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

11,207 papers, page 128 of 225

6351. ICLR 2025Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding
6352. ICLR 2025Latent Action Pretraining from Videos
6353. ICLR 2025Layerwise Recurrent Router for Mixture-of-Experts
6354. ICLR 2025LeanAgent: Lifelong Learning for Formal Theorem Proving
6355. ICLR 2025Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion
6356. ICLR 2025Learning Diagrams: A Graphical Language for Compositional Training Regimes
6357. ICLR 2025Learning Dynamics of LLM Finetuning
6358. ICLR 2025Learning Gain Map for Inverse Tone Mapping
6359. ICLR 2025Learning Harmonized Representations for Speculative Sampling
6360. ICLR 2025Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
6361. ICLR 2025Learning Mask Invariant Mutual Information for Masked Image Modeling
6362. ICLR 2025Learning Spatial-Semantic Features for Robust Video Object Segmentation
6363. ICLR 2025Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
6364. ICLR 2025LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions
6365. ICLR 2025Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction
6366. ICLR 2025Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
6367. ICLR 2025LICO: Large Language Models for In-Context Molecular Optimization
6368. ICLR 2025Lightweight Neural App Control
6369. ICLR 2025LiveBench: A Challenging, Contamination-Limited LLM Benchmark
6370. ICLR 2025LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
6371. ICLR 2025LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing
6372. ICLR 2025LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
6373. ICLR 2025LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
6374. ICLR 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
6375. ICLR 2025LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases
6376. ICLR 2025LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension
6377. ICLR 2025LLMs Can Plan Only If We Tell Them
6378. ICLR 2025LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
6379. ICLR 2025Local Patterns Generalize Better for Novel Anomalies
6380. ICLR 2025Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection
6381. ICLR 2025Locality Alignment Improves Vision-Language Models
6382. ICLR 2025Logically Consistent Language Models via Neuro-Symbolic Integration
6383. ICLR 2025Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
6384. ICLR 2025LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
6385. ICLR 2025Long Context Compression with Activation Beacon
6386. ICLR 2025Longhorn: State Space Models are Amortized Online Learners
6387. ICLR 2025LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
6388. ICLR 2025Looking Inward: Language Models Can Learn About Themselves by Introspection
6389. ICLR 2025LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation Models
6390. ICLR 2025LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
6391. ICLR 2025Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
6392. ICLR 2025MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval
6393. ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
6394. ICLR 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
6395. ICLR 2025MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
6396. ICLR 2025Matryoshka Multimodal Models
6397. ICLR 2025MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
6398. ICLR 2025MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
6399. ICLR 2025Measuring And Improving Engagement of Text-to-Image Generation Models
6400. ICLR 2025Measuring And Improving Persuasiveness Of Large 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.