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

2,676 papers, page 51 of 54

2501. ICLR 2024Think before you speak: Training Language Models With Pause Tokens
2502. ICLR 2024TiC-CLIP: Continual Training of CLIP Models
2503. ICLR 2024Time Travel in LLMs: Tracing Data Contamination in Large Language Models
2504. ICLR 2024Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
2505. ICLR 2024TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
2506. ICLR 2024Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models
2507. ICLR 2024Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
2508. ICLR 2024Towards Foundation Models for Knowledge Graph Reasoning
2509. ICLR 2024Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection
2510. ICLR 2024Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
2511. ICLR 2024Training Diffusion Models with Reinforcement Learning
2512. ICLR 2024Unbiased Watermark for Large Language Models
2513. ICLR 2024Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
2514. ICLR 2024Understanding prompt engineering may not require rethinking generalization
2515. ICLR 2024Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
2516. ICLR 2024UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
2517. ICLR 2024Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
2518. ICLR 2024UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
2519. ICLR 2024UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
2520. ICLR 2024Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
2521. ICLR 2024Unveiling the Pitfalls of Knowledge Editing for Large Language Models
2522. ICLR 2024V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
2523. ICLR 2024VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
2524. ICLR 2024Video Language Planning
2525. ICLR 2024ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
2526. ICLR 2024Vision-by-Language for Training-Free Compositional Image Retrieval
2527. ICLR 2024Vision-Language Foundation Models as Effective Robot Imitators
2528. ICLR 2024Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
2529. ICLR 2024Visual Data-Type Understanding does not emerge from scaling Vision-Language Models
2530. ICLR 2024Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
2531. ICLR 2024What Algorithms can Transformers Learn? A Study in Length Generalization
2532. ICLR 2024What's in a Prior? Learned Proximal Networks for Inverse Problems
2533. ICLR 2024When Semantic Segmentation Meets Frequency Aliasing
2534. ICLR 2024Win-Win: Training High-Resolution Vision Transformers from Two Windows
2535. ICLR 2024Window Attention is Bugged: How not to Interpolate Position Embeddings
2536. ICLR 2024WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
2537. ICLR 2024Xformer: Hybrid X-Shaped Transformer for Image Denoising
2538. ICLR 2024ZipIt! Merging Models from Different Tasks without Training
2539. ICLR 20233D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation
2540. ICLR 2023A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
2541. ICLR 2023A General Rank Preserving Framework for Asymmetric Image Retrieval
2542. ICLR 2023A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
2543. ICLR 2023A Neural Mean Embedding Approach for Back-door and Front-door Adjustment
2544. ICLR 2023A Primal-Dual Framework for Transformers and Neural Networks
2545. ICLR 2023Accurate Image Restoration with Attention Retractable Transformer
2546. ICLR 2023Achieve the Minimum Width of Neural Networks for Universal Approximation
2547. ICLR 2023Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation
2548. ICLR 2023AIM: Adapting Image Models for Efficient Video Action Recognition
2549. ICLR 2023Almost Linear Constant-Factor Sketching for $\ell_1$ and Logistic Regression
2550. ICLR 2023Ask Me Anything: A simple strategy for prompting language models

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.