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 11,207 篇，第 183 / 225 页
- ICLR 2024On the Variance of Neural Network Training with respect to Test Sets and Distributions
- ICLR 2024Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
- ICLR 2024OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
- ICLR 2024Out-of-Variable Generalisation for Discriminative Models
- ICLR 2024Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
- ICLR 2024OWL: A Large Language Model for IT Operations
- ICLR 2024PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
- ICLR 2024PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
- ICLR 2024Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models
- ICLR 2024PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
- ICLR 2024PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- ICLR 2024PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning
- ICLR 2024PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
- ICLR 2024Pre-training with Random Orthogonal Projection Image Modeling
- ICLR 2024Progressive Fourier Neural Representation for Sequential Video Compilation
- ICLR 2024Prompt Gradient Projection for Continual Learning
- ICLR 2024Prompt Learning with Quaternion Networks
- ICLR 2024Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction
- ICLR 2024Pseudo-Generalized Dynamic View Synthesis from a Video
- ICLR 2024Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision
- ICLR 2024QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
- ICLR 2024Quasi-Monte Carlo for 3D Sliced Wasserstein
- ICLR 2024Raidar: geneRative AI Detection viA Rewriting
- ICLR 2024Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- ICLR 2024RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
- ICLR 2024Recursive Generalization Transformer for Image Super-Resolution
- ICLR 2024ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
- ICLR 2024Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
- ICLR 2024Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
- ICLR 2024Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
- ICLR 2024Rethinking Model Ensemble in Transfer-based Adversarial Attacks
- ICLR 2024Retrieval-Enhanced Contrastive Vision-Text Models
- ICLR 2024Rotation Has Two Sides: Evaluating Data Augmentation for Deep One-class Classification
- ICLR 2024SALMONN: Towards Generic Hearing Abilities for Large Language Models
- ICLR 2024Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing
- ICLR 2024Scaling Laws for Sparsely-Connected Foundation Models
- ICLR 2024SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
- ICLR 2024SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
- ICLR 2024Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective
- ICLR 2024Sentence-level Prompts Benefit Composed Image Retrieval
- ICLR 2024Shadow Cones: A Generalized Framework for Partial Order Embeddings
- ICLR 2024Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
- ICLR 2024Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation
- ICLR 2024Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
- ICLR 2024Skip-Attention: Improving Vision Transformers by Paying Less Attention
- ICLR 2024SLiMe: Segment Like Me
- ICLR 2024Soft Contrastive Learning for Time Series
- ICLR 2024SPDER: Semiperiodic Damping-Enabled Object Representation
- ICLR 2024SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models
- ICLR 2024SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
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。