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 501–600 of 660
Hossain, M. I., Sajeeda, A., Perla, N. K., & Shao, M. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21339-x · Cited by 1
On the Taxonomy, Tasks, and Open-Challenges for Multimodal Large Language Models
闫乐成, Li, R., Geng, J., Li, Q., Wu, M., Wang, Z., Li, W., Ji, T., Jiang, S., & Lyu, C. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342688 · Cited by 1
VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval
Silva, D., Semedo, D., & Magalhães, J. (2026) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2026.findings-eacl.208 · Cited by 1
Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection
de Senneville, A., Bou, X., Anger, J., von Gioi, R. G., & Facciolo, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37383-0_16 · Cited by 1
GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction
Li, H., Chen, Y., & Zhang, Z. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-03031-7 · Cited by 1
Liu, Y., Zhao, Z., Wang, C., & Du, N. (2026) · International Conference on Intelligent Perception and Autonomous Control (IPAC) · doi:10.1109/ipac69021.2026.11542612 · Cited by 1
ESC: Emotional Self-correction for Reliable Vision Language Models
Nguyen, T.-H., Nguyen, M.-N., Huy, N. N., Nguyen, H. S., Nhat, H. N. M., Nguyen, T.-H., NGUYEN, C. T., Le, H. M., Nguyen, D. Q., Huynh, P. K., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_26 · Cited by 1
Xie, W., Zeng, Q., Meng, Z., Tian, J., He, S., Yang, D., Du, J., Wang, Y., Li, D., Wang, H., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817651 · Cited by 1
Exploring Efficient Reasoning Segmentation with Small Language Models
Wen, C., Peng, Z., Huang, Y., Yang, X., & Shen, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_32 · Cited by 1
Can You See Me, GenAI? Characterizing Video-Based Conversational Interaction with Generative AI
Cheng, R., Xie, G., & Han, B. (2026) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3777912.3839793 · Cited by 1
Improving Large Vision and Language Models by Learning from a Panel of Peers
Hernandez, J., Shi, J., Jenni, S., Ordóñez, V., & Kafle, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00138 · Cited by 1
A Comparative Evaluation of Function-Calling LLMs in a Cognitive Architecture
Pardini, M., Galatolo, F. A., Cominelli, L., Marco, A. D., Cimino, M. G. C. A., Greco, A., & Scilingo, E. P. (2025) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine66377.2025.11340083 · Cited by 1
Kolavi, A. S., Samarth, P., & Jain, V. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00178 · Cited by 1
Efficient and Global Interaction-Aware Retraining-Free Token Pruning for Vision Transformers
Shi, C., Tian, Y., Du, H., Li, Y., Zhang, G., Yao, G., Li, Y., Qiang, N., Wenxin, Z., Yu, Z., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463577 · Cited by 1
Gamified crowd-sourcing of high-quality data for visual fine-tuningPreprint
Yadav, S., Tomar, R., Jain, G., Ahooja, C., Chaudhary, S., & Elkan, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.04038 · Cited by 1
Natural Language Generation from Visual Events: State-of-the-Art and Key Open QuestionsPreprint
Surikuchi, A. K., Fernández, R., & Pezzelle, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.13034 · Cited by 1
KptLLM++: Towards Generic Keypoint Comprehension with Large Language ModelPreprint
Yang, J., Zeng, W., Jin, S., Xu, L., Liu, W., Chen, Q., Li, Z., & Zhang, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.11102 · Cited by 1
How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in ItalianPreprint
Pedrotti, A., Rambelli, G., Villani, C., Bolognesi, M., & ERC_Abstraction (2024) · arXiv (Cornell University) · doi:10.17605/osf.io/875mw · Cited by 1
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question AnsweringPreprint
Wen, Z., Wei, W., Fang, Y., Yu, X., Zhang, H., Zhu, W., & Zhang, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.06638 · Cited by 1
LaGEA: Language Guided Embodied Agents for Robotic ManipulationPreprint
Chowdhury, A. M., Mazumder, A. M. R., Arib, S. H., & Akter, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.23155 · Cited by 1
Rationale-Enhanced Decoding for Multi-modal Chain-of-ThoughtPreprint
Yamaguchi, S., Nishida, K., & Chijiwa, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.07685 · Cited by 1
Meta-Adaptive Prompt Distillation for Few-Shot Visual Question AnsweringPreprint
Gupta, A. K., Storkey, A., & Lapata, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.06905 · Cited by 1
TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake DetectionPreprint
Jiang-Lin, J.-Y., Huang, K.-Y., Zou, L., Lo, L., Yang, S., Tseng, Y., Lin, K., Chen, C.-L., Ta, Y.-T., Wang, Y., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.10652 · Cited by 1
LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language ModelPreprint
Sun, T., Liu, O., Li, J., & Ma, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.05602 · Cited by 1
Evaluating Multimodal Generative AI with Korean Educational StandardsPreprint
Park, S., & Kim, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.15422 · Cited by 1
Should VLMs be Pre-trained with Image Data?Preprint
Keh, S. S., Mercat, J., Gadre, S. Y., Arora, K., Vasiljevic, I., Burchfiel, B., Song, S., Tedrake, R., Kollar, T., Schmidt, L., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.07603 · Cited by 1
Zhou, A., Tu, M., Wang, L., Sun, T., Cheng, Z., Yin, Y., Jiang, Z., & Gu, Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.16147 · Cited by 1
Table Comprehension in Building Codes using Vision Language Models and Domain-Specific Fine-TuningPreprint
Aqib, M., Hamza, M., Chui, Y. H., & Mei, Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.18306 · Cited by 1
FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint AnalysisPreprint
Gavas, E., Banerjee, S., Hegde, C., & Memon, N. D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.18073 · Cited by 1
Ding, Y., Sun, Q., Wu, P., Li, S., Luo, S., & Liu, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.12260 · Cited by 1
VIGiA: Instructional Video Guidance via Dialogue Reasoning and RetrievalPreprint
Silva, D., Semedo, D., & Maglhaes, J. G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.19146 · Cited by 1
SteelDefectX: A Multi-Form Vision-Language Dataset and Benchmark for Steel Surface Defect AnalysisPreprint
Zhao, S., Gui, J., Yu, B., & Tao, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.21824 · Cited by 1
Semantic Richness or Geometric Reasoning? The Fragility of VLM's Visual InvariancePreprint
Qiu, J., Meurer, Z., Thomas, X., & Ghadiyaram, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.01848 · Cited by 1
Foundation Vision-Language models
Laurençon, H. (2025) · theses.fr (ABES) · doi:10.70675/ec0311a0zb6a4z4249zb9fbz01bf51a02c7c · Cited by 1
Self-citationParuchuri, A., Chatterjee, I., Fuchs, H., Adeli, E., & Didyk, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.14363 · Cited by 1
V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy OptimizationPreprint
Jiang, Y., An, Y., Yang, X., Wuerkaixi, A., Cheng, X., Xie, F., Jiang, Z., Liu, C., Zeng, K., & Zhang, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.20755 · Cited by 1
Structured Layout Priors for Robust Out-of-Distribution Visual Document UnderstandingPreprint
Hachem, P. E., Nassar, A., Gurbuz, A. S., Auer, C., & Staar, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.19866 · Cited by 1
Talemi, N. A., Kashiani, H., & Afghah, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.04434 · Cited by 1
An Effective Router for Vision-Language Model SelectionPreprint
(157994), C. W., Wang, S., Zhang, B., Tu, Z., & Chu, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.08970 · Cited by 1
Multi-Label Test-Time Adaptation with Bayesian Conditional PriorsPreprint
Li, Q., Zhou, A., Jiang, Z., Cheng, Z., Wang, C., Yin, Y., & Gu, Q. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.12925 · Cited by 1
GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal ModelsPreprint
Allabadi, G., Sodano, M., Estevão, R., Wang, Y., Adve, V., Kıcıman, E., & Chandra, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.12744 · Cited by 1
Santillana, J. S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.08477 · Cited by 1
Huang, C., Li, F., Liu, T., Liu, W., & Wu, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.21837 · Cited by 1
DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense DocumentsPreprint
Yu, Z., Nguyen, L. T., Park, J., Gu, X., He, Z., Lee, S., Feris, R., & Lee, Y. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.02059 · Cited by 1
REKI: Registering Knowledge in VLAsPreprint
Marrie, J., Pacaud, P., Rahary, A. R., Chen, S., & Böhle, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.22178 · Cited by 1
VIT-Pro: Visual Instruction Tuning for Product Images
Prabhakaran, V., Aggarwal, P., Kulshreshtha, V., Das, A., Sruti, S. V. S., & Saladi, A. (2025) · Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track) · doi:10.18653/v1/2025.naacl-industry.57
GlyphPattern: An Abstract Pattern Recognition Benchmark for Vision-Language ModelsPreprint
Wu, Z., Kim, Y., & Anderson, C. J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.05894
Mitigating Hallucinations on Object Attributes using Multiview Images and Negative Instructions
Tan, Z., Li, Y., Meng, S., Yuan, X., Li, W., Mo, T., Wang, B., & Chu, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888481
From Centralized to Composable: Advances in Distributed and Multimodal Language ModelingPreprint
Mirta, I., & Elli, K. (2025) · Engineering Archive (engrXiv) · doi:10.31224/4624
VisCon-100K: Leveraging Contextual Web Data for Fine-Tuning Vision Language Models
Kumar, G. K., Chaabane, I., & Wu, K. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8298-0_31
GlyphPattern: An Abstract Pattern Recognition for Vision-Language Models
Wu, Z., Kim, Y., & Anderson, C. J. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.63
Towards practical automatic document understanding
Ma, Y. (2025) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/201841
Crop-and-Prompt: Multi-Grained Prompting for Fine-Grained Visual-Language Understanding
Zang, Z., & Wang, H. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11182630
Vision language models have difficulty recognizing virtual objectsPreprint
Tran, T., Khemlani, S., & Trafton, J. G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.10453
Is It Large Enough? A Prompt Learning for Large Multi-modal Models
Jain, S., & Sharma, V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-03708-4_5
Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP InferencePreprint
Jiang, C., Dong, M., Shi, X., & Gui, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.09064
An Efficient Training Pipeline for Reasoning Graphical User Interface AgentsPreprint
Πανταζόπουλος, Γ., & Bilici, E. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.08172
Doctor Sun: a bilingual multimodal large language model for biomedical AI
Xue, D., Shao, Z., Duan, Z., Liu, F., Li, B., & Zhang, Z. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3853
Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in TaiwanPreprint
Yao, J., Xie, B., Peng, S.-W., Chen, H.-Y., Zheng, H.-R., Tan, B.-J., Wang, A., & Su, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.01274
A Survey of Architectural Design in Large Vision-Language ModelsPreprint
Pan, Y., Xu, Z. W., Hu, L., Zhang, L., & Nie, L. (2025) · doi:10.36227/techrxiv.176620829.92520878/v1
Kåsene, V. H., & Lison, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.02917
InfoCausalQA:Can Models Perform Non-explicit Causal Reasoning Based on Infographic?Preprint
Ka, K., Park, J., Jeon, J., & Yu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.06220
Where and When? Large Vision-Language Models for Entity Prediction in Multimodal News Events
Calvo, B. A. V. (2024) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Multimodal understanding of long documents : from topic modeling to question answering
Abaskohi, A. (2025) · cIRcle (University of British Columbia) · doi:10.14288/1.0449900
CAVE: Detecting and Explaining Commonsense Anomalies in Visual EnvironmentsPreprint
Bhagwatkar, R., Montariol, S., Romanou, A., Borges, B., Rish, I., & Bosselut, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.26006
Kumar, A., & Sohan, A. (2025) · International Journal of Innovative Research in Advanced Engineering · doi:10.26562/ijirae.2025.v1211.13
Ortega, A. L. (2025) · UPCommons institutional repository (Universitat Politècnica de Catalunya)
Rewarding fine-grained image captioning with keyword group contrastive
Ye, K., Lu, Z., Shen, L., & Cui, T. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131405
How well do vision models understand tasks with multiple labels?
Bilge, Y. C. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131479
A survey of large vision-language models: An architectural view
Pan, Y., Xu, Z., Hu, L., Zhang, L., Liu, Y., Zhu, Y., Xu, Y., & Nie, L. (2026) · Information Fusion · doi:10.36227/techrxiv.176620829.92520878/v2
Sketch2Feedback: Grammar-in-the-Loop Framework for Rubric-Aligned Feedback on Student STEM DiagramsPreprint
Bansal, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.18520
Ajay, S., L, G. G., & Krishnamurthy, V. (2025) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict67193.2025.11399109
Wu, S., Zhu, K., Bai, Y., Liang, Y., Li, Y., Wu, H., Liu, J., Liu, R., Qu, X., Cheng, X., et al. (2026) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2026.findings-eacl.287
Leum-VL Technical ReportPreprint
He, Y., Huang, C., Wu, Y., Wang, H., Shen, C., Zhang, J., & Li, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.20354
Chitrakshara: A Large Multilingual Multimodal Dataset for Indian languagesPreprint
Khan, S., Faraz, A., Ravi, A., Nauman, M., Sarfraz, M., Patidar, A., Kolla, R., Khatri, C., & Agarwal, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.23521
Video question answering with limited supervision
Engin, D. (2024) · theses.fr (ABES) · doi:10.70675/c9c7dcf2z4ca3z4e91z9d27zdacd00f76581
DAPWeb: Construct-Aligned Evaluation of MLLMs for Web-Based Child Mental Screening
Guo, R., Wang, F., Lin, L.-Y., & Wang, G. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792992
Shah, A., Tripathi, V., Singh, M., & Silpasuwanchai, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.13803
S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language ModelsPreprint
Shukla, N., Jandial, S., & Ross, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.18512
Mitigating hallucinations in image captioning via frequency perturbation entropy
Pan, L., Song, C., Gan, X., Xu, K., & Mengqian, D. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132544
ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly DetectionPreprint
Chen, Q., Song, J., Tan, S., & Zhong, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.17949
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
Zeng, X., Sun, Y., Li, H., Liu, S., & Wang, H. (2026) · arXiv (Cornell University)
PRISM: Perception Reasoning Interleaved for Sequential Decision MakingPreprint
Aissi, M.-S., Grislain, C., Romac, C., Soulier, L., Chétouani, M., Sigaud, O., & Thome, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.05407
ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine MolluscsPreprint
Zhou, Z., Wang, Y., Wang, N., Wu, C., & Yan, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.07338
Deep Pre-Alignment for VLMsPreprint
Yu, T., Fang, K., Wan, Z., Zhang, K., Zhang, Y., Song, J., Zheng, B., & Yao, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.15300
Riekers, N., & Risius, M. (2026) · AIS Electronic Library (AISeL)
Docs2Synth: A Synthetic Data Tuned Retriever Framework for Documents Understanding
Ding, Y., Sun, Q., Wu, P., Li, S., Luo, S., & Liu, W. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774905.3793117
Do VLMs Align Better with Humans than LLMs during Natural Reading?Preprint
Wu, J., Ma, Z., Li, J., Tang, B., & Lu, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.28818
FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection
Bhaskar, P., Rizwan, N., Jogchand, D., Pandey, S. K., & Mukherjee, A. (2026) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/2026.emnlp-main.1596
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight MergingPreprint
Choi, M., & Kim, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.01717
Zamba2-VL Technical ReportPreprint
Shapourian, H., Hejazi, K., Sule, O. M., & Millidge, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.00390
An Attribute-Based Measure of Video ComplexityPreprint
Sarkar, A., Li, Y., Wang, Z., Yuan, H., Nuthalapati, S. V., Singh, A., Cheng, J., Li, A., Mishra, S. K., Jacobs, D. W., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.00640
The Hidden Evolution of Disguised Visual Context inside the VLMPreprint
Suharitdamrong, W., Alex, T., Zhu, X., Awais, M., & Atito, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.20077
Zhang, J., Lashkov, I., Zhou, S., & Zhang, G. (2026) · Artificial Intelligence for Transportation · doi:10.1016/j.ait.2026.100077
DnA: Denoising Attention for Visual Tasks
Campos, R., Maity, S., Li, X., Das, S., & Dutta, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_2
S2H-DPO: Hardness-Aware Preference Optimization for Vision–Language Models
Shukla, N., Jandial, S., & Ross, A. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1825
Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
Xu, Z., Wang, L., Liu, Y., Li, L., Zhou, H., Meng, F., Zhou, J., & Sun, X. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.571
CEBC: Conformal Evidence-Bounded Control for Low-Hallucination Vision–Language Generation
Mishra, A., Kumar, T., Shah, A., Bhattacharya, S., & Foltín, M. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.2142
Huang, B., Wang, Z., Chen, Y., & Du, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.00606
Toward Causal Generative Modeling: From Representation Learning to Controllable Generation
Komanduri, A. (2026) · Journal of the Arkansas Academy of Science
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.