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

1,051 papers, page 14 of 22

651. ICML 2026PosterAgent: Agentic Poster Generation via Stage-Aware Reinforcement Learning
652. ICML 2026Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
653. ICML 2026Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
654. ICML 2026Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
655. ICML 2026PRIM：Cooperative Dynamic Token Compression for Efficient Large Multimodal Models
656. ICML 2026Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation
657. ICML 2026PRISM: Perception Reasoning Interleaved for Sequential Decision Making.
658. ICML 2026PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization
659. ICML 2026PRISM: Training-Free Video Anomaly Detection via Intrinsic Statistical Modeling
660. ICML 2026Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
661. ICML 2026ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response
662. ICML 2026ProactiveLLM: Learning Active Interaction for Streaming Large Language Models
663. ICML 2026Probabilistic Salient Object Ranking
664. ICML 2026Probably Approximately Correct Labels
665. ICML 2026Probing How Scalable Table Data Enhances General Long-Context Reasoning
666. ICML 2026Procedural Pretraining: Warming Up Language Models with Abstract Data
667. ICML 2026ProConMV: Provenance-Enabled Conceptual Framework for Interpretable Multi-View Diabetic Retinopathy Diagnosis
668. ICML 2026Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers
669. ICML 2026Prompt Tuning for CLIP on the Pretrained Manifold
670. ICML 2026ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling
671. ICML 2026Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
672. ICML 2026Proteus: Lookup-Free Trellis-Coded Quantization by Lattice-Breaking Compute Codes for 2-Bit LLMs
673. ICML 2026Prototype-Based Test-Time Adaptation of Vision-Language Models
674. ICML 2026Prototype-guided Bilateral Alignment Multimodal Federated Learning
675. ICML 2026Proximal-IMH: Proximal Posterior Proposals for Independent Metropolis–Hastings with Approximate Operators
676. ICML 2026PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
677. ICML 2026PSBench: Editing Image via GUI Agents in Photoshop
678. ICML 2026Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation
679. ICML 2026Q-Delta: Beyond Key–Value Associative State Evolution
680. ICML 2026QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog Generation
681. ICML 2026QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
682. ICML 2026Quantifying the noise sensitivity of the Wasserstein metric for images
683. ICML 2026QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
684. ICML 2026R$^3$L: Reasoning 3D Layouts from Relative Spatial Relations
685. ICML 2026R2-Router: A New Paradigm for LLM Routing with Reasoning
686. ICML 2026RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
687. ICML 2026RaBiT: Residual Aware Binarization Training for Accurate and Efficient LLMs
688. ICML 2026RADIO1D: Elastic Representations for Condensed Vision Modeling
689. ICML 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
690. ICML 2026Real-Time Visual Attribution Streaming in Thinking Model
691. ICML 2026REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment
692. ICML 2026Reason with Thumbnails, Answer with Focus: An Efficient and Effective Paradigm for Multimodal Grounded Visual Reasoning
693. ICML 2026Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
694. ICML 2026ReasonEdit: Editing Vision--Language Models using Human Reasoning
695. ICML 2026Reasoning Compartmentalization: Bridging the Concretization Gap via Abstraction-based Routing
696. ICML 2026Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge
697. ICML 2026Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
698. ICML 2026Reasoning-VLA: An Efficient and Spatial-Guided General Vision-Language-Action Reasoning Model for Autonomous Driving
699. ICML 2026RefChess: Training-Free Contextual Search for Zero-Shot Referring Image Segmentation
700. ICML 2026Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering

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.