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 124 / 225 页
- ICLR 2025CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
- ICLR 2025Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
- ICLR 2025Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
- ICLR 2025CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features
- ICLR 2025CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning
- ICLR 2025Cut Your Losses in Large-Vocabulary Language Models
- ICLR 2025Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection
- ICLR 2025DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
- ICLR 2025DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models
- ICLR 2025Data Pruning by Information Maximization
- ICLR 2025Data Selection via Optimal Control for Language Models
- ICLR 2025DataMan: Data Manager for Pre-training Large Language Models
- ICLR 2025DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation
- ICLR 2025Deconstructing What Makes a Good Optimizer for Autoregressive Language Models
- ICLR 2025Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs
- ICLR 2025Deep Linear Probe Generators for Weight Space Learning
- ICLR 2025DELTA: DENSE EFFICIENT LONG-RANGE 3D TRACKING FOR ANY VIDEO
- ICLR 2025Demystifying the Token Dynamics of Deep Selective State Space Models
- ICLR 2025Density estimation with LLMs: a geometric investigation of in-context learning trajectories
- ICLR 2025DEPT: Decoupled Embeddings for Pre-training Language Models
- ICLR 2025Designing Concise ConvNets with Columnar Stages
- ICLR 2025Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
- ICLR 2025Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision
- ICLR 2025Differential Transformer
- ICLR 2025Differentially Private Steering for Large Language Model Alignment
- ICLR 2025Diffusion Feedback Helps CLIP See Better
- ICLR 2025Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents
- ICLR 2025Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
- ICLR 2025Discovering Clone Negatives via Adaptive Contrastive Learning for Image-Text Matching
- ICLR 2025Discovering Influential Neuron Path in Vision Transformers
- ICLR 2025DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation
- ICLR 2025Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers
- ICLR 2025Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning
- ICLR 2025Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
- ICLR 2025Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?
- ICLR 2025Do LLMs estimate uncertainty well in instruction-following?
- ICLR 2025Do LLMs have Consistent Values?
- ICLR 2025Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?
- ICLR 2025Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under Ambiguities
- ICLR 2025Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding
- ICLR 2025Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives
- ICLR 2025DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models
- ICLR 2025Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
- ICLR 2025Does Spatial Cognition Emerge in Frontier Models?
- ICLR 2025DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
- ICLR 2025DPLM-2: A Multimodal Diffusion Protein Language Model
- ICLR 2025Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
- ICLR 2025DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models
- ICLR 2025DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
- ICLR 2025Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
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。