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 323 篇，第 1 / 7 页

1. ICML 2024A Dynamic Algorithm for Weighted Submodular Cover Problem
2. ICML 2024A Multimodal Automated Interpretability Agent
3. ICML 2024A Neural-Preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
4. ICML 2024A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions
5. ICML 2024A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
6. ICML 2024A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
7. ICML 2024A Touch, Vision, and Language Dataset for Multimodal Alignment
8. ICML 2024A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples
9. ICML 2024Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
10. ICML 2024Active Label Correction for Semantic Segmentation with Foundation Models
11. ICML 2024Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
12. ICML 2024Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
13. ICML 2024Adaptively Perturbed Mirror Descent for Learning in Games
14. ICML 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
15. ICML 2024ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data
16. ICML 2024Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models
17. ICML 2024Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models
18. ICML 2024An Embodied Generalist Agent in 3D World
19. ICML 2024An Empirical Study Into What Matters for Calibrating Vision-Language Models
20. ICML 2024An LLM Compiler for Parallel Function Calling
21. ICML 2024Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts
22. ICML 2024Analyzing $D^\alpha$ seeding for $k$-means
23. ICML 2024AND: Audio Network Dissection for Interpreting Deep Acoustic Models
24. ICML 2024Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
25. ICML 2024Arrows of Time for Large Language Models
26. ICML 2024ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations
27. ICML 2024AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
28. ICML 2024AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios
29. ICML 2024Auto-Encoding Morph-Tokens for Multimodal LLM
30. ICML 2024Autoformalizing Euclidean Geometry
31. ICML 2024Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise
32. ICML 2024Balancing Similarity and Complementarity for Federated Learning
33. ICML 2024BAT: Learning to Reason about Spatial Sounds with Large Language Models
34. ICML 2024BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
35. ICML 2024Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data
36. ICML 2024Best Arm Identification for Stochastic Rising Bandits
37. ICML 2024Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models
38. ICML 2024BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization
39. ICML 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
40. ICML 2024BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation
41. ICML 2024Borda Regret Minimization for Generalized Linear Dueling Bandits
42. ICML 2024Bridging Environments and Language with Rendering Functions and Vision-Language Models
43. ICML 2024By Tying Embeddings You Are Assuming the Distributional Hypothesis
44. ICML 2024CaM: Cache Merging for Memory-efficient LLMs Inference
45. ICML 2024Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
46. ICML 2024CARTE: Pretraining and Transfer for Tabular Learning
47. ICML 2024Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
48. ICML 2024Case-Based or Rule-Based: How Do Transformers Do the Math?
49. ICML 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
50. ICML 2024CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks

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。