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

5,190 papers, page 94 of 104

4651. NeurIPS 2026Omni-Interactive Universal Embedder
4652. NeurIPS 2026OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
4653. NeurIPS 2026OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
4654. NeurIPS 2026OmniSE: Support-Faithful Optimization for Evidence-Centric Audio-Video Reasoning
4655. NeurIPS 2026OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
4656. NeurIPS 2026OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
4657. NeurIPS 2026OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
4658. NeurIPS 2026OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning
4659. NeurIPS 2026On JEPA Isotropy
4660. NeurIPS 2026On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
4661. NeurIPS 2026On the Provable Emergence of Hierarchical Concept Structure in CLIP Embeddings
4662. NeurIPS 2026On the Relaxation of Conditional Independence Assumption for Image Segmentation
4663. NeurIPS 2026On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
4664. NeurIPS 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
4665. NeurIPS 2026One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
4666. NeurIPS 2026OneCanvas: 3D Scene Understanding via Panoramic Reprojection
4667. NeurIPS 2026OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
4668. NeurIPS 2026Online Evaluation of LLMs via Dyadic Designs
4669. NeurIPS 2026Open Vocabulary Domain Unlearning
4670. NeurIPS 2026OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models
4671. NeurIPS 2026OpenView: Empowering MLLMs with Out-of-view VQA
4672. NeurIPS 2026OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation
4673. NeurIPS 2026Operads for compositional reasoning in LLMs
4674. NeurIPS 2026OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
4675. NeurIPS 2026Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation
4676. NeurIPS 2026OrbitLoRA: Learning Rotation-Aware Low-Data Adaptation of Vision Foundation Models
4677. NeurIPS 2026Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection
4678. NeurIPS 2026Origami as a Real-Image Benchmark for Procedural State-Transition Reasoning
4679. NeurIPS 2026OroPrecipBench: a km-scale benchmark for spatial precipitation downscaling over complex terrain
4680. NeurIPS 2026OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action Policies
4681. NeurIPS 2026OTEdit: Entropic Transport Corrected Trajectory for Inversion-Free Flow-Based Image Editing
4682. NeurIPS 2026Overcoming Kernel Redundancy for Scaling Logic Gate Networks
4683. NeurIPS 2026OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
4684. NeurIPS 2026P-EAGLE: Parallel-Drafting EAGLE with Scalable Training
4685. NeurIPS 2026P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models
4686. NeurIPS 2026PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models
4687. NeurIPS 2026PACE: Pareto-Adaptive Compression for Efficient Native MLLMs
4688. NeurIPS 2026PACE: Progress Actively-internalized Conditioning Execution for Long-horizon Manipulation
4689. NeurIPS 2026PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
4690. NeurIPS 2026PAI-Actor: Cinematic Multi-Actor Character Replacement in Dynamic Scenes
4691. NeurIPS 2026Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
4692. NeurIPS 2026Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
4693. NeurIPS 2026PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World
4694. NeurIPS 2026PaperLens: How Predictable Is Paper Acceptance?
4695. NeurIPS 2026PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
4696. NeurIPS 2026Parameterized Stripe Attention for Efficient Video Generation
4697. NeurIPS 2026Parametric Meets Non-parametric: Bridging Dual Prediction Spaces for Semi-supervised Medical Image Segmentation
4698. NeurIPS 2026PARE: Pruning and Adaptive Routing for Efficient Video Generation
4699. NeurIPS 2026Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models
4700. NeurIPS 2026Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers

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.