多模态大模型论文趋势 2023–2026

主要结论

• 多模态大模型论文从 2023 年的 1,226 篇增长到 2026 年的 5,192 篇，三年间扩大到约 4.2 倍。
• NeurIPS 是发多模态大模型论文最多的会议，2023–2026 年共 3,319 篇，占四个会议总量的 30%。
• 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 596 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 1；同组增长最快的AI 智能体是 12 倍，多模态大模型是 4.2 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部多模态大模型论文

共 390 篇，第 1 / 8 页

1. ICML 2025$\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts
2. ICML 20253D Question Answering via only 2D Vision-Language Models
3. ICML 2025A Closer Look at Multimodal Representation Collapse
4. ICML 2025A Simple Model of Inference Scaling Laws
5. ICML 2025A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?
6. ICML 2025Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
7. ICML 2025Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation
8. ICML 2025AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
9. ICML 2025AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
10. ICML 2025AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment
11. ICML 2025Agent Reviewers: Domain-specific Multimodal Agents with Shared Memory for Paper Review
12. ICML 2025Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders
13. ICML 2025Aligning Multimodal Representations through an Information Bottleneck
14. ICML 2025An Analysis for Reasoning Bias of Language Models with Small Initialization
15. ICML 2025An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
16. ICML 2025An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability
17. ICML 2025An Entropy-Based Model for Hierarchical Learning
18. ICML 2025any4: Learned 4-bit Numeric Representation for LLMs
19. ICML 2025Attention-Level Speculation
20. ICML 2025Autoformulation of Mathematical Optimization Models Using LLMs
21. ICML 2025Avoiding spurious sharpness minimization broadens applicability of SAM
22. ICML 2025Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing
23. ICML 2025BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation
24. ICML 2025BaxBench: Can LLMs Generate Correct and Secure Backends?
25. ICML 2025BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition
26. ICML 2025Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning
27. ICML 2025Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
28. ICML 2025Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
29. ICML 2025Binary Hypothesis Testing for Softmax Models and Leverage Score Models
30. ICML 2025BoA: Attention-aware Post-training Quantization without Backpropagation
31. ICML 2025Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
32. ICML 2025Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
33. ICML 2025Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models
34. ICML 2025Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
35. ICML 2025CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
36. ICML 2025Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?
37. ICML 2025Can Large Language Models Understand Intermediate Representations in Compilers?
38. ICML 2025Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
39. ICML 2025Can We Predict Performance of Large Models across Vision-Language Tasks?
40. ICML 2025Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
41. ICML 2025CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
42. ICML 2025Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models
43. ICML 2025Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
44. ICML 2025CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models
45. ICML 2025CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization
46. ICML 2025CoMemo: LVLMs Need Image Context with Image Memory
47. ICML 2025Compositional Condition Question Answering in Tabular Understanding
48. ICML 2025Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
49. ICML 2025Context is Key: A Benchmark for Forecasting with Essential Textual Information
50. ICML 2025ConText: Driving In-context Learning for Text Removal and Segmentation

常见问题

2023–2026 年四大会议一共有多少篇多模态大模型论文？

共 11,209 篇，按年份分别是 2023 年 1,226 篇、2024 年 1,716 篇、2025 年 3,075 篇、2026 年 5,192 篇。

NeurIPS 2026 有多少篇多模态大模型论文？

NeurIPS 2026 有 1,366 篇多模态大模型论文，上一届是 1,074 篇。

ICLR 2026 有多少篇多模态大模型论文？

ICLR 2026 有 1,401 篇多模态大模型论文，上一届是 816 篇。

ICML 2026 有多少篇多模态大模型论文？

ICML 2026 有 1,051 篇多模态大模型论文，上一届是 390 篇。

CVPR 2026 有多少篇多模态大模型论文？

CVPR 2026 有 1,374 篇多模态大模型论文，上一届是 795 篇。

哪个会议的多模态大模型论文最多？

NeurIPS，2023–2026 年共 3,319 篇。