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 8 of 54

351. ICLR 2026Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding
352. ICLR 2026Entropy-Monitored Kernelized Token Distillation for Audio-Visual Compression
353. ICLR 2026EntropyLong: Effective Long-Context Training via Predictive Uncertainty
354. ICLR 2026Equilibrium Language Models
355. ICLR 2026Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
356. ICLR 2026ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
357. ICLR 2026Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models
358. ICLR 2026ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
359. ICLR 2026Escaping Low-Rank Traps: Interpretable Visual Concept Learning via Implicit Vector Quantization
360. ICLR 2026Estimating Semantic Alphabet Size for LLM Uncertainty Quantification
361. ICLR 2026Evaluating Cross-Modal Reasoning Ability and Problem Charactaristics with Multimodal Item Response Theory
362. ICLR 2026EventFlash: Towards Efficient MLLMs for Event-Based Vision
363. ICLR 2026Evidence for Limited Metacognition in LLMs
364. ICLR 2026EVLP: Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning
365. ICLR 2026Evolution and compression in LLMs: on the emergence of human-aligned categorization
366. ICLR 2026Expert Divergence Learning for MoE-based Language Models
367. ICLR 2026Expert Heads: Robust Evidence Identification for Large Language Models
368. ICLR 2026Expert Merging in Sparse Mixture of Experts with Nash Bargaining
369. ICLR 2026Explainable LLM Unlearning through Reasoning
370. ICLR 2026Exploiting Low-Dimensional Manifold of Features for Few-shot Whole Slide Image Classification
371. ICLR 2026Exploring Cross-Modal Flows for Few-Shot Learning
372. ICLR 2026Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
373. ICLR 2026Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs
374. ICLR 2026Exploring the Basin-Like Loss Landscape in Large Language Models
375. ICLR 2026ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
376. ICLR 2026Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction
377. ICLR 2026Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding
378. ICLR 2026Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs
379. ICLR 2026FakeXplain: AI-Generated Image Detection via Human-Aligned Grounded Reasoning
380. ICLR 2026Falcon: Fast Proximal Linearization of Normalized Cuts for Unsupervised Image Segmentation
381. ICLR 2026Fantastic Tractor-Dogs and How Not to Find Them With Open-Vocabulary Detectors
382. ICLR 2026FASA: FREQUENCY-AWARE SPARSE ATTENTION
383. ICLR 2026Fast Data Mixture Optimization via Gradient Descent
384. ICLR 2026FaSTA*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
385. ICLR 2026Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
386. ICLR 2026Faster Vision Transformers with Adaptive Patches
387. ICLR 2026FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise Decoding
388. ICLR 2026Fed-Duet: Dual Expert-Orchestrated Framework for Continual Federated Vision-Language Learning
389. ICLR 2026FETAL-GAUGE: A BENCHMARK FOR ASSESSING VISION-LANGUAGE MODELS IN FETAL ULTRASOUND
390. ICLR 2026Figma2Code: Automating Multimodal Design to Code in the Wild
391. ICLR 2026Fine-Grained Activation Steering: Steering Less, Achieving More
392. ICLR 2026Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
393. ICLR 2026FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
394. ICLR 2026FlashRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
395. ICLR 2026FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
396. ICLR 2026Flatness Guided Test-Time Adaptation for Vision-Language Models
397. ICLR 2026Flatter Tokens are More Valuable for Speculative Draft Model Training
398. ICLR 2026FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
399. ICLR 2026Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets
400. ICLR 2026FlowAD: Ego-Scene Interactive Modeling for Autonomous Driving

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.