Multimodal LLMs papers, 2023–2026

Key findings

• Multimodal LLMs went from 1,226 papers in 2023 to 5,192 in 2026, roughly 4.2x in three years.
• NeurIPS publishes the most Multimodal LLMs work: 3,319 papers from 2023 to 2026, 30% of the four-venue total.
• The fastest-growing overlap is with Applications · computer vision: papers tagged with both rose from 35 in 2023 to 596 in 2026.
• Among the 4 topics under Trending Systems, it ranks #1 by 2026 paper count; the fastest grower in the group, AI Agents, is up 12x versus 4.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
• ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
• ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
• CVPR 20263D Space as a Scratchpad for Editable Text-to-Image Generation
• NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
• ICML 2025Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
• ICLR 2025$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
• CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
• NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
• ICML 2024A Multimodal Automated Interpretability Agent
• ICLR 2024Alt-Text with Context: Improving Accessibility for Images on Twitter
• CVPR 2024Data-Efficient Multimodal Fusion on a Single GPU
• NeurIPS 20234M: Massively Multimodal Masked Modeling
• ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
• ICLR 2023A Primal-Dual Framework for Transformers and Neural Networks
• CVPR 20233D Concept Learning and Reasoning From Multi-View Images
• NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
• ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
• CVPR 20263D-IDE 3D Implicit Depth Emergent

All Multimodal LLMs papers

433 papers, page 2 of 9

51. NeurIPS 2023Brant: Foundation Model for Intracranial Neural Signal
52. NeurIPS 2023Break It Down: Evidence for Structural Compositionality in Neural Networks
53. NeurIPS 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
54. NeurIPS 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
55. NeurIPS 2023CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches
56. NeurIPS 2023Can Language Models Solve Graph Problems in Natural Language?
57. NeurIPS 2023Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization
58. NeurIPS 2023CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models
59. NeurIPS 2023Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer
60. NeurIPS 2023CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care
61. NeurIPS 2023CAST: Cross-Attention in Space and Time for Video Action Recognition
62. NeurIPS 2023Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions
63. NeurIPS 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
64. NeurIPS 2023ChatGPT-Powered Hierarchical Comparisons for Image Classification
65. NeurIPS 2023Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
66. NeurIPS 2023Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models
67. NeurIPS 2023CLadder: Assessing Causal Reasoning in Language Models
68. NeurIPS 2023CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection
69. NeurIPS 2023COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs
70. NeurIPS 2023Cola: A Benchmark for Compositional Text-to-image Retrieval
71. NeurIPS 2023Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
72. NeurIPS 2023Compact Neural Volumetric Video Representations with Dynamic Codebooks
73. NeurIPS 2023Composable Coresets for Determinant Maximization: Greedy is Almost Optimal
74. NeurIPS 2023Compositional Foundation Models for Hierarchical Planning
75. NeurIPS 2023Computational Guarantees for Doubly Entropic Wasserstein Barycenters
76. NeurIPS 2023Computing a human-like reaction time metric from stable recurrent vision models
77. NeurIPS 2023Consensus and Subjectivity of Skin Tone Annotation for ML Fairness
78. NeurIPS 2023Context-PIPs: Persistent Independent Particles Demands Spatial Context Features
79. NeurIPS 2023Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels
80. NeurIPS 2023Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
81. NeurIPS 2023Convolutional State Space Models for Long-Range Spatiotemporal Modeling
82. NeurIPS 2023Counterfactual Memorization in Neural Language Models
83. NeurIPS 2023CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders
84. NeurIPS 2023CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography
85. NeurIPS 2023CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss
86. NeurIPS 2023D4: Improving LLM Pretraining via Document De-Duplication and Diversification
87. NeurIPS 2023DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
88. NeurIPS 2023Data Portraits: Recording Foundation Model Training Data
89. NeurIPS 2023Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
90. NeurIPS 2023DataComp: In search of the next generation of multimodal datasets
91. NeurIPS 2023DataPerf: Benchmarks for Data-Centric AI Development
92. NeurIPS 2023DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models
93. NeurIPS 2023Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model
94. NeurIPS 2023DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
95. NeurIPS 2023Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
96. NeurIPS 2023DesCo: Learning Object Recognition with Rich Language Descriptions
97. NeurIPS 2023Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents
98. NeurIPS 2023Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models
99. NeurIPS 2023DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics
100. NeurIPS 2023DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization

FAQ

How many Multimodal LLMs papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

11,209 in total: 1,226 in 2023, 1,716 in 2024, 3,075 in 2025, 5,192 in 2026.

How many Multimodal LLMs papers are at NeurIPS 2026?

NeurIPS 2026 has 1,366 Multimodal LLMs papers, versus 1,074 the year before.

How many Multimodal LLMs papers are at ICLR 2026?

ICLR 2026 has 1,401 Multimodal LLMs papers, versus 816 the year before.

How many Multimodal LLMs papers are at ICML 2026?

ICML 2026 has 1,051 Multimodal LLMs papers, versus 390 the year before.

How many Multimodal LLMs papers are at CVPR 2026?

CVPR 2026 has 1,374 Multimodal LLMs papers, versus 795 the year before.

Which conference publishes the most Multimodal LLMs papers?

NeurIPS, with 3,319 papers from 2023 to 2026.