What matters when building vision-language models?
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
The growing interest in vision-language models (VLMs) has been driven by improvements in large language models and vision transformers. Despite the abundance of literature on this subject, we observe that critical decisions regarding the design of VLMs are often not justified. We argue that these unsupported decisions impede progress in the field by making it difficult to identify which choices improve model performance. To address this issue, we conduct extensive experiments around pre-trained models, architecture choice, data, and training methods. Our consolidation of findings includes the development of Idefics2, an efficient foundational VLM of 8 billion parameters. Idefics2 achieves state-of-the-art performance within its size category across various multimodal benchmarks, and is often on par with models four times its size. We release the model (base, instructed, and chat) along with the datasets created for its training.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
MiniCPM-V: A GPT-4V Level MLLM on Your PhonePreprint
Yao, Y., Yu, T., Zhang, A., Wang, C., Cui, J., Zhu, H., Cai, T., Li, H., Zhao, W., He, Z., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.01800 · Cited by 1,617
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Tong, S., Brown, E., Wu, P., Woo, S., Middepogu, M., Akula, S. C., Yang, J., Yang, S., Iyer, A., Pan, X., et al. (2024) · neural information processing systems · doi:10.52202/079017-2771 · Cited by 1,210
LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
Li, F., Zhang, R., Zhang, H., Zhang, Y., Li, B., Li, W., Ma, Z., & Li, C. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2407.07895 · Cited by 1,008
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal UnderstandingPreprint
Wu, Z., Chen, X., Pan, Z., Liu, X., Liu, W., Dai, D., Gao, H., Ma, Y., Wu, C., Wang, B., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.10302 · Cited by 996
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
Wu, H., Li, D., Chen, B., & Li, J. (2024) · neural information processing systems · doi:10.52202/079017-0907 · Cited by 849
Metadata
- Authors
- Laurençon, H., Tronchon, L., Cord, M., & Sanh, V.
- ORCID
- Cord, Matthieu
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 87874-87907
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W4415796627
- Cited by
- 66
- References
- 0
- Citations by year
- 2026: 39 · 2025: 23 · 2024: 4
- FWCI
- 13.67
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- vision-language models, model design, multimodal representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: What matters when building vision-language models? https://app.cochat.ai/papers/10.52202/079017-2789
- The paper
- Laurençon, H., Tronchon, L., Cord, M., & Sanh, V. (2024). What matters when building vision-language models? Advances in Neural Information Processing Systems 37. https://doi.org/10.52202/079017-2789
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.