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

390 papers, page 2 of 8

51. ICML 2025Contrastive Localized Language-Image Pre-Training
52. ICML 2025CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
53. ICML 2025Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
54. ICML 2025CPCF: A Cross-Prompt Contrastive Framework for Referring Multimodal Large Language Models
55. ICML 2025Cradle: Empowering Foundation Agents towards General Computer Control
56. ICML 2025Cross-Modal Alignment via Variational Copula Modelling
57. ICML 2025CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
58. ICML 2025CTBench: A Library and Benchmark for Certified Training
59. ICML 2025CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
60. ICML 2025Curvature Enhanced Data Augmentation for Regression
61. ICML 2025DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
62. ICML 2025Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development
63. ICML 2025DEALing with Image Reconstruction: Deep Attentive Least Squares
64. ICML 2025Decomposition of Graphic Design with Unified Multimodal Model
65. ICML 2025Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension Reduction
66. ICML 2025DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts
67. ICML 2025Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision
68. ICML 2025Delta Decompression for MoE-based LLMs Compression
69. ICML 2025Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
70. ICML 2025Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMs
71. ICML 2025Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
72. ICML 2025Diffusion Instruction Tuning
73. ICML 2025DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression
74. ICML 2025Dimensionality Reduction on Complex Vector Spaces for Euclidean Distance with Dynamic Weights
75. ICML 2025DIS-CO: Discovering Copyrighted Content in VLMs Training Data
76. ICML 2025DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
77. ICML 2025Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering
78. ICML 2025Do Vision-Language Models Really Understand Visual Language?
79. ICML 2025DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning
80. ICML 2025Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering
81. ICML 2025DS-VLM: Diffusion Supervision Vision Language Model
82. ICML 2025Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning
83. ICML 2025DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making
84. ICML 2025EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
85. ICML 2025EditLord: Learning Code Transformation Rules for Code Editing
86. ICML 2025EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction
87. ICML 2025EEG-Language Pretraining for Highly Label-Efficient Clinical Phenotyping
88. ICML 2025Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
89. ICML 2025Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment
90. ICML 2025Efficient Multi-modal Long Context Learning for Training-free Adaptation
91. ICML 2025Efficient Quantification of Multimodal Interaction at Sample Level
92. ICML 2025Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
93. ICML 2025Efficiently Serving Large Multimodal Models Using EPD Disaggregation
94. ICML 2025ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
95. ICML 2025ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
96. ICML 2025Elucidating the design space of language models for image generation
97. ICML 2025Elucidating the Design Space of Multimodal Protein Language Models
98. ICML 2025Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
99. ICML 2025Emergent Response Planning in LLMs
100. ICML 2025Empowering World Models with Reflection for Embodied Video Prediction

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.