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 321 篇，第 1 / 7 页

1. ICLR 2024#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
2. ICLR 2024$\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning
3. ICLR 20243D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
4. ICLR 2024A Benchmark for Learning to Translate a New Language from One Grammar Book
5. ICLR 2024A Foundation Model for Error Correction Codes
6. ICLR 2024A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
7. ICLR 2024A Semantic Invariant Robust Watermark for Large Language Models
8. ICLR 2024A Simple and Effective Pruning Approach for Large Language Models
9. ICLR 2024A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis
10. ICLR 2024A unique M-pattern for micro-expression spotting in long videos
11. ICLR 2024Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
12. ICLR 2024Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
13. ICLR 2024Adaptive Window Pruning for Efficient Local Motion Deblurring
14. ICLR 2024Adversarial AutoMixup
15. ICLR 2024AffineQuant: Affine Transformation Quantization for Large Language Models
16. ICLR 2024AlpaGasus: Training a Better Alpaca with Fewer Data
17. ICLR 2024Alt-Text with Context: Improving Accessibility for Images on Twitter
18. ICLR 2024An Extensible Framework for Open Heterogeneous Collaborative Perception
19. ICLR 2024An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
20. ICLR 2024An interpretable error correction method for enhancing code-to-code translation
21. ICLR 2024An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
22. ICLR 2024An Unforgeable Publicly Verifiable Watermark for Large Language Models
23. ICLR 2024Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
24. ICLR 2024AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
25. ICLR 2024AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
26. ICLR 2024ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference
27. ICLR 2024At Which Training Stage Does Code Data Help LLMs Reasoning?
28. ICLR 2024BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation
29. ICLR 2024Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
30. ICLR 2024Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
31. ICLR 2024Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
32. ICLR 2024Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
33. ICLR 2024BooookScore: A systematic exploration of book-length summarization in the era of LLMs
34. ICLR 2024Boosting Vanilla Lightweight Vision Transformers via Re-parameterization
35. ICLR 2024Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification
36. ICLR 2024Boundary Denoising for Video Activity Localization
37. ICLR 2024BrainLM: A foundation model for brain activity recordings
38. ICLR 2024BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity
39. ICLR 2024Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
40. ICLR 2024Bridging Vision and Language Spaces with Assignment Prediction
41. ICLR 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
42. ICLR 2024CABINET: Content Relevance-based Noise Reduction for Table Question Answering
43. ICLR 2024CAMBranch: Contrastive Learning with Augmented MILPs for Branching
44. ICLR 2024Can Large Language Models Infer Causation from Correlation?
45. ICLR 2024Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
46. ICLR 2024Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
47. ICLR 2024Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
48. ICLR 2024Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision?
49. ICLR 2024Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
50. ICLR 2024Causal-StoNet: Causal Inference for High-Dimensional Complex Data

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。