large multimodal models](https://md.research.elamur.ai/free/en/papers/zhang-2026-trimtokenator-adaptive-visual-token-pruning/). arXiv preprint arXiv:2509.00320.
37. Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, and Yu Su. 2023a. Magicbrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems, 36:31428–31449. [find](https://scholar.google.com/scholar?q=Kai+Zhang%2C+Lingbo+Mo%2C+Wenhu+Chen%2C+Huan+Sun%2C+and+Yu+Su%2E+2023a%2E+Magicbrush%3A+A+manually+annotated+dataset+for+instruction%2Dguided+image+editing%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%3A31428)
38. Lvmin Zhang and Maneesh Agrawala. 2024. Transparent image layer diffusion using latent transparency. arXiv preprint arXiv:2402.17113. — [arXiv:2402.17113](https://arxiv.org/abs/2402.17113) [find](https://scholar.google.com/scholar?q=Lvmin+Zhang+and+Maneesh+Agrawala%2E+2024%2E+Transparent+image+layer+diffusion+using+latent+transparency%2E+arXiv+preprint+arXiv%3A2402%2E17113%2E+%E2%80%94+%5BarXiv%3A2402%2E17113%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E17113%29)
39. Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2023b. Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3836–3847. [find](https://scholar.google.com/scholar?q=Lvmin+Zhang%2C+Anyi+Rao%2C+and+Maneesh+Agrawala%2E+2023b%2E+Adding+conditional+control+to+text%2Dto%2Dimage+diffusion+models%2E+In+Proceedings+of+the+IEEE%2FCVF+international+conference+on+computer+vision%2C+pages+3836)
40. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595. [find](https://scholar.google.com/scholar?q=Richard+Zhang%2C+Phillip+Isola%2C+Alexei+A+Efros%2C+Eli+Shechtman%2C+and+Oliver+Wang%2E+2018%2E+The+unreasonable+effectiveness+of+deep+features+as+a+perceptual+metric%2E+In+Proceedings+of+the+IEEE+conference+on+com)
41. Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, and Yi Yang. 2025b. In-context edit: Enabling instructional image editing with in-context generation in large scale diffusion transformer. arXiv preprint arXiv:2504.20690. — [arXiv:2504.20690](https://arxiv.org/abs/2504.20690) [find](https://scholar.google.com/scholar?q=Zechuan+Zhang%2C+Ji+Xie%2C+Yu+Lu%2C+Zongxin+Yang%2C+and+Yi+Yang%2E+2025b%2E+In%2Dcontext+edit%3A+Enabling+instructional+image+editing+with+in%2Dcontext+generation+in+large+scale+diffusion+transformer%2E+arXiv+preprint+ar)

*Updated 2 November 2026*