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 816 篇，第 6 / 17 页
- ICLR 2025Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
- ICLR 2025FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs
- ICLR 2025Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
- ICLR 2025Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond
- ICLR 2025Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
- ICLR 2025Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement
- ICLR 2025Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models
- ICLR 2025Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
- ICLR 2025Fine-tuning can Help Detect Pretraining Data from Large Language Models
- ICLR 2025Fine-tuning with Reserved Majority for Noise Reduction
- ICLR 2025FlashMask: Efficient and Rich Mask Extension of FlashAttention
- ICLR 2025FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
- ICLR 2025FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model
- ICLR 2025Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration
- ICLR 2025Forgetting Transformer: Softmax Attention with a Forget Gate
- ICLR 2025Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models
- ICLR 2025Fourier Sliced-Wasserstein Embedding for Multisets and Measures
- ICLR 2025Frame-Voyager: Learning to Query Frames for Video Large Language Models
- ICLR 2025Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation
- ICLR 2025Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning
- ICLR 2025FreSh: Frequency Shifting for Accelerated Neural Representation Learning
- ICLR 2025From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
- ICLR 2025From Attention to Activation: Unraveling the Enigmas of Large Language Models
- ICLR 2025From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
- ICLR 2025From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
- ICLR 2025From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
- ICLR 2025From Tokens to Words: On the Inner Lexicon of LLMs
- ICLR 2025Fundamental Limitations on Subquadratic Alternatives to Transformers
- ICLR 2025Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
- ICLR 2025G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
- ICLR 2025Gated Delta Networks: Improving Mamba2 with Delta Rule
- ICLR 2025General Scene Adaptation for Vision-and-Language Navigation
- ICLR 2025Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining Data
- ICLR 2025Generating CAD Code with Vision-Language Models for 3D Designs
- ICLR 2025Generative Monoculture in Large Language Models
- ICLR 2025GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
- ICLR 2025GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation
- ICLR 2025GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
- ICLR 2025Gramian Multimodal Representation Learning and Alignment
- ICLR 2025GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
- ICLR 2025Grounding Multimodal Large Language Model in GUI World
- ICLR 2025GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
- ICLR 2025GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
- ICLR 2025Gumbel Counterfactual Generation From Language Models
- ICLR 2025Halton Scheduler for Masked Generative Image Transformer
- ICLR 2025HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation
- ICLR 2025HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
- ICLR 2025Harnessing Diversity for Important Data Selection in Pretraining Large Language Models
- ICLR 2025Harnessing Webpage UIs for Text-Rich Visual Understanding
- ICLR 2025HeadMap: Locating and Enhancing Knowledge Circuits in LLMs
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。