多模态大模型论文趋势 2023–2026
视觉语言模型、图像/视频理解与生成式多模态基础模型
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 11,209 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 433 | 138 | 146 | 509 | 1,226 |
| 2024 | 446 | 321 | 323 | 626 | 1,716 |
| 2025 | 1,074 | 816 | 390 | 795 | 3,075 |
| 2026 | 1,366 | 1,401 | 1,051 | 1,374 | 5,192 |
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 1,910 篇，第 34 / 39 页
- ICML 2024Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
- ICML 2024PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming
- ICML 2024PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR
- ICML 2024PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
- ICML 2024Position: A Call for Embodied AI
- ICML 2024Position: Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?
- ICML 2024Position: Do pretrained Transformers Learn In-Context by Gradient Descent?
- ICML 2024Position: Embracing Negative Results in Machine Learning
- ICML 2024Position: Foundation Agents as the Paradigm Shift for Decision Making
- ICML 2024Position: Levels of AGI for Operationalizing Progress on the Path to AGI
- ICML 2024Position: LLMs Can’t Plan, But Can Help Planning in LLM-Modulo Frameworks
- ICML 2024Position: Standardization of Behavioral Use Clauses is Necessary for the Adoption of Responsible Licensing of AI
- ICML 2024Position: Stop Making Unscientific AGI Performance Claims
- ICML 2024Position: Technical Research and Talent is Needed for Effective AI Governance
- ICML 2024Position: Tensor Networks are a Valuable Asset for Green AI
- ICML 2024Position: The Reasonable Person Standard for AI
- ICML 2024Position: Towards Implicit Prompt For Text-To-Image Models
- ICML 2024Position: TrustLLM: Trustworthiness in Large Language Models
- ICML 2024Position: Understanding LLMs Requires More Than Statistical Generalization
- ICML 2024Position: What makes an image realistic?
- ICML 2024Positive Concave Deep Equilibrium Models
- ICML 2024Post-hoc Part-Prototype Networks
- ICML 2024Practical Performance Guarantees for Pipelined DNN Inference
- ICML 2024PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
- ICML 2024Predicting Lagrangian Multipliers for Mixed Integer Linear Programs
- ICML 2024Predictive Dynamic Fusion
- ICML 2024Premise Order Matters in Reasoning with Large Language Models
- ICML 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
- ICML 2024Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
- ICML 2024Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
- ICML 2024Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
- ICML 2024Prompt-based Visual Alignment for Zero-shot Policy Transfer
- ICML 2024Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
- ICML 2024QuRating: Selecting High-Quality Data for Training Language Models
- ICML 2024Random features models: a way to study the success of naive imputation
- ICML 2024Randomized Confidence Bounds for Stochastic Partial Monitoring
- ICML 2024Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
- ICML 2024Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion
- ICML 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractions
- ICML 2024Relaxing the Accurate Imputation Assumption in Doubly Robust Learning for Debiased Collaborative Filtering
- ICML 2024ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate
- ICML 2024ReLUs Are Sufficient for Learning Implicit Neural Representations
- ICML 2024REMEDI: Corrective Transformations for Improved Neural Entropy Estimation
- ICML 2024Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration
- ICML 2024Rethinking Optimization and Architecture for Tiny Language Models
- ICML 2024Retrieval Across Any Domains via Large-scale Pre-trained Model
- ICML 2024Revealing Vision-Language Integration in the Brain with Multimodal Networks
- ICML 2024Revisiting Context Aggregation for Image Matting
- ICML 2024Revisiting the Role of Language Priors in Vision-Language Models
- ICML 2024RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查多模态大模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "multimodal-llms"}
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。