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

1,366 papers, page 17 of 28

801. NeurIPS 2026Neural Spectral Capacity: An Architectural Quantity from Network Specification Alone
802. NeurIPS 2026Neuro-KE: Knowledge-Guided Interfaces for Semantically Grounded EEG Foundation Models
803. NeurIPS 2026NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
804. NeurIPS 2026Neuron Populations Exhibit Divergent Selectivity with Scale
805. NeurIPS 2026NeuroNTP - A Generalizable Multimodal Foundation Model for Epilepsy
806. NeurIPS 2026Never Stop Learning: Test-Time Reinforcement Learning for Vision-Language-Action Models
807. NeurIPS 2026No Free Alignment: Observability-Aware Alignment for Multimodal Heterogeneous Learning
808. NeurIPS 2026No One Knows the State-of-the-Art in Geospatial Foundation Models
809. NeurIPS 2026Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
810. NeurIPS 2026Nonlinear Direct Feedback Alignment for Scalable Backpropagation-Free Training
811. NeurIPS 2026Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation
812. NeurIPS 2026Normative Networks for Source Separation via Local Plasticity and Dendritic Computation
813. NeurIPS 2026Not All Layers Are Equal in Image-to-Video Transfer
814. NeurIPS 2026Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models
815. NeurIPS 2026Not Every Image Teaches Vision: Visual-Necessity-Gated Continual Learning for Multimodal Large Language Models
816. NeurIPS 2026Not Suppressing or Purifying: Backdoor Containment via Expert Quarantine and Shutdown in LLMs
817. NeurIPS 2026NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
818. NeurIPS 2026NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
819. NeurIPS 2026NPCBench: A Clinical Apprenticeship Benchmark for Guideline-Constrained Care-Pathway Reasoning in Nasopharyngeal Carcinoma
820. NeurIPS 2026NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
821. NeurIPS 2026Nüwa.RNA: An RNA Foundation Model for Unified Representation with Deep Structure Infusion
822. NeurIPS 2026OATS: Online Data Augmentation for Time Series Foundation Models
823. NeurIPS 2026Object Hallucination Mitigation in Large Vision-Language Models via Self-Vision Dual Masking and Uncertainty-Triggered Assembly
824. NeurIPS 2026OBJECT-UNI: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation
825. NeurIPS 2026OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
826. NeurIPS 2026OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
827. NeurIPS 2026Omni-Interactive Universal Embedder
828. NeurIPS 2026OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
829. NeurIPS 2026OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
830. NeurIPS 2026OmniSE: Support-Faithful Optimization for Evidence-Centric Audio-Video Reasoning
831. NeurIPS 2026OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
832. NeurIPS 2026OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
833. NeurIPS 2026OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
834. NeurIPS 2026OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning
835. NeurIPS 2026On JEPA Isotropy
836. NeurIPS 2026On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
837. NeurIPS 2026On the Provable Emergence of Hierarchical Concept Structure in CLIP Embeddings
838. NeurIPS 2026On the Relaxation of Conditional Independence Assumption for Image Segmentation
839. NeurIPS 2026On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
840. NeurIPS 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
841. NeurIPS 2026One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
842. NeurIPS 2026OneCanvas: 3D Scene Understanding via Panoramic Reprojection
843. NeurIPS 2026OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
844. NeurIPS 2026Online Evaluation of LLMs via Dyadic Designs
845. NeurIPS 2026Open Vocabulary Domain Unlearning
846. NeurIPS 2026OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models
847. NeurIPS 2026OpenView: Empowering MLLMs with Out-of-view VQA
848. NeurIPS 2026OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation
849. NeurIPS 2026Operads for compositional reasoning in LLMs
850. NeurIPS 2026OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation

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.