Conference paper · 2026 · Open access
Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
IEEE International Conference on Acoustics Speech and Signal Processing, 12667–12671 · Published 21 April 2026 · DOI 10.1109/icassp55912.2026.11461396
In brief
“Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning” is a 2026 conference paper by Bob Zhang and 7 co-authors, published in IEEE International Conference on Acoustics Speech and Signal Processing. OpenAlex counts 12 citations as of 19 November 2026, which puts it in the top 4% of works published in 2026 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 12
- Most cited in
- 2026 (8)
- Field-weighted impact
- 11.40
- References
- 51
- Authors
- 8
Abstract
Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning (RL) based post-training strategy for MLLMs in multi-image grounding tasks. We first synthesize high-quality chain-of-thought (CoT) data for cold-start initialization, followed by supervised fine-tuning (SFT) using low-rank adaptation (LoRA). Subsequently, we apply rejection sampling with the merged SFT model to curate reliable RL data and use rule-based RL to guide the model toward optimal reasoning paths. Extensive experiments demonstrate the effectiveness of our approach, achieving +9.04% on MIG-Bench and +4.41% on average across seven out-of-domain benchmarks.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhang, B., Li, H., Zhang, T., Li, J., Yan, C., Liu, X., Cai, J., & Hao, Y. (2026). Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning. IEEE International Conference on Acoustics Speech and Signal Processing, 12667–12671. https://doi.org/10.1109/icassp55912.2026.11461396
MLA 9
Zhang, Bob, et al. “Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning.” IEEE International Conference on Acoustics Speech and Signal Processing, 2026, pp. 12667–12671. https://doi.org/10.1109/icassp55912.2026.11461396.
Chicago
Zhang, Bob, Haoran Li, Tao Zhang, Jianan Li, Cilin Yan, Xikai Liu, Jiayin Cai, and Yanbin Hao. 2026. “Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning.” IEEE International Conference on Acoustics Speech and Signal Processing: 12667–12671. https://doi.org/10.1109/icassp55912.2026.11461396.
Harvard
Zhang, B. et al. (2026) ‘Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning’, IEEE International Conference on Acoustics Speech and Signal Processing, pp. 12667–12671. doi:10.1109/icassp55912.2026.11461396.
IEEE
B. Zhang et al., “Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning,” IEEE International Conference on Acoustics Speech and Signal Processing, pp. 12667–12671, 2026, doi: 10.1109/icassp55912.2026.11461396.
BibTeX
@inproceedings{zhang2026improving,
title = {{Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning}},
author = {Zhang, Bob and Li, Haoran and Zhang, Tao and Li, Jianan and Yan, Cilin and Liu, Xikai and Cai, Jiayin and Hao, Yanbin},
booktitle = {IEEE International Conference on Acoustics Speech and Signal Processing},
year = {2026},
pages = {12667--12671},
doi = {10.1109/icassp55912.2026.11461396},
url = {https://doi.org/10.1109/icassp55912.2026.11461396}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- multimodal large language models
- reinforcement learning
- post-training
- low-rank adaptation
- rejection sampling
- visual grounding
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Zhang, B., Li, H., Zhang, T., Li, J., Yan, C., Liu, X., Cai, J., & Hao, Y. (2026). Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning. IEEE International Conference on Acoustics Speech and Signal Processing, 12667–12671. https://doi.org/10.1109/icassp55912.2026.11461396
How many times has this paper been cited?
12 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Bob Zhang, Haoran Li, Tao Zhang, Jianan Li, Cilin Yan, Xikai Liu, Jiayin Cai, Yanbin Hao.
What is the DOI of this paper?
10.1109/icassp55912.2026.11461396, permanently at https://doi.org/10.1109/icassp55912.2026.11461396. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.