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 133 of 225

6601. ICLR 2025SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
6602. ICLR 2025Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models
6603. ICLR 2025SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
6604. ICLR 2025SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
6605. ICLR 2025SBSC: Step-by-Step Coding for Improving Mathematical Olympiad Performance
6606. ICLR 2025Scaling Laws for Downstream Task Performance in Machine Translation
6607. ICLR 2025Scaling Laws for Precision
6608. ICLR 2025Scaling Long Context Training Data by Long-Distance Referrals
6609. ICLR 2025Scaling Optimal LR Across Token Horizons
6610. ICLR 2025Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study
6611. ICLR 2025Scaling Wearable Foundation Models
6612. ICLR 2025SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
6613. ICLR 2025ScImage: How good are multimodal large language models at scientific text-to-image generation?
6614. ICLR 2025Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer
6615. ICLR 2025See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
6616. ICLR 2025See What You Are Told: Visual Attention Sink in Large Multimodal Models
6617. ICLR 2025SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
6618. ICLR 2025SegLLM: Multi-round Reasoning Segmentation with Large Language Models
6619. ICLR 2025Segment Any 3D Object with Language
6620. ICLR 2025Selective Attention Improves Transformer
6621. ICLR 2025Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
6622. ICLR 2025Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
6623. ICLR 2025Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
6624. ICLR 2025Self-Updatable Large Language Models by Integrating Context into Model Parameters
6625. ICLR 2025Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs
6626. ICLR 2025Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement Learning
6627. ICLR 2025Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
6628. ICLR 2025Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal Consistency
6629. ICLR 2025Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
6630. ICLR 2025Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity
6631. ICLR 2025Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
6632. ICLR 2025Should VLMs be Pre-trained with Image Data?
6633. ICLR 2025Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
6634. ICLR 2025SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments
6635. ICLR 2025Sketch2Diagram: Generating Vector Diagrams from Hand-Drawn Sketches
6636. ICLR 2025SleepSMC: Ubiquitous Sleep Staging via Supervised Multimodal Coordination
6637. ICLR 2025SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
6638. ICLR 2025Small Models are LLM Knowledge Triggers for Medical Tabular Prediction
6639. ICLR 2025Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
6640. ICLR 2025Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises
6641. ICLR 2025SMT: Fine-Tuning Large Language Models with Sparse Matrices
6642. ICLR 2025Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
6643. ICLR 2025SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
6644. ICLR 2025SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
6645. ICLR 2025Sparse autoencoders reveal selective remapping of visual concepts during adaptation
6646. ICLR 2025Specialized Foundation Models Struggle to Beat Supervised Baselines
6647. ICLR 2025SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
6648. ICLR 2025SpinQuant: LLM Quantization with Learned Rotations
6649. ICLR 2025SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models
6650. ICLR 2025STAR: Synthesis of Tailored Architectures

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.