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 11 of 28

501. NeurIPS 2026From Heartbeat to Cardiochoreography: A Mechanics Foundation Model for Individualized 4D Cardiac Motion Generation Conditioned on Electrophysiology
502. NeurIPS 2026From Label Priors to Task Evidence: Long-Video Frame Selection via Bayesian GRPO
503. NeurIPS 2026From Matrix Inversion to Constraints: Provably Tighter Confidence Regions for Importance Weights in Label Shift
504. NeurIPS 2026From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient
505. NeurIPS 2026From Perception to Punchline: Empowering VLM with the Art of In-the-wild Memes
506. NeurIPS 2026From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent Space
507. NeurIPS 2026From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
508. NeurIPS 2026From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
509. NeurIPS 2026From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models
510. NeurIPS 2026From Weeks to Hours: Fast and Principled SFT Curation for LLM
511. NeurIPS 2026FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
512. NeurIPS 2026FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning
513. NeurIPS 2026Fusion or Confusion? Multimodal Complexity Is Not All You Need
514. NeurIPS 2026FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
515. NeurIPS 2026FUTON: Fourier Tensor Network for Implicit Neural Representations
516. NeurIPS 2026G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
517. NeurIPS 2026GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment
518. NeurIPS 2026GEAR: A GPU-Accelerated Global Solver for Nonlinear Programs via Linear Bound Propagation
519. NeurIPS 2026GeLVR: Geometry-Consistent Latent Visual Reasoning in Multimodal LLMs
520. NeurIPS 2026Generalized Influence Functions for Better Model Change Estimates
521. NeurIPS 2026Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife
522. NeurIPS 2026Generation-for-Understanding with Structured Action Scripts for Embodied Multimodal Learning
523. NeurIPS 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
524. NeurIPS 2026Generative Scenario Rollouts for End-to-End Autonomous Driving
525. NeurIPS 2026GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
526. NeurIPS 2026GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
527. NeurIPS 2026GeoDial: A Multimodal Dialog Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns
528. NeurIPS 2026GeoMamba: Geometry-Aware State Space Modeling for Image Restoration
529. NeurIPS 2026Geometric Latent Reasoning Induces Shorter Generations in LLMs
530. NeurIPS 2026Geometry is an Operator: Lie-Algebraic Space Routing for View-Robust 3D MLLMs
531. NeurIPS 2026Geometry-Aware Zeroth-Order Optimization for Fine-Tuning Quantized LLMs
532. NeurIPS 2026Geometry-Calibrated Conformal Abstention for Language Models
533. NeurIPS 2026GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization
534. NeurIPS 2026GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
535. NeurIPS 2026Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
536. NeurIPS 2026GIVLA: Deep Geometry Internalization for A Lightweight VLA via Geometry Instruction and Gradient-Informed Training
537. NeurIPS 2026Glance Before You Tell: Anomaly-Guided 3D Radiology Report Generation with Heat-Conduction Slice Encoders
538. NeurIPS 2026GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations
539. NeurIPS 2026GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
540. NeurIPS 2026Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
541. NeurIPS 2026GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning
542. NeurIPS 2026GPT-Image-Edit-1M: An Auditable Million-Scale Dataset for Instruction-Guided Image Editing
543. NeurIPS 2026Greedy Alignment Principle for Optimizer Selection
544. NeurIPS 2026GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement
545. NeurIPS 2026GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
546. NeurIPS 2026Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model
547. NeurIPS 2026Grounding Multimodal Reasoning with Evidence-Ablated Negatives
548. NeurIPS 2026GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
549. NeurIPS 2026GT-Free OCR Metrics: A Reference-Free Evaluation Framework for Document OCR Systems
550. NeurIPS 2026Guiding Data Allocation for Robust Subpopulation Generalization

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.