---
title: "VIDA — paper by Liu et al. (2026) — summary and ideas"
description: "Interior design clients often submit brief, vague requests with photos. 38 references. Among them: 0."
authors: ["Yanshan Liu", "Hongbo Zhang", "Zhen Sun", "Jiaheng Wei", "Kaishun Wu"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1687/"
doi: "10.18653/v1/2026.findings-acl.1687"
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/liu-2026-vida-visual-intent-driven-design/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2026-vida-visual-intent-driven-design/)

[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/47/) / VIDA: A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification

# VIDA: A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification

**Authors:** Yanshan Liu, [Hongbo Zhang](https://md.research.elamur.ai/free/en/authors/hongbo-zhang/), Zhen Sun, [Jiaheng Wei](https://md.research.elamur.ai/free/en/authors/jiaheng-wei/) and Kaishun Wu · **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.1687/) · [PDF](https://aclanthology.org/2026.findings-acl.1687.pdf) · [DOI 10.18653/v1/2026.findings-acl.1687](https://doi.org/10.18653/v1/2026.findings-acl.1687) · [OpenAlex](https://openalex.org/W7166876588)

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

## Summary
Interior design clients often submit brief, vague requests with photos. Human designers resolve these by asking targeted questions in a sensible order: layout and other essentials first, decorative details later. Current vision-language models lack this skill. When fine-tuned on dialogue, they also tend to lose track of the image ("modality forgetting") and ask hallucinated or off-topic questions.

The authors build VIDA, an assistant that produces visually grounded clarification questions ranked by priority. Training has two stages: imitation via supervised fine-tuning, then reinforcement learning with Group Sequence Policy Optimization (GSPO). The RL stage uses a hierarchical reward with Dynamic Intent Binding, which rewards the model for addressing high-priority missing constraints. To support this work, they release InteriorClarify, a benchmark of real consultations labeled by professionals with a three-level importance scheme.

VIDA outperforms VLM and LLM baselines on strategic alignment and intent accuracy, and it recovers the visual grounding lost under plain fine-tuning. This matters for building proactive assistants in professional consultation domains.

## Key points
- **InteriorClarify dataset:** 1,016 cases. About 85% come from Chinese community platforms (REDNote, Zhihu, Douban, Tieba), about 5% from online chat logs and about 10% from offline recordings.
  - 821 cases include real room photos.
  - The 195 text-only cases received images generated with Qwen-image.
  - The data was translated from Chinese using Qwen2.5-7B-Instruct and Baidu Translate.
- **Annotation scheme:** 10 professional designers labeled missing information across nine design elements. Each element is assigned a tier: L3 (critical), L2 (influential) or L1 (refinement).
- **Automatic results:** VIDA reaches 49.02% Strategic Alignment Score (SAS) and 82.35% K-RME. That is a 20.59% SAS gain over SFT baselines.
- **Expert study:** In a blind comparison with ties excluded, practitioners preferred VIDA 73.2% of the time versus 26.8% for the baseline.
- **Limitations:**
  - The model still makes errors in fine-grained spatial reasoning in cluttered scenes.
  - Strategy overfitting reduces the variety of question phrasing.
  - The data reflects Chinese design norms, which may limit generalization.
  - Some images are synthetic.

*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

- [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 · 53 works · 1,367 citations

Also on the byline: [Beijing Wuzi University](https://ror.org/00bd1d647).

📚 Shelves (7): [🖥️ 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 133 works · [⚙️ Control and Systems Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/control-and-systems-engineering/) · 45 works

🧭 Topics (1): [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Yanshan Liu, Hongbo Zhang, Zhen Sun, Jiaheng Wei and Kaishun Wu. 2026. VIDA: A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification. 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{liu2026vida,
  title = {{VIDA: A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification}},
  author = {Yanshan Liu, Hongbo Zhang, Zhen Sun, Jiaheng Wei and Kaishun Wu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1687},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1687}
}
```

- [← previous VET: Verifiable Execution Tracing for Reliable Text-to-SQL Generation](https://md.research.elamur.ai/free/en/papers/wang-2026-vet-verifiable-execution-tracing-reliable/)
- [next → Vietnamese Automatic Speech Recognition: A Revisit](https://md.research.elamur.ai/free/en/papers/vu-2026-vietnamese-automatic-speech-recognition-revisit/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/47/)

## References

38 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, and 1 others. 2022. [Flamingo: A visual language model for few-shot learning](https://md.research.elamur.ai/free/en/papers/alayrac-2022-flamingo-visual-language-model-few/). In Advances in Neural Information Processing Systems, volume 35, page…
2. Mohammad Aliannejadi, Julia Gisle, Aleksandr Chuklin, Jeff Dalton, and Mikhail Burtsev. 2021. Building and evaluating open-domain dialogue corpora with clarifying questions. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4473–4484, Online and Punta C… [find](https://scholar.google.com/scholar?q=Mohammad+Aliannejadi%2C+Julia+Gisle%2C+Aleksandr+Chuklin%2C+Jeff+Dalton%2C+and+Mikhail+Burtsev%2E+2021%2E+Building+and+evaluating+open%2Ddomain+dialogue+corpora+with+clarifying+questions%2E+In+Proceedings+of+the+2021)
3. Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, and W. Bruce Croft. 2019. Asking clarifying questions in open-domain information-seeking conversations. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 475–484, Paris, France… [find](https://scholar.google.com/scholar?q=Mohammad+Aliannejadi%2C+Hamed+Zamani%2C+Fabio+Crestani%2C+and+W%2E+Bruce+Croft%2E+2019%2E+Asking+clarifying+questions+in+open%2Ddomain+information%2Dseeking+conversations%2E+In+Proceedings+of+the+42nd+International+ACM)
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in Neural Information Processing Systems, 33:1877–1901.
5. Yue Feng, Hossein A. Rahmani, Aldo Lipani, and Emine Yilmaz. 2023. Towards asking clarification questions for information seeking on task-oriented dialogues. Preprint, arXiv:2305.13690. — [arXiv:2305.13690](https://arxiv.org/abs/2305.13690) [find](https://scholar.google.com/scholar?q=Yue+Feng%2C+Hossein+A%2E+Rahmani%2C+Aldo+Lipani%2C+and+Emine+Yilmaz%2E+2023%2E+Towards+asking+clarification+questions+for+information+seeking+on+task%2Doriented+dialogues%2E+Preprint%2C+arXiv%3A2305%2E13690%2E+%E2%80%94+%5BarXiv%3A2305%2E)
6. Menghong Guan, Subrota Kumar Mondal, Hong-Ning Dai, and Haiyong Bao. 2023. Reinforcement learning-driven deep question generation with rich semantics. Information Processing and Management, 60(2). [find](https://scholar.google.com/scholar?q=Menghong+Guan%2C+Subrota+Kumar+Mondal%2C+Hong%2DNing+Dai%2C+and+Haiyong+Bao%2E+2023%2E+Reinforcement+learning%2Ddriven+deep+question+generation+with+rich+semantics%2E+Information+Processing+and+Management%2C+60%282%29%2E)
7. Xiang Hu, Zuijie Wen, Yafang Wang, Xiaolong Li, and Gerard De Melo. 2020. Interactive question clarification in dialogue via reinforcement learning. In Proceedings of the 28th International Conference on Computational Linguistics: Industry Track, pages 78–89, Online. International Committee on Compu… [find](https://scholar.google.com/scholar?q=Xiang+Hu%2C+Zuijie+Wen%2C+Yafang+Wang%2C+Xiaolong+Li%2C+and+Gerard+De+Melo%2E+2020%2E+Interactive+question+clarification+in+dialogue+via+reinforcement+learning%2E+In+Proceedings+of+the+28th+International+Conference)
8. Pu Jian, Donglei Yu, Wen Yang, Shuo Ren, and Jiajun Zhang. 2025. [Teaching vision-language models to ask: Resolving ambiguity in visual questions](https://md.research.elamur.ai/free/en/papers/jian-2025-teaching-vision-language-models-ask/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3619–3638. Association for Compu…
9. Kasia Kobalczyk, Nicolás Astorga, Tennison Liu, and Mihaela van der Schaar. 2025. Active task disambiguation with LLMs. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Kasia+Kobalczyk%2C+Nicol%C3%A1s+Astorga%2C+Tennison+Liu%2C+and+Mihaela+van+der+Schaar%2E+2025%2E+Active+task+disambiguation+with+LLMs%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2E)
10. Vaibhav Kumar and Alan W Black. 2020. Clarq: A large-scale and diverse dataset for clarification question generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7296–7301, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Vaibhav+Kumar+and+Alan+W+Black%2E+2020%2E+Clarq%3A+A+large%2Dscale+and+diverse+dataset+for+clarification+question+generation%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+Lin)
11. Wai-Chung Kwan, Hong-ru Wang, Huimin Wang, and Kam-Fai Wong. 2023. A survey on recent advances and challenges in reinforcement learning methods for task-oriented dialogue policy learning. Machine Intelligence Research. [find](https://scholar.google.com/scholar?q=Wai%2DChung+Kwan%2C+Hong%2Dru+Wang%2C+Huimin+Wang%2C+and+Kam%2DFai+Wong%2E+2023%2E+A+survey+on+recent+advances+and+challenges+in+reinforcement+learning+methods+for+task%2Doriented+dialogue+policy+learning%2E+Machine+Inte)
12. Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. [Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation](https://md.research.elamur.ai/free/en/papers/li-2022-blip-bootstrapping-language-image-pre/). In Proceedings of the 39th International Conference on Machine Learning (ICML), pages 12888–12900.
13. Ling Li, Yao Zhou, Yuxuan Liang, Fugee Tsung, and Jiaheng Wei. 2025. Recognition through reasoning: Reinforcing image geo-localization with large vision-language models. arXiv preprint arXiv:2506.14674. — [arXiv:2506.14674](https://arxiv.org/abs/2506.14674) [find](https://scholar.google.com/scholar?q=Ling+Li%2C+Yao+Zhou%2C+Yuxuan+Liang%2C+Fugee+Tsung%2C+and+Jiaheng+Wei%2E+2025%2E+Recognition+through+reasoning%3A+Reinforcing+image+geo%2Dlocalization+with+large+vision%2Dlanguage+models%2E+arXiv+preprint+arXiv%3A2506%2E1467)
14. Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West, Alexander Koller, Swabha Swayamdipta, Noah A Smith, and Yejin Choi. 2023. [We’re afraid language models aren’t modeling ambiguity](https://md.research.elamur.ai/free/en/papers/liu-2023-we-re-afraid-language-models/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7…
15. Brielen Madureira and David Schlangen. 2023. [Instruction clarification requests in multimodal collaborative dialogue games: Tasks, and an analysis of the codraw dataset](https://md.research.elamur.ai/free/en/papers/madureira-2023-instruction-clarification-requests-multimodal-collaborative/). Preprint, arXiv:2302.14406.
16. Ninareh Mehrabi, Mohammad Alouf, Apurv Sharma, Anurag Rao, and Ahmad Beirami. 2023. Resolving ambiguities in text-to-image generative models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pages 7051–7074. [find](https://scholar.google.com/scholar?q=Ninareh+Mehrabi%2C+Mohammad+Alouf%2C+Apurv+Sharma%2C+Anurag+Rao%2C+and+Ahmad+Beirami%2E+2023%2E+Resolving+ambiguities+in+text%2Dto%2Dimage+generative+models%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Associati)
17. Fangwen Mu, Lin Shi, Song Wang, Zhuohao Yu, Binquan Zhang, Chenxue Wang, Shengze Liu, and Qing Wang. 2024. Clarifygpt: A framework for enhancing llm-based code generation via requirements clarification. In Proceedings of the 2024 ACM International Conference on the Foundations of Software Engineerin… [find](https://scholar.google.com/scholar?q=Fangwen+Mu%2C+Lin+Shi%2C+Song+Wang%2C+Zhuohao+Yu%2C+Binquan+Zhang%2C+Chenxue+Wang%2C+Shengze+Liu%2C+and+Qing+Wang%2E+2024%2E+Clarifygpt%3A+A+framework+for+enhancing+llm%2Dbased+code+generation+via+requirements+clarificatio)
18. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, and Ryan Lowe. 2022.… — [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
19. Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, and Huan Sun. 2019. Reinforced dynamic reasoning for conversational question generation. Preprint, arXiv:1907.12667. [find](https://scholar.google.com/scholar?q=Boyuan+Pan%2C+Hao+Li%2C+Ziyu+Yao%2C+Deng+Cai%2C+and+Huan+Sun%2E+2019%2E+Reinforced+dynamic+reasoning+for+conversational+question+generation%2E+Preprint%2C+arXiv%3A1907%2E12667%2E)
20. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). arXiv preprint arXiv:2305.18290.
21. Kimia Ramezan, Alireza Amiri Bavandpour, Yifei Yuan, Clemencia Siro, and Mohammad Aliannejadi. 2025. [find](https://scholar.google.com/scholar?q=Kimia+Ramezan%2C+Alireza+Amiri+Bavandpour%2C+Yifei+Yuan%2C+Clemencia+Siro%2C+and+Mohammad+Aliannejadi%2E+2025%2E)
22. Multi-turn multi-modal question clarification for enhanced conversational understanding. Preprint, arXiv:2502.11442. — [arXiv:2502.11442](https://arxiv.org/abs/2502.11442) [find](https://scholar.google.com/scholar?q=Multi%2Dturn+multi%2Dmodal+question+clarification+for+enhanced+conversational+understanding%2E+Preprint%2C+arXiv%3A2502%2E11442%2E+%E2%80%94+%5BarXiv%3A2502%2E11442%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2502%2E11442%29)
23. Sudha Rao and Hal Daume III. 2018. Learning to ask good questions: Ranking clarification questions using neural expected value of perfect information. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2737–2746, Melbourne, Austr… [find](https://scholar.google.com/scholar?q=Sudha+Rao+and+Hal+Daume+III%2E+2018%2E+Learning+to+ask+good+questions%3A+Ranking+clarification+questions+using+neural+expected+value+of+perfect+information%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+)
24. Sudha Rao and Hal Daumé. 2019. Answer-based adversarial training for generating clarification questions. Preprint, arXiv:1904.02281. [find](https://scholar.google.com/scholar?q=Sudha+Rao+and+Hal+Daum%C3%A9%2E+2019%2E+Answer%2Dbased+adversarial+training+for+generating+clarification+questions%2E+Preprint%2C+arXiv%3A1904%2E02281%2E)
25. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). Preprint, arXiv:2402.03300.
26. Zhengxiang Shi, Yue Feng, and Aldo Lipani. 2022. Learning to execute actions or ask clarification questions. Preprint, arXiv:2204.08373. [find](https://scholar.google.com/scholar?q=Zhengxiang+Shi%2C+Yue+Feng%2C+and+Aldo+Lipani%2E+2022%2E+Learning+to+execute+actions+or+ask+clarification+questions%2E+Preprint%2C+arXiv%3A2204%2E08373%2E)
27. Zhengxiang Shi, Jerome Ramos, To Eun Kim, Xi Wang, Hossein A. Rahmani, and Aldo Lipani. 2023. When and what to ask through world states and text instructions: Iglu nlp challenge solution. Preprint, arXiv:2305.05754. — [arXiv:2305.05754](https://arxiv.org/abs/2305.05754) [find](https://scholar.google.com/scholar?q=Zhengxiang+Shi%2C+Jerome+Ramos%2C+To+Eun+Kim%2C+Xi+Wang%2C+Hossein+A%2E+Rahmani%2C+and+Aldo+Lipani%2E+2023%2E+When+and+what+to+ask+through+world+states+and+text+instructions%3A+Iglu+nlp+challenge+solution%2E+Preprint%2C+ar)
28. Han Sun, Qin Li, Peixin Wang, and Min Zhang. 2026. Mitigating object hallucinations in lvlms via attention imbalance rectification. arXiv preprint arXiv:2603.24058. — [arXiv:2603.24058](https://arxiv.org/abs/2603.24058) [find](https://scholar.google.com/scholar?q=Han+Sun%2C+Qin+Li%2C+Peixin+Wang%2C+and+Min+Zhang%2E+2026%2E+Mitigating+object+hallucinations+in+lvlms+via+attention+imbalance+rectification%2E+arXiv+preprint+arXiv%3A2603%2E24058%2E+%E2%80%94+%5BarXiv%3A2603%2E24058%5D%28https%3A%2F%2Farxiv%2E)
29. Zhen Sun, Ziyi Zhang, Zeren Luo, Zhiyuan Zhong, Zeyang Sha, Tianshuo Cong, Zheng Li, Shiwen Cui, Weiqiang Wang, Jiaheng Wei, and 1 others. 2025. Can vlms detect and localize fine-grained ai-edited images? arXiv preprint arXiv:2505.15644. — [arXiv:2505.15644](https://arxiv.org/abs/2505.15644) [find](https://scholar.google.com/scholar?q=Zhen+Sun%2C+Ziyi+Zhang%2C+Zeren+Luo%2C+Zhiyuan+Zhong%2C+Zeyang+Sha%2C+Tianshuo+Cong%2C+Zheng+Li%2C+Shiwen+Cui%2C+Weiqiang+Wang%2C+Jiaheng+Wei%2C+and+1+others%2E+2025%2E+Can+vlms+detect+and+localize+fine%2Dgrained+ai%2Dedited+ima)
30. Shuai Wang, Zhenhua Liu, Jiaheng Wei, Xuanwu Yin, Dong Li, and Emad Barsoum. 2025. Athena: Enhancing multimodal reasoning with data-efficient process reward models. arXiv preprint arXiv:2506.09532. — [arXiv:2506.09532](https://arxiv.org/abs/2506.09532) [find](https://scholar.google.com/scholar?q=Shuai+Wang%2C+Zhenhua+Liu%2C+Jiaheng+Wei%2C+Xuanwu+Yin%2C+Dong+Li%2C+and+Emad+Barsoum%2E+2025%2E+Athena%3A+Enhancing+multimodal+reasoning+with+data%2Defficient+process+reward+models%2E+arXiv+preprint+arXiv%3A2506%2E09532%2E+%E2%80%94+)
31. Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang, An Yang, Bowen Yu, Chen Cheng, Dayiheng Liu, Deqing Li, and 20 others. 2025. [Qwen-image technical report](https://md.research.elamur.ai/free/en/papers/wu-2025-qwen-image-technical-report/). Preprint, arXiv:250…
32. Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, and Pengcheng Yang. 2019. Asking clarification questions in knowledge-based question answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Pro… [find](https://scholar.google.com/scholar?q=Jingjing+Xu%2C+Yuechen+Wang%2C+Duyu+Tang%2C+Nan+Duan%2C+and+Pengcheng+Yang%2E+2019%2E+Asking+clarification+questions+in+knowledge%2Dbased+question+answering%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Metho)
33. Yifei Yuan, Clemencia Siro, Mohammad Aliannejadi, Maarten De Rijke, and Wai Lam. 2024. Asking multimodal clarifying questions in mixed-initiative conversational search. In Proceedings of the ACM Web Conference 2024, pages 1474–1485, Singapore, Singapore. ACM. [find](https://scholar.google.com/scholar?q=Yifei+Yuan%2C+Clemencia+Siro%2C+Mohammad+Aliannejadi%2C+Maarten+De+Rijke%2C+and+Wai+Lam%2E+2024%2E+Asking+multimodal+clarifying+questions+in+mixed%2Dinitiative+conversational+search%2E+In+Proceedings+of+the+ACM+Web+C)
34. Hamed Zamani, Gord Lueck, Everest Chen, Rodolfo Quispe, Flint Luu, and Nick Craswell. 2020. Mimics: A large-scale data collection for search clarification. Preprint, arXiv:2006.10174. — [arXiv:2006.10174](https://arxiv.org/abs/2006.10174) [find](https://scholar.google.com/scholar?q=Hamed+Zamani%2C+Gord+Lueck%2C+Everest+Chen%2C+Rodolfo+Quispe%2C+Flint+Luu%2C+and+Nick+Craswell%2E+2020%2E+Mimics%3A+A+large%2Dscale+data+collection+for+search+clarification%2E+Preprint%2C+arXiv%3A2006%2E10174%2E+%E2%80%94+%5BarXiv%3A2006%2E10)
35. J. D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, and Qian Yang. 2023. Why johnny can’t prompt: How non-ai experts try (and fail) to design llm prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, pages 1–21. [find](https://scholar.google.com/scholar?q=J%2E+D%2E+Zamfirescu%2DPereira%2C+Richmond+Y%2E+Wong%2C+Bjoern+Hartmann%2C+and+Qian+Yang%2E+2023%2E+Why+johnny+can%E2%80%99t+prompt%3A+How+non%2Dai+experts+try+%28and+fail%29+to+design+llm+prompts%2E+In+Proceedings+of+the+2023+CHI+Confe)
36. He Zhang, Ying Sun, Weiyu Guo, Yafei Liu, Haonan Lu, Xiaodong Lin, and Hui Xiong. 2023. Interactive interior design recommendation via coarse-to-fine multimodal reinforcement learning. In Proceedings of the 31st ACM International Conference on Multimedia, pages 6472–6480. ACM. [find](https://scholar.google.com/scholar?q=He+Zhang%2C+Ying+Sun%2C+Weiyu+Guo%2C+Yafei+Liu%2C+Haonan+Lu%2C+Xiaodong+Lin%2C+and+Hui+Xiong%2E+2023%2E+Interactive+interior+design+recommendation+via+coarse%2Dto%2Dfine+multimodal+reinforcement+learning%2E+In+Proceedings+)
37. Michael J. Q. Zhang, W. Bradley Knox, and Eunsol Choi. 2025a. Modeling future conversation turns to teach llms to ask clarifying questions. Preprint, arXiv:2410.13788. [find](https://scholar.google.com/scholar?q=Michael+J%2E+Q%2E+Zhang%2C+W%2E+Bradley+Knox%2C+and+Eunsol+Choi%2E+2025a%2E+Modeling+future+conversation+turns+to+teach+llms+to+ask+clarifying+questions%2E+Preprint%2C+arXiv%3A2410%2E13788%2E)
38. Ziyi Zhang, Zhen Sun, Zongmin Zhang, Zifan Peng, Yuemeng Zhao, Zichun Wang, Zeren Luo, Ruiting Zuo, and Xinlei He. 2025b. "I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments. arXiv preprint arXiv:2505.04488. — [arXiv:2505.04488](https://arxiv.org/abs/2505.04488) [find](https://scholar.google.com/scholar?q=Ziyi+Zhang%2C+Zhen+Sun%2C+Zongmin+Zhang%2C+Zifan+Peng%2C+Yuemeng+Zhao%2C+Zichun+Wang%2C+Zeren+Luo%2C+Ruiting+Zuo%2C+and+Xinlei+He%2E+2025b%2E+%22I+Can+See+Forever%21%22%3A+Evaluating+Real%2Dtime+VideoLLMs+for+Assisting+Individuals)

*Updated 1 November 2026*