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
Items 401–500 of 660
Data-Centric Lessons To Improve Speech-Language Pretraining
Udandarao, V., Lu, Z., Chang, X., Wang, Y.-Q., Yao, V., Jose, A. M., Faghri, F., Gardner, J., & Chiu, C.-C. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2510.20860 · Cited by 4
PrefGen: Multimodal Preference Learning for Preference-Conditioned Image GenerationPreprint
Mo, W., Zhang, T., Bai, Y., Han, L., Ba, Y., & Metaxas, D. N. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.06020 · Cited by 4
Unifying Speech Recognition, Synthesis and Conversion with Autoregressive TransformersPreprint
Cai, R., Lin, Y. C., Wang, Y., Fu, C., & Zeng, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.10770 · Cited by 4
Understanding the Fine-Grained Knowledge Capabilities of Vision-Language ModelsPreprint
Ghosh, D., Zhang, Y., & Schmidt, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.17871 · Cited by 4
ReMoT: Reinforcement Learning with Motion Contrast TripletsPreprint
Wan, C., Guo, Z., Li, J., Dong, S., Bai, Y., Peng, L., Ma, Z., & Gong, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.00461 · Cited by 4
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language ModelsPreprint
Dong, Y., Liu, Z., Tian, S., Rao, Y., & Liu, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.18118 · Cited by 4
To Agree or To Be Right? The Grounding-Sycophancy Tradeoff in Medical Vision-Language ModelsPreprint
Aranya, O. F. M. R. R., & Desai, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.22623 · Cited by 4
When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMsPreprint
Khayatan, P., Parekh, J., Dapogny, A., Shukor, M., Newson, A., & Cord, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.21911 · Cited by 4
Self-citationWhat Matters When Building Vision Language Models for Product Image Analysis?
Trabelsi, A., Zontak, M., Qian, Y., Jackson, B., Khan, S., & Batur, U. (2025) · 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00151 · Cited by 3
Beyond Text or Image: A Comparative Study of Fine-Tuned VLM for Meme Hate Speech Detection
Zhang, B., Xu, J., Ihnaini, B., & Sangi, A. R. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11086000 · Cited by 3
Investigating Social Biases in Multimodal LLMs
Perera, M. V., Narayan, K., & Patel, V. M. (2025) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg61629.2025.11099161 · Cited by 3
Classifying the Unknown: In-Context Learning for Open-Vocabulary Text and Symbol Recognition
Simon, T., Mocaër, W., Tranouez, P., Chatelain, C., & Paquet, T. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04627-7_13 · Cited by 3
Wang, S., Guo, Y., Zhang, T., Lin, R., Yue, T., Wang, Y., Li, Z., Gao, F., Wang, S., & Ma, S. (2025) · Transactions on Artificial Intelligence · doi:10.53941/tai.2025.100014 · Cited by 3
Sardari, S., Fernandes, F., Araya-Martinez, J. M., Zak, J. A., & Roitberg, A. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11163755 · Cited by 3
Zhou, A., Tu, M., Wang, L., Sun, T., Cheng, Z., Yin, Y., Jiang, Z., & Gu, Q. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3763784 · Cited by 3
MdCoT: Medical Diagnosis Chain-of-Thought with Self-Diagnostic Refinement for Alzheimer’s Disease
Lu, C.-L., Zhang, Y., Wang, P., Lü, W., & Qin, L. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209984 · Cited by 3
RG-VQA: Leveraging Retriever-Generator Pipelines for Knowledge Intensive Visual Question Answering
Sravanthi, S. L., Agarwal, P., Mondal, D., Singh, R., Panda, S., Mishra, A., Pradeep, K., B, S. K., Rao, G. S., & Bhattacharyya, P. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.1306 · Cited by 3
Train a Unified Multimodal Data Quality Classifier with Synthetic Data
Wang, W., Lin, R., Li, S., Lockard, C., Sarkhel, R., Lokegaonkar, S., Shang, J., Yan, X., Zalmout, N., & Li, X. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.104 · Cited by 3
Can Vision-Language Models Understand Construction Workers? An Exploratory Study
Bui, H., Chodosh, N., & Tavakoli, A. (2026) · IEEE Access · doi:10.1109/access.2026.3661520 · Cited by 3
Liu, J., Ning, J., Ma, C., Qu, W., Shen, J., Luo, S., Wei, J., Ye, J., Li, P., Li, T., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37035-8_14 · Cited by 3
Yang, X., fang, H., Kong, J., Mao, Y., Chen, B., & Xia, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37592-6_15 · Cited by 3
GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models
Zheng, S., Zhu, Y., Zhao, H., Yang, F., Zhan, Y., Tang, M., & Wang, J. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i34.40120 · Cited by 3
Efficient and Effective In-context Demonstration Selection with Coreset
Wang, Z., Wang, J., Xu, H., Yan, M., Huang, F., Yang, X., Wei, X.-S., Mi, S., & Zhang, Y. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i13.38017 · Cited by 3
Ye, G., Zhao, H., Shen, Y., Li, J., Li, F., Jiang, Z., & Li, K. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3676204 · Cited by 3
Statkiewicz, G., Dobrzeniecka, A., Seweryn, K., Krasnodębska, A., Piosek, K., Bogusz, K., Cygert, S., & Kusa, W. (2026) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2026.eacl-srw.44 · Cited by 3
$\mathcal{D}$-Attn: Decomposed Attention for Large Vision-and-Language Models
Kuo, C.-W., Zhu, S., Chen, F., Shen, X., & Wen, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02219 · Cited by 3
Segment Anything Model for medical image segmentation: A review
Xiao, H., Liu, S., Liu, X., Qian, L., & Jiang, J. (2026) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2026.102789 · Cited by 3
ViQ: Text-Aligned Visual Quantized Representations at Any Resolution
Yu, X., Liu, Z., Yang, Z., Dong, Y. H., Qian, S., Lu, J., Hu, H., & Rao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37356-4_30 · Cited by 3
MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays
Cho, S. S., Han, Y., & Do, J. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1512 · Cited by 3
Contrastive learning in building vision-language models for subsurface geoscience
Aseev, A., Huang, J., & Mishra, P. (2025) · The Leading Edge · doi:10.1190/tle44020080.1 · Cited by 3
NuCap: A Numerically Aware Captioning Framework for Improved Numerical Reasoning
Jeong, Y., & Choi, Y. S. (2025) · Applied Sciences · doi:10.3390/app15105608 · Cited by 3
LIME: Less Is More for MLLM Evaluation
Zhu, K., Zang, Q., Jia, S., Wu, S., Fang, F., Li, Y., Guo, S., Zheng, T., Guo, J., Li, B., et al. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.474 · Cited by 3
FORTIFY: Generative Model Fine-tuning with ORPO for ReTrieval Expansion of InFormal NoisY Text
DeGenaro, D., Yang, E., Etter, D., Carpenter, C., Sanders, K., Martin, A. A., Murray, K., & Kriz, R. (2025) · Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR) · doi:10.18653/v1/2025.magmar-1.13 · Cited by 3
CHARM: Cross-modal hierarchical attention for recognizing malicious memes
Zhu, K., Yang, A., Li, Z., Zhang, Z., Wang, H., & Yu, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131938 · Cited by 3
DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
Huang, C., Zhang, Z., Liu, J., Sun, X., Wu, J., Yu, X., Wang, Z., Xu, C., Barsoum, E., & Liu, Z. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1015 · Cited by 3
Spanio, M. (2024) · Padua Research Archive (University of Padova) · Cited by 3
FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image InsertionPreprint
Ruan, J., Yang, Y., Lin, Z., Feng, Y., Xiong, F., Tang, Z., & Li, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.12564 · Cited by 3
Introducing Milabench: Benchmarking Accelerators for AIPreprint
Delaunay, P., Bouthillier, X., Breuleux, O., Ortiz-Gagné, S., Bilaniuk, O., Normandin, F., Bergeron, A., Carrez, B., Alain, G., Blanc, S., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.11940 · Cited by 3
Çekinel, R. F., Karagöz, P., & Çöltekin, Ç. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.05155 · Cited by 3
Shams, D., Salama, I., & Callixtus, I. (2025) · Preprints.org · doi:10.20944/preprints202501.0502.v1 · Cited by 3
Multimodal and Distributed LLMs: Bridging Scalability and Cross-Modal ReasoningPreprint
Kumar, R., Laurent, I., Müller, D., & Elli, K. (2025) · Preprints.org · doi:10.20944/preprints202505.1156.v1 · Cited by 3
Gigant, T., Guinaudeau, C., & Dufaux, F. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.10049 · Cited by 3
URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document UnderstandingPreprint
Shi, Y., Wang, J., Shan, Z., Peng, D., Lin, Z., & Jin, L. (2025) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.48550/arxiv.2511.10552 · Cited by 3
Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian ProcessesPreprint
Hoche, J., Bursuc, A., Brellmann, D., Louppe, G., Izmailov, P., Yao, A., & Franchi, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.14177 · Cited by 3
Multimodal Causal-Driven Representation Learning for Generalizable Medical Image SegmentationPreprint
Liang, X., Zhou, L., Li, N., Xu, M., Song, Z., Yi, D., Wu, J., Ma, J., Liu, H., Lei, Z., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.05008 · Cited by 3
VISOR++: Universal Visual Inputs based Steering for Large Vision Language ModelsPreprint
Balakrishnan, R., & Phute, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.25533 · Cited by 3
DigiData: Training and Evaluating General-Purpose Mobile Control AgentsPreprint
Sun, Y., Wang, M., Qian, S., Wong, W. R., Gan, E., D'Oro, P., Munoz, A. C., Silwal, S., Matias, P., Kamra, N., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.07413 · Cited by 3
Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning RatePreprint
Bu, Z., Xu, S., & Mao, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.07145 · Cited by 3
MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMsPreprint
Li, J., Tiulpin, A., & Blaschko, M. B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.03072 · Cited by 4
ZAYA1-VL-8B Technical ReportPreprint
Shapourian, H., Hejazi, K., Sule, O. M., & Millidge, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.08560 · Cited by 3
DataComp-VLM: Improved Open Datasets for Vision-Language ModelsPreprint
Farina, M., Udandarao, V., Nguyen, T., Kuzucu, S., Böther, M., Hochlehnert, A., Ghosh, A., Nezhurina, M., Roth, K., Struber, J., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.28551 · Cited by 3
Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
Li, Z., Chen, G., Liu, S., Wang, S., VS, V., Ji, Y., Lan, S., Zhang, H., Zhao, Y., Radhakrishnan, S., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.14818 · Cited by 2
STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
Jiang, J., Li, X., Liu, Z., Li, M., Chen, G., Li, Z., Huang, D.-A., Liu, G., Yu, Z., Keutzer, K., et al. (2025) · 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00614 · Cited by 2
Visual Lifelog Retrieval through Captioning-Enhanced Interpretation
Shih, Y.-F., Yen, A.-Z., Huang, H., & Chen, H. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825835 · Cited by 2
A Novel Trustworthy Video Summarization Algorithm Through a Mixture of LoRA Experts
Du, W., Wang, G., Li, X., Chen, G., Gao, J. S., & Zhao, H. (2025) · Electronics · doi:10.3390/electronics14112269 · Cited by 2
Visual Document Understanding: A Comparative Review of Modern Methods
Nandi, K., & Sundaram, S. S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-93694-4_29 · Cited by 2
Optimizing Multimodal Language Models Through Attention-Based Interpretability
Sergeev, A., & Котельников, Е. В. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-07175-0_25 · Cited by 2
reVISION: A Polish Benchmark for Evaluating Vision-Language Models on Multimodal National Exam Data
Ciesiółka, M., & Graliński, F. (2025) · Annals of Computer Science and Information Systems · doi:10.15439/2025f2608 · Cited by 2
Spoken Question Answering for Visual Queries
Shabtay, N., Kons, Z., Dekel, A., Aronowitz, H., Hoory, R., & Arbelle, A. (2025) · Interspeech (USB) · doi:10.21437/interspeech.2025-843 · Cited by 2
UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality Assessment
Cao, J., An, G., Gao, F., Gu, K., & Liu, Y. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i4.37246 · Cited by 2
Li, Z., Kong, C., Yu, Y., Wu, Q., Jiang, X., Cheung, N., Wen, B., Kot, A. C., & Jiang, X. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i42.40873 · Cited by 2
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
Deria, A., Kumar, K., He, X., Razzak, I., Cholakkal, H., Khan, F. S., & Khan, S. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836231 · Cited by 2
Enhancing Vision Language Corruption Robustness using Cross-Distribution & Prompted Denoisers
Latif, S. S., Shiper, S., Kiran, K. M. R., Ishmam, M. F., Hossain, M. A., Kamal, A. R. M., & Ashmafee, M. H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00558 · Cited by 2
Yu, Z., Liu, Y., & Chen, Q. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115017 · Cited by 2
Towards Unconstrained Human-Object Interaction
Tonini, F., Conti, A., Vaquero, L., Beyan, C., & Ricci, E. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11557036 · Cited by 2
Zheng, X., Wang, X., & Wan, X. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.273 · Cited by 2
Zheng, X., Wang, X., & Wan, X. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.429 · Cited by 2
DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding
Hannan, T., Mallios, D., Pathak, P., Sardari, F., Seidl, T., Bertasius, G., Fayyaz, M., & Sengupta, S. (2026) · doi:10.1109/cvprf71909.2026.00895 · Cited by 2
OmniDialog: A Multimodal Benchmark for Generalization Across Text, Visual, and Audio Modalities
Razzhigaev, A., Kurkin, M., Goncharova, E., Abdullaeva, I., Lysenko, A., Panchenko, A., Кузнецов, А. В., & Dimitrov, D. (2024) · GenBench Workshop on Generalisation (Benchmarking) in NLP (GenBench) · doi:10.18653/v1/2024.genbench-1.12 · Cited by 2
Subjective and Objective Quality Assessments of AI-Generated Images for Language E-Learning
Onuoha, C., Dang, V. H., Nam, N. D., Hương, T. T., Nam, P. N., & Thang, T. C. (2025) · IEEE Access · doi:10.1109/access.2025.3578047 · Cited by 2
Langvision-Lora-Nas: Neural Architecture Search for Variable Lora Rank In Vision Language Models
Chitty-Venkata, K. T., Emani, M. K., & Vishwanath, V. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084278 · Cited by 2
Karagöz, P., Çekinel, R. F., & Çöltekin, Ç. (2025) · OpenMETU (Middle East Technical University) · Cited by 2
Efficient Architectures for High Resolution Vision-Language ModelsPreprint
Carvalho, M., & Martins, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.02584 · Cited by 2
Inference Compute-Optimal Video Vision Language ModelsPreprint
Wang, P., Peng, S., Zhang, X., Yu, H., Yang, Y., Huang, L., Liu, F., & Wang, Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.18855 · Cited by 2
Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video CaptionPreprint
Qin, L., Tan, Z., Yang, M., Yang, X., & Li, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.09279 · Cited by 2
ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language ModelPreprint
Kang, W., Zhuang, W., Li, Z., Yan, Y., & Lyu, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.08066 · Cited by 2
Train a Unified Multimodal Data Quality Classifier with Synthetic DataPreprint
Wang, W., Lin, R., Li, S., Lockard, C., Sarkhel, R., Lokegaonkar, S., Shang, J., Yan, X., Zalmout, N., & Li, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.15162 · Cited by 2
Zou, Z., Gao, Y., Guan, J., Li, B., & Marttinen, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.10292 · Cited by 2
Synthetic Document Question Answering in HungarianPreprint
Li, J. C., Csaki, Z., Hiremath, N., Guha, E., Hong, F., Ma, E., & Thakker, U. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.23008 · Cited by 2
CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented CaptioningPreprint
Ibrahim, G., Ramos, R., & Kementchedjhieva, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.20411 · Cited by 2
CAIRe: Cultural Attribution of Images by Retrieval-Augmented EvaluationPreprint
Yayavaram, A., Yayavaram, S., Khanuja, S., Saxon, M., & Neubig, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.09109 · Cited by 2
Zhu, G., Hou, Z., Liu, Z., Sang, Z., Xie, C., & Yang, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.22261 · Cited by 2
Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial UnderstandingPreprint
Mirjalili, V., Giahi, R., Kollipara, S., Kekuda, A., Yao, K., Zhao, K., Xu, J., Nag, K., Subramaniam, S., Biswas, T., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.21922 · Cited by 2
Ding, Y., Han, S. C., Jiang, Y., Li, Y., Li, Z., & Peng, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.23273 · Cited by 2
Typhoon OCR: Open Vision-Language Model For Thai Document ExtractionPreprint
Nonesung, S., Nitarach, N., Jaknamon, T., Taveekitworachai, P., & Pipatanakul, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.14722 · Cited by 2
MaD-Mix: Multi-Modal Data Mixtures via Latent Space Coupling for Vision-Language Model TrainingPreprint
Xie, W., Tonin, F., & Cevher, V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.07790 · Cited by 2
Madinei, P., Karmakar, S., Hoffing, R. C., Gervitz, F., & Eckstein, M. P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.16138 · Cited by 2
Differentially Private Multimodal In-Context LearningPreprint
Ngong, I. C., Reza, Z. N., & Near, J. P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.04894 · Cited by 2
Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFTPreprint
Sun, P., Yang, Y., Shen, H., Ban, Y., Fu, T., Wang, Y., & Li, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.09715 · Cited by 2
HIFICL: High-Fidelity In-Context Learning for Multimodal TasksPreprint
Li, X., Liu, Y., Kang, X., Luo, Z., Lou, F., Wu, X., & Xiong, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.12760 · Cited by 2
Li, S., Srivastav, V., Yin, S., Chanel, N., Sharma, S., Banik, N., Arboit, L., Yuan, K., Mascagni, P., & Padoy, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.29962 · Cited by 2
CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop ReasoningPreprint
Sung, J., Lyu, S., Kim, M., An, S., Nagrani, A., & Seo, P. H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.01634 · Cited by 2
Vo, Q., Nguyen, C.-D. T., Srey, P., Tuan, L. A., & Nguyen, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.11131 · Cited by 2
What is in a food store name? Leveraging large language models to enhance food environment data
Etheredge, A. J., Hosmer, S., Crossa, A., Suss, R., & Torrey, M. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1476950 · Cited by 1
Beyond Relevance: Utility-Driven Retrieval for Visual Document Question Answering
Yu, B., Wu, G., Yao, Z., Shi, H., Chen, Q., Bu, L., Sun, L., & Wei, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9921-6_31 · Cited by 1
Vision on the Move: Automated Hazardous Material Plate Detection in Freight Transport
Tijink, M., Levendeev, S., Nieuwenhuis, E., Spreeuwers, L., Strisciuglio, N., & Talavera, E. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04968-1_22 · Cited by 1
Biescas, N., Biswas, S., Lladós, J., & Landeghem, J. V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04627-7_1 · Cited by 1
FashionLIP: Automated Fashion Image Captioning Using Cascaded Contrastive Learning
Hegde, A., Kuppala, Y., & Ma, M. (2025) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr67560.2025.00024 · Cited by 1
EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection
Yang, H., Wang, J., & Zhang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3349-7_31 · Cited by 1
Exploring visual language models for driver gaze estimation: A task-based approach to debugging AI
Cañas, P. N., Artiles, A. H., Nieto, M., & Rodríguez, I. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104593 · Cited by 1
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
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.