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

3,302 papers, page 32 of 67

1551. CVPR 2025DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
1552. CVPR 2025DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
1553. CVPR 2025Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality
1554. CVPR 2025DiskVPS: Vanishing Point Detector via Hough Transform in a Disk Region
1555. CVPR 2025Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
1556. CVPR 2025Distilled Prompt Learning for Incomplete Multimodal Survival Prediction
1557. CVPR 2025Distilling Monocular Foundation Model for Fine-grained Depth Completion
1558. CVPR 2025Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment
1559. CVPR 2025Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
1560. CVPR 2025DistinctAD: Distinctive Audio Description Generation in Contexts
1561. CVPR 2025Distraction is All You Need for Multimodal Large Language Model Jailbreaking
1562. CVPR 2025DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
1563. CVPR 2025DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
1564. CVPR 2025DL2G: Degradation-guided Local-to-Global Restoration for Eyeglass Reflection Removal
1565. CVPR 2025Do Computer Vision Foundation Models Learn the Low-level Characteristics of the Human Visual System?
1566. CVPR 2025Docopilot: Improving Multimodal Models for Document-Level Understanding
1567. CVPR 2025Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
1568. CVPR 2025DocVLM: Make Your VLM an Efficient Reader
1569. CVPR 2025Domain Generalization in CLIP via Learning with Diverse Text Prompts
1570. CVPR 2025DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles
1571. CVPR 2025DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution
1572. CVPR 2025DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models
1573. CVPR 2025DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation
1574. CVPR 2025DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
1575. CVPR 2025DreamTrack: Dreaming the Future for Multimodal Visual Object Tracking
1576. CVPR 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
1577. CVPR 2025DTOS: Dynamic Time Object Sensing with Large Multimodal Model
1578. CVPR 2025Dual Diffusion for Unified Image Generation and Understanding
1579. CVPR 2025Dual Exposure Stereo for Extended Dynamic Range 3D Imaging
1580. CVPR 2025Dual Semantic Guidance for Open Vocabulary Semantic Segmentation
1581. CVPR 2025Dual-Granularity Semantic Guided Sparse Routing Diffusion Model for General Pansharpening
1582. CVPR 2025DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition
1583. CVPR 2025DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
1584. CVPR 2025DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation
1585. CVPR 2025Dynamic Content Prediction with Motion-aware Priors for Blind Face Video Restoration
1586. CVPR 2025Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis
1587. CVPR 2025DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding
1588. CVPR 2025DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution
1589. CVPR 2025EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
1590. CVPR 2025EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting
1591. CVPR 2025ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark
1592. CVPR 2025EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights
1593. CVPR 2025ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression
1594. CVPR 2025EdgeTAM: On-Device Track Anything Model
1595. CVPR 2025EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark
1596. CVPR 2025Effective SAM Combination for Open-Vocabulary Semantic Segmentation
1597. CVPR 2025Efficient Transfer Learning for Video-language Foundation Models
1598. CVPR 2025Efficient Video Super-Resolution for Real-time Rendering with Decoupled G-buffer Guidance
1599. CVPR 2025Efficient Visual State Space Model for Image Deblurring
1600. CVPR 2025EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models

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.