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

1,051 papers, page 21 of 22

1001. ICML 2026Vision Transformer Finetuning Benefits from Non-Smooth Components
1002. ICML 2026Vision-aligned Latent Reasoning for Multi-modal Large Language Model
1003. ICML 2026Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
1004. ICML 2026Vision-Language-Action Pretraining from Large-Scale Human Videos
1005. ICML 2026Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
1006. ICML 2026VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning
1007. ICML 2026Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
1008. ICML 2026Visual Persuasion: What Influences Decisions of Vision-Language Models?
1009. ICML 2026VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge
1010. ICML 2026VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
1011. ICML 2026VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
1012. ICML 2026VLANeXt: Recipes for Building Strong VLA Models
1013. ICML 2026VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
1014. ICML 2026VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models
1015. ICML 2026VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing
1016. ICML 2026Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction
1017. ICML 2026VR-Thinker: Boosting Multimodal Reward Models through Think with Image Reasoning
1018. ICML 2026VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning
1019. ICML 2026WatchLog: Efficient and Interpretable Event Reasoning for Endpoint Detection and Response Logs with Multimodal LLMs
1020. ICML 2026Weaving Graph over Tokens: Contextualizing Structured Sequences for LLMs
1021. ICML 2026Weight-Space Learning for Certifiable Few-shot Transfer Learning
1022. ICML 2026What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
1023. ICML 2026When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
1024. ICML 2026When Does Sparsity Mitigate the Curse of Depth in LLMs
1025. ICML 2026When Is Rank-1 Enough? Geometry-Guided Initialization for Parameter-Efficient Fine-Tuning
1026. ICML 2026When LLMs Encounter Open-world Graph Learning: A Fresh View on Unlabeled Data Uncertainty
1027. ICML 2026When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
1028. ICML 2026When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
1029. ICML 2026When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
1030. ICML 2026Why Are Linear RNNs More Parallelizable?
1031. ICML 2026Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO
1032. ICML 2026Width Independent Bounds for the Local Lipschitz Constant of Deep Neural Networks at Random Initialization and after Lazy Training
1033. ICML 2026WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop Environments
1034. ICML 2026WISE: World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
1035. ICML 2026WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models
1036. ICML 2026World Guidance: World Modeling in Condition Space for Action Generation
1037. ICML 2026World-Model Inspired Emotion-aware Token Refinement for Training-Free Multimodal Emotion Recognition
1038. ICML 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
1039. ICML 2026WorldTravel: A Realistic Multimodal Travel-Planning Benchmark with Tightly Coupled Constraints
1040. ICML 2026WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
1041. ICML 2026XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition
1042. ICML 2026XPERT: Expert Knowledge Transfer for Effective Training of Language Models
1043. ICML 2026XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations
1044. ICML 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agents
1045. ICML 2026Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation
1046. ICML 2026Zero-shot Active Mapping via Fused 360-BEV Representations and Vision–Language Models
1047. ICML 2026Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language
1048. ICML 2026Zero-Shot Text-to-Motion Evaluation using Video Language Models
1049. ICML 2026ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
1050. ICML 2026Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

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.