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 1,226 篇，第 20 / 25 页
- NeurIPS 2023From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader
- NeurIPS 2023Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
- NeurIPS 2023Generating Images with Multimodal Language Models
- NeurIPS 2023Generator Identification for Linear SDEs with Additive and Multiplicative Noise
- NeurIPS 2023GenEval: An object-focused framework for evaluating text-to-image alignment
- NeurIPS 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image
- NeurIPS 2023GEO-Bench: Toward Foundation Models for Earth Monitoring
- NeurIPS 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
- NeurIPS 2023Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
- NeurIPS 2023GEX: A flexible method for approximating influence via Geometric Ensemble
- NeurIPS 2023Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
- NeurIPS 2023Global Structure-Aware Diffusion Process for Low-light Image Enhancement
- NeurIPS 2023Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data
- NeurIPS 2023Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
- NeurIPS 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction
- NeurIPS 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Models
- NeurIPS 2023GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph
- NeurIPS 2023Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing
- NeurIPS 2023Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents
- NeurIPS 2023Guide Your Agent with Adaptive Multimodal Rewards
- NeurIPS 2023Guiding Large Language Models via Directional Stimulus Prompting
- NeurIPS 2023H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
- NeurIPS 2023HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding
- NeurIPS 2023Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition
- NeurIPS 2023HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
- NeurIPS 2023Hardware Resilience Properties of Text-Guided Image Classifiers
- NeurIPS 2023Hierarchical Integration Diffusion Model for Realistic Image Deblurring
- NeurIPS 2023HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count
- NeurIPS 2023Holistic Evaluation of Text-to-Image Models
- NeurIPS 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
- NeurIPS 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
- NeurIPS 2023IEBins: Iterative Elastic Bins for Monocular Depth Estimation
- NeurIPS 2023Im-Promptu: In-Context Composition from Image Prompts
- NeurIPS 2023Image Captioners Are Scalable Vision Learners Too
- NeurIPS 2023ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
- NeurIPS 2023Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
- NeurIPS 2023Improving CLIP Training with Language Rewrites
- NeurIPS 2023Improving multimodal datasets with image captioning
- NeurIPS 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biases
- NeurIPS 2023Incomplete Multimodality-Diffused Emotion Recognition
- NeurIPS 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
- NeurIPS 2023Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization
- NeurIPS 2023INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis
- NeurIPS 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
- NeurIPS 2023Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes
- NeurIPS 2023Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile
- NeurIPS 2023Into the LAION’s Den: Investigating Hate in Multimodal Datasets
- NeurIPS 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- NeurIPS 2023Joint processing of linguistic properties in brains and language models
- NeurIPS 2023Joint Prompt Optimization of Stacked LLMs using Variational Inference
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。