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 1,051 篇，第 17 / 22 页
- ICML 2026SLASH the Sink: Sharpening Structural Attention Inside LLMs
- ICML 2026SleepLM: Natural-Language Intelligence for Human Sleep
- ICML 2026SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
- ICML 2026SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
- ICML 2026SLIM: Secure and Efficient Inference for Large Language Models on Untrusted Devices via TEEs
- ICML 2026SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection
- ICML 2026SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs
- ICML 2026Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
- ICML 2026SMD: Multi-view Safety-Critical Driving Video Generation in the Real-world Domain
- ICML 2026SMM Transformer: Leveraging Spiking Neural Networks for Multimodal Tasks
- ICML 2026Smoothing Slot Attention Iterations and Recurrences
- ICML 2026SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs
- ICML 2026SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval
- ICML 2026SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
- ICML 2026SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis
- ICML 2026SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
- ICML 2026SpanNorm: Reconciling Training Stability and Performance in Deep Transformers
- ICML 2026SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
- ICML 2026SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
- ICML 2026Sparser Block-Sparse Attention via Token Permutation
- ICML 2026Sparser, Faster, Lighter Transformer Language Models
- ICML 2026SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes
- ICML 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
- ICML 2026Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers
- ICML 2026SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
- ICML 2026Spatio-Temporal LLM: Reasoning about Environments and Actions
- ICML 2026SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models
- ICML 2026SpecPL: Disentangling Spectral Granularity for Prompt Learning
- ICML 2026SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
- ICML 2026Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy
- ICML 2026Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models
- ICML 2026Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
- ICML 2026Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning
- ICML 2026SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
- ICML 2026Spherical SO(3) Equivariant Local Attention
- ICML 2026Spiked-CFR: Causal Representation Learning from LLMs via Wasserstein Projection Pursuit
- ICML 2026SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks
- ICML 2026SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
- ICML 2026SPLIT-VLM: Salience-Guided Partitioning towards Local Coverage for Importance-Aware Token Dropping in Vision-Language Models
- ICML 2026SPR: A Structured Prompt Refinement Network for Modality Missing
- ICML 2026SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
- ICML 2026SSDCN: Spatial-Spectral Dual-Clustering-based Network for Hyperspectral Image Super-resolution
- ICML 2026SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
- ICML 2026ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding
- ICML 2026Stabilizing Native Low-Rank LLM Pretraining
- ICML 2026Stable Spectral Copula Alignment for Robust Multimodal Learning
- ICML 2026StableI2I: Spotting Unintended Changes in Image-to-Image Transition
- ICML 2026StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
- ICML 2026STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
- ICML 2026Statistically Calibrated Scaling for Token Merging in Transformers
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。