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

1,401 papers, page 7 of 29

301. ICLR 2026DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
302. ICLR 2026DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing
303. ICLR 2026DRIFT-Net: A Spectral-Coupled Neural Operator for PDEs Learning
304. ICLR 2026DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking
305. ICLR 2026DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
306. ICLR 2026DTP: Delta-Guided Two Stage Pruning for Mamba-based Multimodal Large Language Models
307. ICLR 2026Dual Language Models: Balancing sample-efficiency and overfitting resilience
308. ICLR 2026Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis
309. ICLR 2026DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
310. ICLR 2026Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
311. ICLR 2026Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
312. ICLR 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
313. ICLR 2026DynamicInfer: Runtime-Aware Sparse Offloading for LLMs Inference on a Consumer-Grade GPU
314. ICLR 2026Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
315. ICLR 2026EAMET: ROBUST MASSIVE MODEL EDITING VIA EMBEDDING ALIGNMENT OPTIMIZATION
316. ICLR 2026Early Signs of Steganographic Capabilities in Frontier LLMs
317. ICLR 2026EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements
318. ICLR 2026EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
319. ICLR 2026EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
320. ICLR 2026Efficient Agent Training for Computer Use
321. ICLR 2026Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
322. ICLR 2026Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
323. ICLR 2026Efficient Message-Passing Transformer for Error Correcting Codes
324. ICLR 2026Efficient Multimodal Spatial Reasoning via Dynamic and Asymmetric Routing
325. ICLR 2026Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees
326. ICLR 2026Efficient Test-Time Scaling for Small Vision-Language Models
327. ICLR 2026EgoBrain: Synergizing Minds and Eyes For Human Action Understanding
328. ICLR 2026EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
329. ICLR 2026EgoTwin: Dreaming Body and View in First Person
330. ICLR 2026ELEPHANT: Measuring and understanding social sycophancy in LLMs
331. ICLR 2026Eliciting Numerical Predictive Distributions of LLMs Without Auto-Regression
332. ICLR 2026Embodied Navigation Foundation Model
333. ICLR 2026Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
334. ICLR 2026Emergent Discrete Controller Modules for Symbolic Planning in Transformers
335. ICLR 2026EmoPrefer: Can Large Language Models Understand Human Emotion Preferences?
336. ICLR 2026EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models
337. ICLR 2026EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning
338. ICLR 2026Empowering Small VLMs to Think with Dynamic Memorization and Exploration
339. ICLR 2026Enabling True Global Perception in State Space Models for Visual Tasks
340. ICLR 2026Enabling Your Forensic Detector Know How Well It Performs on Distorted Samples
341. ICLR 2026ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
342. ICLR 2026Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World
343. ICLR 2026Enhanced Continual Learning of Vision-Language Models with Model Fusion
344. ICLR 2026Enhancing Geometric Perception in VLMs via Translator-Guided Reinforcement Learning
345. ICLR 2026Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
346. ICLR 2026Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition
347. ICLR 2026Enhancing Multi-Image Understanding through Delimiter Token Scaling
348. ICLR 2026Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset Selection
349. ICLR 2026Enhancing Visual Token Representations for Video Large Language Models via Training-free Spatial-Temporal Pooling and Gridding
350. ICLR 2026Entropy-Based Block Pruning for Efficient 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.