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

816 papers, page 12 of 17

551. ICLR 2025PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
552. ICLR 2025PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
553. ICLR 2025PiCO: Peer Review in LLMs based on Consistency Optimization
554. ICLR 2025Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming
555. ICLR 2025Planning in Natural Language Improves LLM Search for Code Generation
556. ICLR 2025PolaFormer: Polarity-aware Linear Attention for Vision Transformers
557. ICLR 2025Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
558. ICLR 2025Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
559. ICLR 2025PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos
560. ICLR 2025Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
561. ICLR 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
562. ICLR 2025Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
563. ICLR 2025ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs
564. ICLR 2025Probabilistic Language-Image Pre-Training
565. ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
566. ICLR 2025Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
567. ICLR 2025Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
568. ICLR 2025Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection
569. ICLR 2025Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning
570. ICLR 2025Proxy Denoising for Source-Free Domain Adaptation
571. ICLR 2025Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
572. ICLR 2025QPM: Discrete Optimization for Globally Interpretable Image Classification
573. ICLR 2025Quantifying Generalization Complexity for Large Language Models
574. ICLR 2025Quantized Spike-driven Transformer
575. ICLR 2025Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model
576. ICLR 2025R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
577. ICLR 2025RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models
578. ICLR 2025Radar: Fast Long-Context Decoding for Any Transformer
579. ICLR 2025RandLoRA: Full rank parameter-efficient fine-tuning of large models
580. ICLR 2025Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image Denoising
581. ICLR 2025Ranking-aware adapter for text-driven image ordering with CLIP
582. ICLR 2025Rapid Selection and Ordering of In-Context Demonstrations via Prompt Embedding Clustering
583. ICLR 2025Re-Aligning Language to Visual Objects with an Agentic Workflow
584. ICLR 2025Re-Imagining Multimodal Instruction Tuning: A Representation View
585. ICLR 2025Real2Code: Reconstruct Articulated Objects via Code Generation
586. ICLR 2025Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
587. ICLR 2025ReAttention: Training-Free Infinite Context with Finite Attention Scope
588. ICLR 2025Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
589. ICLR 2025ReCogLab: a framework testing relational reasoning & cognitive hypotheses on LLMs
590. ICLR 2025Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
591. ICLR 2025Reconstructive Visual Instruction Tuning
592. ICLR 2025Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering
593. ICLR 2025REEF: Representation Encoding Fingerprints for Large Language Models
594. ICLR 2025Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
595. ICLR 2025ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
596. ICLR 2025RegMix: Data Mixture as Regression for Language Model Pre-training
597. ICLR 2025Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer
598. ICLR 2025REMEDY: Recipe Merging Dynamics in Large Vision-Language Models
599. ICLR 2025Rethinking Invariance in In-context Learning
600. ICLR 2025RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning

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.