Vision-Language Pretraining papers, 2023–2026

Key findings

• Vision-Language Pretraining went from 65 papers in 2023 to 87 in 2026, roughly 1.3x in three years.
• NeurIPS publishes the most Vision-Language Pretraining work: 93 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Applications · computer vision: papers tagged with both rose from 0 in 2023 to 9 in 2026.
• Among the 5 topics under Open-Vocabulary Vision, it ranks #4 by 2026 paper count; the fastest grower in the group, Visual Grounding, is up 4.3x versus 1.3x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Benchmarking Optimizers for Large Language Model Pretraining
• ICML 2026How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off
• ICLR 2026PonderLM: Pretraining Language Models to Ponder in Continuous Space
• CVPR 2026Large-scale Codec Avatars The Unreasonable Effectiveness of Large-scale Avatar Pretraining
• NeurIPS 2025ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining
• ICML 2025Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
• ICLR 2025Attributing Culture-Conditioned Generations to Pretraining Corpora
• CVPR 2025MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining
• NeurIPS 2024Data curation via joint example selection further accelerates multimodal learning
• ICML 2024Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
• ICLR 2024Demystifying CLIP Data
• CVPR 2024ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks
• NeurIPS 2023Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
• ICML 2023Contrastive Learning Meets Homophily: Two Birds with One Stone
• ICLR 2023Energy-Inspired Self-Supervised Pretraining for Vision Models
• CVPR 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm
• NeurIPS 2026C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
• ICML 2026Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
• ICLR 2026MICLIP: Learning to Interpret Representation in Vision Models
• CVPR 2026The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations

All Vision-Language Pretraining papers

263 papers, page 5 of 6

201. CVPR 2023CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data
202. CVPR 2023CREPE: Can Vision-Language Foundation Models Reason Compositionally?
203. CVPR 2023DegAE: A New Pretraining Paradigm for Low-Level Vision
204. CVPR 2023Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models
205. CVPR 2023FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
206. CVPR 2023HyperMatch: Noise-Tolerant Semi-Supervised Learning via Relaxed Contrastive Constraint
207. CVPR 2023Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks
208. CVPR 2023Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding
209. CVPR 2023Learning Imbalanced Data With Vision Transformers
210. CVPR 2023Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce
211. CVPR 2023MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
212. CVPR 2023MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
213. CVPR 2023OmniMAE: Single Model Masked Pretraining on Images and Videos
214. CVPR 2023Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator
215. CVPR 2023Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
216. CVPR 2023Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers
217. CVPR 2023Training Debiased Subnetworks With Contrastive Weight Pruning
218. CVPR 2023VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining
219. ICLR 2023A theoretical study of inductive biases in contrastive learning
220. ICLR 2023CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
221. ICLR 2023Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning
222. ICLR 2023Energy-Inspired Self-Supervised Pretraining for Vision Models
223. ICLR 2023From $t$-SNE to UMAP with contrastive learning
224. ICLR 2023HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention
225. ICLR 2023Learning Language Representations with Logical Inductive Bias
226. ICLR 2023Proposal-Contrastive Pretraining for Object Detection from Fewer Data
227. ICLR 2023Protein Representation Learning by Geometric Structure Pretraining
228. ICLR 2023Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints
229. ICLR 2023UL2: Unifying Language Learning Paradigms
230. ICLR 2023What Do Self-Supervised Vision Transformers Learn?
231. ICLR 2023When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?
232. ICML 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
233. ICML 2023Contrastive Learning Meets Homophily: Two Birds with One Stone
234. ICML 2023End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
235. ICML 2023Lifelong Language Pretraining with Distribution-Specialized Experts
236. ICML 2023Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
237. ICML 2023Pretraining Language Models with Human Preferences
238. ICML 2023Why Is Public Pretraining Necessary for Private Model Training?
239. ICML 2023XTab: Cross-table Pretraining for Tabular Transformers
240. NeurIPS 2023Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
241. NeurIPS 2023Brain encoding models based on multimodal transformers can transfer across language and vision
242. NeurIPS 2023CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
243. NeurIPS 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
244. NeurIPS 2023D4: Improving LLM Pretraining via Document De-Duplication and Diversification
245. NeurIPS 2023DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics
246. NeurIPS 2023Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
247. NeurIPS 2023DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
248. NeurIPS 2023Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
249. NeurIPS 2023Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation
250. NeurIPS 2023Image Captioners Are Scalable Vision Learners Too

FAQ

How many Vision-Language Pretraining papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

263 in total: 65 in 2023, 55 in 2024, 56 in 2025, 87 in 2026.

How many Vision-Language Pretraining papers are at NeurIPS 2026?

NeurIPS 2026 has 27 Vision-Language Pretraining papers, versus 26 the year before.

How many Vision-Language Pretraining papers are at ICLR 2026?

ICLR 2026 has 14 Vision-Language Pretraining papers, versus 17 the year before.

How many Vision-Language Pretraining papers are at ICML 2026?

ICML 2026 has 19 Vision-Language Pretraining papers, versus 3 the year before.

How many Vision-Language Pretraining papers are at CVPR 2026?

CVPR 2026 has 27 Vision-Language Pretraining papers, versus 10 the year before.

Which conference publishes the most Vision-Language Pretraining papers?

NeurIPS, with 93 papers from 2023 to 2026.