---
title: "Beyond Unimodal Shortcuts — paper by Ma et al. (2026)"
description: "To counter this, they propose Modality-aware Consistency Reasoning (MCR), which has two stages: MRSI fine-tunes the… 62 references."
authors: ["Jinlong Ma", "Yu Zhang", "Xuefeng Bai", "Kehai Chen", "Yuwei Wang", "Zeming Liu", "Jun Yu", "Min Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.2162/"
doi: "10.18653/v1/2026.findings-acl.2162"
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/ma-2026-beyond-unimodal-shortcuts-mllms-as/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ma-2026-beyond-unimodal-shortcuts-mllms-as/)

[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/25/) / Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition

# Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition

**Authors:** Jinlong Ma, [Yu Zhang](https://md.research.elamur.ai/free/en/authors/yu-zhang/), [Xuefeng Bai](https://md.research.elamur.ai/free/en/authors/xuefeng-bai/), [Kehai Chen](https://md.research.elamur.ai/free/en/authors/kehai-chen/), [Yuwei Wang](https://md.research.elamur.ai/free/en/authors/yuwei-wang/), [Zeming Liu](https://md.research.elamur.ai/free/en/authors/zeming-liu/), [Jun Yu](https://md.research.elamur.ai/free/en/authors/jun-yu/) and [Min Zhang](https://md.research.elamur.ai/free/en/authors/min-zhang/) · **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.2162/) · [PDF](https://aclanthology.org/2026.findings-acl.2162.pdf) · [DOI 10.18653/v1/2026.findings-acl.2162](https://doi.org/10.18653/v1/2026.findings-acl.2162) · [OpenAlex](https://openalex.org/W7166800304)

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

## Summary
Grounded Multimodal Named Entity Recognition (GMNER) asks a system to find named entities in a sentence, label their types, and link each one to a bounding box in the paired image, or mark it as absent from the image. Earlier work mostly used MLLMs as helper modules inside cascaded pipelines. This paper instead has a single MLLM solve the whole task end-to-end as generative reasoning. The authors find that such models suffer from modality bias. Textual bias makes the model ignore the image: it boxes a person who is not shown. Visual bias makes it ignore the text: it reports an entity seen only in the image. To counter this, they propose Modality-aware Consistency Reasoning (MCR), which has two stages:
- **MRSI** fine-tunes the model on reasoning chains written in several styles and built around explicit task constraints.
- **CVO** then refines these reasoning traces with GRPO, using verifiable rewards.

Applied to Qwen2.5-VL and MiMo-VL, MCR outperforms baselines on GMNER, MNER, visual grounding and FMNERG benchmarks. The results suggest that enforcing explicit cross-modal checks matters for reliable grounding.

## Key points
- MRSI is built on four constraints: entity recognition, type classification, visual entailment, and visual grounding. The reasoning chains are generated from gold labels using templates, LLMs or MLLMs.
- Using several reasoning styles, rather than one, gave higher rewards and F1 in CVO and made training more stable on Qwen2.5VL-7B and MimoVL-7B.
- In an attention analysis, textual-bias errors put only 59.6% of attention on visual tokens. Correct predictions put 71.8% there, and MCR raised this to 74.4%.
- On GMNER, F1 was 63.6 for basic SFT and 70.6 for MCR. Extending SFT to the same 19 h training budget reached only 64.8. Inference time was 6 min for MCR versus 3 min for SFT.
- The method is limited by the MLLM's built-in knowledge, so it may handle unseen entities poorly. Code and data are available at github.com/aaaalonga/MCR.

*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

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 185 works · 29,140 citations
- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) — University, Beijing, China · 86 works · 9,097 citations
- [Institute of Computing Technology](https://md.research.elamur.ai/free/en/labs/institute-of-computing-technology/) — Research institute, Beijing, China · 57 works · 3,782 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 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 (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [🏷️ Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · 214 works

## Cite

Cite as: Jinlong Ma, Yu Zhang, Xuefeng Bai, Kehai Chen, Yuwei Wang, Zeming Liu, Jun Yu and Min Zhang. 2026. Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition. 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{ma2026beyond,
  title = {{Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition}},
  author = {Jinlong Ma, Yu Zhang, Xuefeng Bai, Kehai Chen, Yuwei Wang, Zeming Liu, Jun Yu and Min Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2162},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2162}
}
```

- [← previous Beyond Uniform SVD: Dual-Level Optimization across Columns and Modules for LLM Compression](https://md.research.elamur.ai/free/en/papers/xv-2026-beyond-uniform-svd-dual-level/)
- [next → Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text](https://md.research.elamur.ai/free/en/papers/greenfeld-2026-beyond-word-boundaries-hebrew-coreference/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/)

## References

62 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Arkadeep Acharya, Brijraj Singh, and Naoyuki Onoe. 2023. Llm based generation of item-description for recommendation system. In Proceedings of the 17th ACM conference on recommender systems, pages 1204–1207. [find](https://scholar.google.com/scholar?q=Arkadeep+Acharya%2C+Brijraj+Singh%2C+and+Naoyuki+Onoe%2E+2023%2E+Llm+based+generation+of+item%2Ddescription+for+recommendation+system%2E+In+Proceedings+of+the+17th+ACM+conference+on+recommender+systems%2C+pages+120)
2. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
3. Xigang Bao, Mengyuan Tian, Luyao Wang, Zhiyuan Zha, and Biao Qin. 2024. Contrastive pre-training with multi-level alignment for grounded multimodal named entity recognition. In Proceedings of the 2024 international conference on multimedia retrieval, pages 795–803. [find](https://scholar.google.com/scholar?q=Xigang+Bao%2C+Mengyuan+Tian%2C+Luyao+Wang%2C+Zhiyuan+Zha%2C+and+Biao+Qin%2E+2024%2E+Contrastive+pre%2Dtraining+with+multi%2Dlevel+alignment+for+grounded+multimodal+named+entity+recognition%2E+In+Proceedings+of+the+2024)
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. Qiguang Chen, Libo Qin, Jinhao Liu, Dengyun Peng, Jiannan Guan, Peng Wang, Mengkang Hu, Yuhang Zhou, Te Gao, and Wanxiang Che. 2025a. [Towards reasoning era: A survey of long chain-of-thought for reasoning large language models](https://md.research.elamur.ai/free/en/papers/chen-2025-towards-reasoning-era-survey-long/). arXiv preprint arXiv:2503.09567.
6. Shuang Chen, Yue Guo, Zhaochen Su, Yafu Li, Yulun Wu, Jiacheng Chen, Jiayu Chen, Weijie Wang, Xiaoye Qu, and Yu Cheng. 2025b. Advancing multimodal reasoning: From optimized cold start to staged reinforcement learning. arXiv preprint arXiv:2506.04207. — [arXiv:2506.04207](https://arxiv.org/abs/2506.04207) [find](https://scholar.google.com/scholar?q=Shuang+Chen%2C+Yue+Guo%2C+Zhaochen+Su%2C+Yafu+Li%2C+Yulun+Wu%2C+Jiacheng+Chen%2C+Jiayu+Chen%2C+Weijie+Wang%2C+Xiaoye+Qu%2C+and+Yu+Cheng%2E+2025b%2E+Advancing+multimodal+reasoning%3A+From+optimized+cold+start+to+staged+reinfo)
7. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Pal: Program-aided language models. In International Conference on Machine Learning, pages 10764–10799. PMLR. [find](https://scholar.google.com/scholar?q=Luyu+Gao%2C+Aman+Madaan%2C+Shuyan+Zhou%2C+Uri+Alon%2C+Pengfei+Liu%2C+Yiming+Yang%2C+Jamie+Callan%2C+and+Graham+Neubig%2E+2023%2E+Pal%3A+Program%2Daided+language+models%2E+In+International+Conference+on+Machine+Learning%2C+page)
8. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
9. Shuting He, Henghui Ding, Chang Liu, and Xudong Jiang. 2023. Grec: Generalized referring expression comprehension. arXiv preprint arXiv:2308.16182. — [arXiv:2308.16182](https://arxiv.org/abs/2308.16182) [find](https://scholar.google.com/scholar?q=Shuting+He%2C+Henghui+Ding%2C+Chang+Liu%2C+and+Xudong+Jiang%2E+2023%2E+Grec%3A+Generalized+referring+expression+comprehension%2E+arXiv+preprint+arXiv%3A2308%2E16182%2E+%E2%80%94+%5BarXiv%3A2308%2E16182%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2308%2E1618)
10. Zefeng He, Siyuan Huang, Xiaoye Qu, Yafu Li, Tong Zhu, Yu Cheng, and Yang Yang. 2026. Gems: Agent-native multimodal generation with memory and skills. arXiv preprint arXiv:2603.28088. — [arXiv:2603.28088](https://arxiv.org/abs/2603.28088) [find](https://scholar.google.com/scholar?q=Zefeng+He%2C+Siyuan+Huang%2C+Xiaoye+Qu%2C+Yafu+Li%2C+Tong+Zhu%2C+Yu+Cheng%2C+and+Yang+Yang%2E+2026%2E+Gems%3A+Agent%2Dnative+multimodal+generation+with+memory+and+skills%2E+arXiv+preprint+arXiv%3A2603%2E28088%2E+%E2%80%94+%5BarXiv%3A2603%2E28)
11. Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, and 1 others. 2025. Glm-4.1 v-thinking: Towards versatile multimodal reasoning with scalable reinforcement learning. arXiv e-prints, pages arXiv–2507. [find](https://scholar.google.com/scholar?q=Wenyi+Hong%2C+Wenmeng+Yu%2C+Xiaotao+Gu%2C+Guo+Wang%2C+Guobing+Gan%2C+Haomiao+Tang%2C+Jiale+Cheng%2C+Ji+Qi%2C+Junhui+Ji%2C+Lihang+Pan%2C+and+1+others%2E+2025%2E+Glm%2D4%2E1+v%2Dthinking%3A+Towards+versatile+multimodal+reasoning+with+)
12. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
13. Shizhou Huang, Bo Xu, Changqun Li, Jiabo Ye, and Xin Lin. 2024. Mner-mi: A multi-image dataset for multimodal named entity recognition in social media. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages… [find](https://scholar.google.com/scholar?q=Shizhou+Huang%2C+Bo+Xu%2C+Changqun+Li%2C+Jiabo+Ye%2C+and+Xin+Lin%2E+2024%2E+Mner%2Dmi%3A+A+multi%2Dimage+dataset+for+multimodal+named+entity+recognition+in+social+media%2E+In+Proceedings+of+the+2024+Joint+International+C)
14. Meihuizi Jia, Lei Shen, Xin Shen, Lejian Liao, Meng Chen, Xiaodong He, Zhendong Chen, and Jiaqi Li. 2023. Mner-qg: An end-to-end mrc framework for multimodal named entity recognition with query grounding. In Proceedings of the AAAI conference on artificial intelligence, volume 37, pages 8032–8040. [find](https://scholar.google.com/scholar?q=Meihuizi+Jia%2C+Lei+Shen%2C+Xin+Shen%2C+Lejian+Liao%2C+Meng+Chen%2C+Xiaodong+He%2C+Zhendong+Chen%2C+and+Jiaqi+Li%2E+2023%2E+Mner%2Dqg%3A+An+end%2Dto%2Dend+mrc+framework+for+multimodal+named+entity+recognition+with+query+ground)
15. Lingjie Jiang, Shaohan Huang, Xun Wu, Yixia Li, Guanhua Chen, Dongdong Zhang, and Furu Wei. 2026. Viscodex: Unified multimodal code generation via merging vision and coding models. In The Fourteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Lingjie+Jiang%2C+Shaohan+Huang%2C+Xun+Wu%2C+Yixia+Li%2C+Guanhua+Chen%2C+Dongdong+Zhang%2C+and+Furu+Wei%2E+2026%2E+Viscodex%3A+Unified+multimodal+code+generation+via+merging+vision+and+coding+models%2E+In+The+Fourteenth+I)
16. Aybora Koksal and A Aydin Alatan. 2025. Milchat: Introducing chain of thought reasoning and grpo to a multimodal small language model for remote sensing. arXiv preprint arXiv:2505.07984. — [arXiv:2505.07984](https://arxiv.org/abs/2505.07984) [find](https://scholar.google.com/scholar?q=Aybora+Koksal+and+A+Aydin+Alatan%2E+2025%2E+Milchat%3A+Introducing+chain+of+thought+reasoning+and+grpo+to+a+multimodal+small+language+model+for+remote+sensing%2E+arXiv+preprint+arXiv%3A2505%2E07984%2E+%E2%80%94+%5BarXiv%3A2505)
17. Komal Kumar, Tajamul Ashraf, Omkar Thawakar, Rao Muhammad Anwer, Hisham Cholakkal, Mubarak Shah, Ming-Hsuan Yang, Phillip HS Torr, Fahad Shahbaz Khan, and Salman Khan. 2025. Llm post-training: A deep dive into reasoning large language models. arXiv preprint arXiv:2502.21321. — [arXiv:2502.21321](https://arxiv.org/abs/2502.21321) [find](https://scholar.google.com/scholar?q=Komal+Kumar%2C+Tajamul+Ashraf%2C+Omkar+Thawakar%2C+Rao+Muhammad+Anwer%2C+Hisham+Cholakkal%2C+Mubarak+Shah%2C+Ming%2DHsuan+Yang%2C+Phillip+HS+Torr%2C+Fahad+Shahbaz+Khan%2C+and+Salman+Khan%2E+2025%2E+Llm+post%2Dtraining%3A+A+deep+)
18. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the 29th symposium on operating systems principles, pages 611–626.
19. Sicong Leng, Yun Xing, Zesen Cheng, Yang Zhou, Hang Zhang, Xin Li, Deli Zhao, Shijian Lu, Chunyan Miao, and Lidong Bing. 2024. The curse of multi-modalities: Evaluating hallucinations of large multimodal models across language, visual, and audio. arXiv preprint arXiv:2410.12787. — [arXiv:2410.12787](https://arxiv.org/abs/2410.12787) [find](https://scholar.google.com/scholar?q=Sicong+Leng%2C+Yun+Xing%2C+Zesen+Cheng%2C+Yang+Zhou%2C+Hang+Zhang%2C+Xin+Li%2C+Deli+Zhao%2C+Shijian+Lu%2C+Chunyan+Miao%2C+and+Lidong+Bing%2E+2024%2E+The+curse+of+multi%2Dmodalities%3A+Evaluating+hallucinations+of+large+multimo)
20. Bo Li, Shaolin Zhu, and Lijie Wen. 2025a. Mit-10m: A large scale parallel corpus of multilingual image translation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 5154–5167. [find](https://scholar.google.com/scholar?q=Bo+Li%2C+Shaolin+Zhu%2C+and+Lijie+Wen%2E+2025a%2E+Mit%2D10m%3A+A+large+scale+parallel+corpus+of+multilingual+image+translation%2E+In+Proceedings+of+the+31st+International+Conference+on+Computational+Linguistics%2C+pa)
21. Chengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia, Shaoguang Mao, Li Dong, Ivan Vulić, and Furu Wei. 2025b. Imagine while reasoning in space: Multimodal visualization-of-thought. arXiv preprint arXiv:2501.07542. — [arXiv:2501.07542](https://arxiv.org/abs/2501.07542) [find](https://scholar.google.com/scholar?q=Chengzu+Li%2C+Wenshan+Wu%2C+Huanyu+Zhang%2C+Yan+Xia%2C+Shaoguang+Mao%2C+Li+Dong%2C+Ivan+Vulic%CC%81%2C+and+Furu+Wei%2E+2025b%2E+Imagine+while+reasoning+in+space%3A+Multimodal+visualization%2Dof%2Dthought%2E+arXiv+preprint+arXiv%3A250)
22. Jinyuan Li, Han Li, Di Sun, Jiahao Wang, Wenkun Zhang, Zan Wang, and Gang Pan. 2024. Llms as bridges: Reformulating grounded multimodal named entity recognition. arXiv preprint arXiv:2402.09989. via reinforcement learning with textual entailment feedback. In Proceedings of the 61st annual meeting of… [find](https://scholar.google.com/scholar?q=Jinyuan+Li%2C+Han+Li%2C+Di+Sun%2C+Jiahao+Wang%2C+Wenkun+Zhang%2C+Zan+Wang%2C+and+Gang+Pan%2E+2024%2E+Llms+as+bridges%3A+Reformulating+grounded+multimodal+named+entity+recognition%2E+arXiv+preprint+arXiv%3A2402%2E09989%2E+via+r)
23. Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, and 1 others. 2025c. [From system 1 to system 2: A survey of reasoning large language models](https://md.research.elamur.ai/free/en/papers/li-2025-system-1-system-2-survey/). arXiv preprint arXiv:2502.17419.
24. Jielong Tang, Shuang Wang, Zhenxing Wang, Jianxing Yu, and Jian Yin. 2025a. Refineg: Synergizing small supervised models and llms for low-resource grounded multimodal ner. arXiv preprint arXiv:2509.10975. — [arXiv:2509.10975](https://arxiv.org/abs/2509.10975) [find](https://scholar.google.com/scholar?q=Jielong+Tang%2C+Shuang+Wang%2C+Zhenxing+Wang%2C+Jianxing+Yu%2C+and+Jian+Yin%2E+2025a%2E+Refineg%3A+Synergizing+small+supervised+models+and+llms+for+low%2Dresource+grounded+multimodal+ner%2E+arXiv+preprint+arXiv%3A2509%2E10)
25. Xinkui Lin, Yuhui Zhang, Yongxiu Xu, Kun Huang, Hongzhang Mu, Yubin Wang, Gaopeng Gou, Li Qian, Li Peng, Wei Liu, and 1 others. 2025. Makar: a multi-agent framework based knowledge-augmented reasoning for grounded multimodal named entity recognition. In Proceedings of the 2025 Conference on Empirica… [find](https://scholar.google.com/scholar?q=Xinkui+Lin%2C+Yuhui+Zhang%2C+Yongxiu+Xu%2C+Kun+Huang%2C+Hongzhang+Mu%2C+Yubin+Wang%2C+Gaopeng+Gou%2C+Li+Qian%2C+Li+Peng%2C+Wei+Liu%2C+and+1+others%2E+2025%2E+Makar%3A+a+multi%2Dagent+framework+based+knowledge%2Daugmented+reasoning)
26. Jielong Tang, Zhenxing Wang, Ziyang Gong, Jianxing Yu, Xiangwei Zhu, and Jian Yin. 2025b. Multi-grained query-guided set prediction network for grounded multimodal named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 25246–25254. [find](https://scholar.google.com/scholar?q=Jielong+Tang%2C+Zhenxing+Wang%2C+Ziyang+Gong%2C+Jianxing+Yu%2C+Xiangwei+Zhu%2C+and+Jian+Yin%2E+2025b%2E+Multi%2Dgrained+query%2Dguided+set+prediction+network+for+grounded+multimodal+named+entity+recognition%2E+In+Proceed)
27. Jintao Liu, Chenglong Liu, and Kaiwen Wei. 2024a. Multi-view prompt for fine-grained multimodal named entity recognition and grounding. In ECAI 2024, pages 2693–2700. IOS Press. [find](https://scholar.google.com/scholar?q=Jintao+Liu%2C+Chenglong+Liu%2C+and+Kaiwen+Wei%2E+2024a%2E+Multi%2Dview+prompt+for+fine%2Dgrained+multimodal+named+entity+recognition+and+grounding%2E+In+ECAI+2024%2C+pages+2693%E2%80%932700%2E+IOS+Press%2E)
28. Jielong Tang, Yang Yang, Jianxing Yu, Zhen-Xing Wang, Haoyuan Liang, Liang Yao, and Jian Yin. 2025c. Unco: Uncertainty-driven collaborative framework of large and small models for grounded multimodal ner. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, page… [find](https://scholar.google.com/scholar?q=Jielong+Tang%2C+Yang+Yang%2C+Jianxing+Yu%2C+Zhen%2DXing+Wang%2C+Haoyuan+Liang%2C+Liang+Yao%2C+and+Jian+Yin%2E+2025c%2E+Unco%3A+Uncertainty%2Ddriven+collaborative+framework+of+large+and+small+models+for+grounded+multimodal+)
29. Peipei Liu, Hong Li, Yimo Ren, Jie Liu, Shuaizong Si, Hongsong Zhu, and Limin Sun. 2024b. Hierarchical aligned multimodal learning for ner on tweet posts. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18680–18688. [find](https://scholar.google.com/scholar?q=Peipei+Liu%2C+Hong+Li%2C+Yimo+Ren%2C+Jie+Liu%2C+Shuaizong+Si%2C+Hongsong+Zhu%2C+and+Limin+Sun%2E+2024b%2E+Hierarchical+aligned+multimodal+learning+for+ner+on+tweet+posts%2E+In+Proceedings+of+the+AAAI+Conference+on+Arti)
30. Yihong Tang, Kehai Chen, Muyun Yang, Zhengyu Niu, Jing Li, Tiejun Zhao, and Min Zhang. 2025d. Thinking in character: Advancing role-playing agents with role-aware reasoning. arXiv preprint arXiv:2506.01748. — [arXiv:2506.01748](https://arxiv.org/abs/2506.01748) [find](https://scholar.google.com/scholar?q=Yihong+Tang%2C+Kehai+Chen%2C+Muyun+Yang%2C+Zhengyu+Niu%2C+Jing+Li%2C+Tiejun+Zhao%2C+and+Min+Zhang%2E+2025d%2E+Thinking+in+character%3A+Advancing+role%2Dplaying+agents+with+role%2Daware+reasoning%2E+arXiv+preprint+arXiv%3A2506%2E)
31. Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, and Jiaqi Wang. 2025. Visual-rft: Visual reinforcement fine-tuning. arXiv preprint arXiv:2503.01785. — [arXiv:2503.01785](https://arxiv.org/abs/2503.01785) [find](https://scholar.google.com/scholar?q=Ziyu+Liu%2C+Zeyi+Sun%2C+Yuhang+Zang%2C+Xiaoyi+Dong%2C+Yuhang+Cao%2C+Haodong+Duan%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+2025%2E+Visual%2Drft%3A+Visual+reinforcement+fine%2Dtuning%2E+arXiv+preprint+arXiv%3A2503%2E01785%2E+%E2%80%94+%5BarXiv%3A2503%2E01)
32. Jingqi Tong, Jixin Tang, Hangcheng Li, Yurong Mou, Ming Zhang, Jun Zhao, Yanbo Wen, Fan Song, Jiahao Zhan, Yuyang Lu, Chaoran Tao, Zhiyuan Guo, Jizhou Yu, Tianhao Cheng, Zhiheng Xi, Changhao Jiang, Zhangyue Yin, Yining Zheng, Weifeng Ge, and 5 others. 2026. Game-RL: Synthesizing multimodal verifiabl… [find](https://scholar.google.com/scholar?q=Jingqi+Tong%2C+Jixin+Tang%2C+Hangcheng+Li%2C+Yurong+Mou%2C+Ming+Zhang%2C+Jun+Zhao%2C+Yanbo+Wen%2C+Fan+Song%2C+Jiahao+Zhan%2C+Yuyang+Lu%2C+Chaoran+Tao%2C+Zhiyuan+Guo%2C+Jizhou+Yu%2C+Tianhao+Cheng%2C+Zhiheng+Xi%2C+Changhao+Jiang%2C+Zh)
33. Seungwhan Moon, Leonardo Neves, and Vitor Carvalho. 2018. Multimodal named entity recognition for short social media posts. arXiv preprint arXiv:1802.07862. [find](https://scholar.google.com/scholar?q=Seungwhan+Moon%2C+Leonardo+Neves%2C+and+Vitor+Carvalho%2E+2018%2E+Multimodal+named+entity+recognition+for+short+social+media+posts%2E+arXiv+preprint+arXiv%3A1802%2E07862%2E)
34. Hyunjong Ok, Taeho Kil, Sukmin Seo, and Jaeho Lee. 2024. Scanner: Knowledge-enhanced approach for robust multi-modal named entity recognition of unseen entities. arXiv preprint arXiv:2404.01914. [find](https://scholar.google.com/scholar?q=Hyunjong+Ok%2C+Taeho+Kil%2C+Sukmin+Seo%2C+and+Jaeho+Lee%2E+2024%2E+Scanner%3A+Knowledge%2Denhanced+approach+for+robust+multi%2Dmodal+named+entity+recognition+of+unseen+entities%2E+arXiv+preprint+arXiv%3A2404%2E01914%2E)
35. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 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/). Advances in neural information processing systems, 35:27730– 27744.
36. Fei Wang, Wenxuan Zhou, James Y Huang, Nan Xu, Sheng Zhang, Hoifung Poon, and Muhao Chen. 2024a. [mdpo: Conditional preference optimization for multimodal large language models](https://md.research.elamur.ai/free/en/papers/wang-2024-mdpo-conditional-preference-optimization-multimodal/). arXiv preprint arXiv:2406.11839.
37. Hongru Wang, Deng Cai, Wanjun Zhong, Shijue Huang, Jeff Z Pan, Zeming Liu, and Kam-Fai Wong. 2025a. Self-reasoning language models: Unfold hidden reasoning chains with few reasoning catalyst. In Findings of the Association for Computational Linguistics: ACL 2025, pages 5578–5596. [find](https://scholar.google.com/scholar?q=Hongru+Wang%2C+Deng+Cai%2C+Wanjun+Zhong%2C+Shijue+Huang%2C+Jeff+Z+Pan%2C+Zeming+Liu%2C+and+Kam%2DFai+Wong%2E+2025a%2E+Self%2Dreasoning+language+models%3A+Unfold+hidden+reasoning+chains+with+few+reasoning+catalyst%2E+In+Findi)
38. Xiaoye Qu, Yafu Li, Zhaochen Su, Weigao Sun, Jianhao Yan, Dongrui Liu, Ganqu Cui, Daizong Liu, Shuxian Liang, Junxian He, and 1 others. 2025. [A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond](https://md.research.elamur.ai/free/en/papers/qu-2025-survey-efficient-reasoning-large-reasoning/). arXiv preprint arXiv:2503.21614.
39. Jieming Wang, Ziyan Li, Jianfei Yu, Li Yang, and Rui Xia. 2023a. Fine-grained multimodal named entity recognition and grounding with a generative framework. In Proceedings of the 31st ACM International Conference on Multimedia, pages 3934– 3943. [find](https://scholar.google.com/scholar?q=Jieming+Wang%2C+Ziyan+Li%2C+Jianfei+Yu%2C+Li+Yang%2C+and+Rui+Xia%2E+2023a%2E+Fine%2Dgrained+multimodal+named+entity+recognition+and+grounding+with+a+generative+framework%2E+In+Proceedings+of+the+31st+ACM+Internationa)
40. Paul Roit, Johan Ferret, Lior Shani, Roee Aharoni, Geoffrey Cideron, Robert Dadashi, Matthieu Geist, Sertan Girgin, Léonard Hussenot, Orgad Keller, and 1 others. 2023. Factually consistent summarization Jieming Wang, Ziyan Li, Jianfei Yu, Li Yang, and Rui Xia. 2023b. Fine-grained multimodal named en… [find](https://scholar.google.com/scholar?q=Paul+Roit%2C+Johan+Ferret%2C+Lior+Shani%2C+Roee+Aharoni%2C+Geoffrey+Cideron%2C+Robert+Dadashi%2C+Matthieu+Geist%2C+Sertan+Girgin%2C+L%C3%A9onard+Hussenot%2C+Orgad+Keller%2C+and+1+others%2E+2023%2E+Factually+consistent+summarizati)
41. Weiqin Wang, Yile Wang, Kehao Chen, and Hui Huang. 2025b. [Beyond majority voting: Towards fine-grained and more reliable reward signal for test-time reinforcement learning](https://md.research.elamur.ai/free/en/papers/wang-2026-beyond-majority-voting-fine-grained/). arXiv preprint arXiv:2512.15146.
42. Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai, Xinyue Lou, Yunghwei Lai, Ziyue Wang, Yawen Wang, Kaiyu Huang, Yile Wang, Peng Li, and 1 others. 2025c. Mucar: Benchmarking multilingual cross-modal ambiguity resolution for multimodal large language models. In Proceedings of the 2025 Conference on Empiri… [find](https://scholar.google.com/scholar?q=Xiaolong+Wang%2C+Zhaolu+Kang%2C+Wangyuxuan+Zhai%2C+Xinyue+Lou%2C+Yunghwei+Lai%2C+Ziyue+Wang%2C+Yawen+Wang%2C+Kaiyu+Huang%2C+Yile+Wang%2C+Peng+Li%2C+and+1+others%2E+2025c%2E+Mucar%3A+Benchmarking+multilingual+cross%2Dmodal+ambigu)
43. Xinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, and Kewei Tu. 2022a. Ita: Image-text alignments for multimodal named entity recognition. In Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human la… [find](https://scholar.google.com/scholar?q=Xinyu+Wang%2C+Min+Gui%2C+Yong+Jiang%2C+Zixia+Jia%2C+Nguyen+Bach%2C+Tao+Wang%2C+Zhongqiang+Huang%2C+and+Kewei+Tu%2E+2022a%2E+Ita%3A+Image%2Dtext+alignments+for+multimodal+named+entity+recognition%2E+In+Proceedings+of+the+2022)
44. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022b. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171.
45. Ziqi Wang, Chen Zhu, Zhi Zheng, Xinhang Li, Tong Xu, Yongyi He, Qi Liu, Ying Yu, and Enhong Chen. 2024b. Granular entity mapper: Advancing fine-grained multimodal named entity recognition and grounding. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3211–3226. [find](https://scholar.google.com/scholar?q=Ziqi+Wang%2C+Chen+Zhu%2C+Zhi+Zheng%2C+Xinhang+Li%2C+Tong+Xu%2C+Yongyi+He%2C+Qi+Liu%2C+Ying+Yu%2C+and+Enhong+Chen%2E+2024b%2E+Granular+entity+mapper%3A+Advancing+fine%2Dgrained+multimodal+named+entity+recognition+and+groundin)
46. Huanjin Yao, Qixiang Yin, Jingyi Zhang, Min Yang, Yibo Wang, Wenhao Wu, Fei Su, Li Shen, Minghui Qiu, Dacheng Tao, and 1 others. 2025. R1-sharevl: Incentivizing reasoning capability of multimodal large language models via share-grpo. arXiv preprint arXiv:2505.16673. — [arXiv:2505.16673](https://arxiv.org/abs/2505.16673) [find](https://scholar.google.com/scholar?q=Huanjin+Yao%2C+Qixiang+Yin%2C+Jingyi+Zhang%2C+Min+Yang%2C+Yibo+Wang%2C+Wenhao+Wu%2C+Fei+Su%2C+Li+Shen%2C+Minghui+Qiu%2C+Dacheng+Tao%2C+and+1+others%2E+2025%2E+R1%2Dsharevl%3A+Incentivizing+reasoning+capability+of+multimodal+larg)
47. Jianfei Yu, Ziyan Li, Jieming Wang, and Rui Xia. 2023. Grounded multimodal named entity recognition on social media. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9141– 9154. [find](https://scholar.google.com/scholar?q=Jianfei+Yu%2C+Ziyan+Li%2C+Jieming+Wang%2C+and+Rui+Xia%2E+2023%2E+Grounded+multimodal+named+entity+recognition+on+social+media%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Computational+Ling)
48. Zihao Yue, Zhenru Lin, Yifan Song, Weikun Wang, Shuhuai Ren, Shuhao Gu, Shicheng Li, Peidian Li, Liang Zhao, Lei Li, and oothers. 2025. [Mimo-vl technical report](https://md.research.elamur.ai/free/en/papers/team-2025-llm-mimo-vl-technical-report/). arXiv preprint arXiv:2506.03569.
49. Pingrui Zhang, Xianqiang Gao, Yuhan Wu, Kehui Liu, Dong Wang, Zhigang Wang, Bin Zhao, Yan Ding, and Xuelong Li. 2025a. Moma-kitchen: A 100k+ benchmark for affordance-grounded last-mile navigation in mobile manipulation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV… [find](https://scholar.google.com/scholar?q=Pingrui+Zhang%2C+Xianqiang+Gao%2C+Yuhan+Wu%2C+Kehui+Liu%2C+Dong+Wang%2C+Zhigang+Wang%2C+Bin+Zhao%2C+Yan+Ding%2C+and+Xuelong+Li%2E+2025a%2E+Moma%2Dkitchen%3A+A+100k%2B+benchmark+for+affordance%2Dgrounded+last%2Dmile+navigation+in+m)
50. Yu Zhang, Kehai Chen, Xuefeng Bai, Zhao Kang, Quanjiang Guo, and Min Zhang. 2024. Question-guided knowledge graph re-scoring and injection for knowledge graph question answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA. Association for Computatio… [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Kehai+Chen%2C+Xuefeng+Bai%2C+Zhao+Kang%2C+Quanjiang+Guo%2C+and+Min+Zhang%2E+2024%2E+Question%2Dguided+knowledge+graph+re%2Dscoring+and+injection+for+knowledge+graph+question+answering%2E+In+Findings+of+the+As)
51. Yu Zhang, Yunqi Li, Yifan Yang, Rui Wang, Yuqing Yang, Dai Qi, Jianmin Bao, Dongdong Chen, Chong Luo, and Lili Qiu. 2025b. Reasongen-r1: Cot for autoregressive image generation models through sft and rl. arXiv preprint arXiv:2505.24875. — [arXiv:2505.24875](https://arxiv.org/abs/2505.24875) [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Yunqi+Li%2C+Yifan+Yang%2C+Rui+Wang%2C+Yuqing+Yang%2C+Dai+Qi%2C+Jianmin+Bao%2C+Dongdong+Chen%2C+Chong+Luo%2C+and+Lili+Qiu%2E+2025b%2E+Reasongen%2Dr1%3A+Cot+for+autoregressive+image+generation+models+through+sft+and+)
52. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
53. Yu Zhang, Jinlong Ma, Yongshuai Hou, Xuefeng Bai, Kehai Chen, Yang Xiang, Jun Yu, and Min Zhang. 2025c. Evaluating and steering modality preferences in multimodal large language model. arXiv preprint arXiv:2505.20977. — [arXiv:2505.20977](https://arxiv.org/abs/2505.20977) [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Jinlong+Ma%2C+Yongshuai+Hou%2C+Xuefeng+Bai%2C+Kehai+Chen%2C+Yang+Xiang%2C+Jun+Yu%2C+and+Min+Zhang%2E+2025c%2E+Evaluating+and+steering+modality+preferences+in+multimodal+large+language+model%2E+arXiv+preprint+)
54. Lai Wei, Yuting Li, Chen Wang, Yue Wang, Linghe Kong, Weiran Huang, and Lichao Sun. 2025. First sft, second rl, third upt: Continual improving multimodal llm reasoning via unsupervised post-training. arXiv preprint arXiv:2505.22453. — [arXiv:2505.22453](https://arxiv.org/abs/2505.22453) [find](https://scholar.google.com/scholar?q=Lai+Wei%2C+Yuting+Li%2C+Chen+Wang%2C+Yue+Wang%2C+Linghe+Kong%2C+Weiran+Huang%2C+and+Lichao+Sun%2E+2025%2E+First+sft%2C+second+rl%2C+third+upt%3A+Continual+improving+multimodal+llm+reasoning+via+unsupervised+post%2Dtraining%2E+)
55. Zefeng Zhang, Hengzhu Tang, Jiawei Sheng, Zhenyu Zhang, Yiming Ren, Zhenyang Li, Dawei Yin, Duohe Ma, and Tingwen Liu. 2025d. Debiasing multimodal large language models via noise-aware preference optimization. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 9423– 9433… [find](https://scholar.google.com/scholar?q=Zefeng+Zhang%2C+Hengzhu+Tang%2C+Jiawei+Sheng%2C+Zhenyu+Zhang%2C+Yiming+Ren%2C+Zhenyang+Li%2C+Dawei+Yin%2C+Duohe+Ma%2C+and+Tingwen+Liu%2E+2025d%2E+Debiasing+multimodal+large+language+models+via+noise%2Daware+preference+opti)
56. Chuan Wu, Meng Su, Youxuan Fang, and Shaolin Zhu. 2025. Unveiling multimodal processing: Exploring activation patterns in multimodal llms for interpretability and efficiency. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9005–9016. [find](https://scholar.google.com/scholar?q=Chuan+Wu%2C+Meng+Su%2C+Youxuan+Fang%2C+and+Shaolin+Zhu%2E+2025%2E+Unveiling+multimodal+processing%3A+Exploring+activation+patterns+in+multimodal+llms+for+interpretability+and+efficiency%2E+In+Findings+of+the+Associ)
57. Wei Xiong, Chenlu Ye, Baohao Liao, Hanze Dong, Xinxing Xu, Christof Monz, Jiang Bian, Nan Jiang, and Tong Zhang. 2025. Reinforce-ada: An adaptive sampling framework for reinforce-style llm training. arXiv preprint arXiv:2510.04996. — [arXiv:2510.04996](https://arxiv.org/abs/2510.04996) [find](https://scholar.google.com/scholar?q=Wei+Xiong%2C+Chenlu+Ye%2C+Baohao+Liao%2C+Hanze+Dong%2C+Xinxing+Xu%2C+Christof+Monz%2C+Jiang+Bian%2C+Nan+Jiang%2C+and+Tong+Zhang%2E+2025%2E+Reinforce%2Dada%3A+An+adaptive+sampling+framework+for+reinforce%2Dstyle+llm+training%2E+a)
58. Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023. [Multimodal chain-of-thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/zhang-2023-multimodal-chain-thought-reasoning-language/). arXiv preprint arXiv:2302.00923.
59. Yuze Zhao, Jintao Huang, Jinghan Hu, Xingjun Wang, Yunlin Mao, Daoze Zhang, Zeyinzi Jiang, Zhikai Wu, Baole Ai, Ang Wang, and 1 others. 2025. Swift: a scalable lightweight infrastructure for fine-tuning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 29733–29735. [find](https://scholar.google.com/scholar?q=Yuze+Zhao%2C+Jintao+Huang%2C+Jinghan+Hu%2C+Xingjun+Wang%2C+Yunlin+Mao%2C+Daoze+Zhang%2C+Zeyinzi+Jiang%2C+Zhikai+Wu%2C+Baole+Ai%2C+Ang+Wang%2C+and+1+others%2E+2025%2E+Swift%3A+a+scalable+lightweight+infrastructure+for+fine%2Dtuni)
60. Xiangqing Zheng, Chengyue Wu, Kehai Chen, and Min Zhang. 2025. Locot2v-bench: A benchmark for long-form and complex text-to-video generation. arXiv preprint arXiv:2510.26412. — [arXiv:2510.26412](https://arxiv.org/abs/2510.26412) [find](https://scholar.google.com/scholar?q=Xiangqing+Zheng%2C+Chengyue+Wu%2C+Kehai+Chen%2C+and+Min+Zhang%2E+2025%2E+Locot2v%2Dbench%3A+A+benchmark+for+long%2Dform+and+complex+text%2Dto%2Dvideo+generation%2E+arXiv+preprint+arXiv%3A2510%2E26412%2E+%E2%80%94+%5BarXiv%3A2510%2E26412%5D%28http)
61. Ruiyang Zhou, Shuozhe Li, Amy Zhang, and Liu Leqi. 2025. Expo: Unlocking hard reasoning with self-explanation-guided reinforcement learning. arXiv preprint arXiv:2507.02834. — [arXiv:2507.02834](https://arxiv.org/abs/2507.02834) [find](https://scholar.google.com/scholar?q=Ruiyang+Zhou%2C+Shuozhe+Li%2C+Amy+Zhang%2C+and+Liu+Leqi%2E+2025%2E+Expo%3A+Unlocking+hard+reasoning+with+self%2Dexplanation%2Dguided+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2507%2E02834%2E+%E2%80%94+%5BarXiv%3A2507%2E02834%5D%28https)
62. B Here is one of the instructions used for distillation, which requires the model to consider the relevant modalities during execution and to produce results consistent with the labels. Modality- and Task- specific Constraints Sining Zhoubian, Dan Zhang, and Jie Tang. 2025. Rest-rl: Achieving accura… — [arXiv:2508.19576](https://arxiv.org/abs/2508.19576) [find](https://scholar.google.com/scholar?q=B+Here+is+one+of+the+instructions+used+for+distillation%2C+which+requires+the+model+to+consider+the+relevant+modalities+during+execution+and+to+produce+results+consistent+with+the+labels%2E+Modality%2D+and+)

*Updated 1 November 2026*