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 1,366 篇，第 16 / 28 页
- NeurIPS 2026Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?
- NeurIPS 2026MIRROR: Manifold Ideal Reference ReconstructOR for AI-Generated Image Detection
- NeurIPS 2026Mission Impossible: Diagnosing and Fixing Non-Operative Instruction Following in Image Editing
- NeurIPS 2026Mitigating Asymmetric Boundary Encroachment in Continual Learning of Vision-Language Models
- NeurIPS 2026MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception
- NeurIPS 2026MixForensics: Blend Before You Encode for Generalizable AI-Generated Video Detection
- NeurIPS 2026MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing
- NeurIPS 2026Mixture of Layers: Dynamic Layer Routing for Visual Reasoning
- NeurIPS 2026Mixture of Probes: Learning with Privileged Modalities in Multimodal LLMs Through Probing
- NeurIPS 2026Mixture-of-Hierarchical Experts: Optimized Mamba Architecture for Vision Diffusion
- NeurIPS 2026ML-assisted Randomization Tests for A/B Experiments
- NeurIPS 2026MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
- NeurIPS 2026MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs
- NeurIPS 2026MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling
- NeurIPS 2026MM-SCALE: Evaluating Evidence-Grounded Moral Judgment in Vision-Language Models
- NeurIPS 2026MMA-SafetyBench: A Benchmark for Multimodal Agent Safety Evaluation
- NeurIPS 2026MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
- NeurIPS 2026mmLIP: mmWave Radar-Language Interactive Pretraining via Point Confidence
- NeurIPS 2026MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
- NeurIPS 2026Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models
- NeurIPS 2026Model Distribution-Aware Multimodal Dataset Distillation
- NeurIPS 2026ModelLens: Finding the Best for Your Task from Myriads of Models
- NeurIPS 2026MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs
- NeurIPS 2026MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
- NeurIPS 2026More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
- NeurIPS 2026MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning
- NeurIPS 2026MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays
- NeurIPS 2026MOSAIC: Concept Bottlenecks via Text-Anchored Optimal Transport
- NeurIPS 2026Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation
- NeurIPS 2026MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening
- NeurIPS 2026MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning
- NeurIPS 2026MSAlign: Aligning Molecular and Mass Spectra Foundation Models for Metabolite Identification
- NeurIPS 2026MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
- NeurIPS 2026Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment
- NeurIPS 2026Multimodal Context-Aware Human Motion Generation with Language, Vision, and Object
- NeurIPS 2026Multimodal Foundation Agents Should Use Brain Data as Privileged Supervision
- NeurIPS 2026Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity
- NeurIPS 2026MultiSTEVE-1s: A Model Zoo and Interpretability Suite for Instruction-Following Vision Agents
- NeurIPS 2026MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
- NeurIPS 2026Muon Does Not Converge on Convex Lipschitz Functions
- NeurIPS 2026MUST: Stage-Adaptive Stability Control for Test-Time Scaling in Multimodal Reasoning
- NeurIPS 2026MUX: Continuous Reasoning via Multiplexed Tokens
- NeurIPS 2026NavOCR: A Dataset Generator for Navigation-Relevant Text Detection in Mobile Robots
- NeurIPS 2026Nearly Optimal Attention Coresets
- NeurIPS 2026Nearly Optimal Bounds for Orthogonal Trace-Sum Maximization
- NeurIPS 2026Necessary but Not Sufficient: Spectral Tests for Value-Linear Attention Surrogates
- NeurIPS 2026NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Model
- NeurIPS 2026Neural Bayesian Filtering
- NeurIPS 2026Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP
- NeurIPS 2026Neural Expansion: A Unified Mechanism for How Deep Neural Network Generalize
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。