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 14 / 28 页
- NeurIPS 2026Latent Spatial Reasoning: Building Innate 3D Awareness via Latent-Space Distillation
- NeurIPS 2026Latent-Lens: Visual Perception in Small Language Models Through Latent Communication
- NeurIPS 2026LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
- NeurIPS 2026Lattice Deduction Transformers
- NeurIPS 2026Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks
- NeurIPS 2026Leak-CURBER: A Leakage-Controlled Multimodal Evaluation Benchmark for Enzymatic Reaction Tasks
- NeurIPS 2026LEAP: Library-driven Evolutionary Abstraction Paradigm for Large Language Models
- NeurIPS 2026Learning Actionable Information Landscapes for Multimodal Active Sensing in Hawkmoths
- NeurIPS 2026Learning Agentic World Vision-Language-Action Models for Autonomous Driving
- NeurIPS 2026Learning Fine-Grained Vision-Language Alignment from Discriminative Part Descriptions
- NeurIPS 2026Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
- NeurIPS 2026Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers
- NeurIPS 2026Learning How to Cube
- NeurIPS 2026Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation
- NeurIPS 2026Learning Semantic Consistency for Open-Vocabulary Dense Perception
- NeurIPS 2026Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval
- NeurIPS 2026Learning to Ask: Metacognitive Action Policy for Large and Small Language Model Collaboration
- NeurIPS 2026Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs
- NeurIPS 2026Learning to Learn from Multimodal Experience
- NeurIPS 2026Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing
- NeurIPS 2026Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning
- NeurIPS 2026Learning Where and What to Restore for Composite Image Restoration
- NeurIPS 2026Learning with Enumeration: Neural-Guided SAT Framework for Cryptographic Key Recovery
- NeurIPS 2026Ledger: A Path-Validated, Database-Grounded Benchmark for Enterprise Web Agents
- NeurIPS 2026LEGO: Sizing Rules for Budget-Aware Dense-to-MoE Conversion of Vision-Language Models
- NeurIPS 2026LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
- NeurIPS 2026Less Language, More Latents: Annotation-Efficient VLAs for Driving
- NeurIPS 2026LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
- NeurIPS 2026Leveraging Latent Visual Reasoning in Silence
- NeurIPS 2026Leveraging unlabelled data for generalizable neural population decoding
- NeurIPS 2026Liars' Bench: Evaluating Lie Detectors for Language Models
- NeurIPS 2026LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding
- NeurIPS 2026LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
- NeurIPS 2026LiFT: Likelihood-Free Tree-Structured Policy Optimization for Flow-Based VLAs
- NeurIPS 2026Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents
- NeurIPS 2026Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval
- NeurIPS 2026LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation
- NeurIPS 2026LLM-AutoSciLab: Closed-Loop Scientific Law Discovery via Active Experimentation with LLMs
- NeurIPS 2026LLMs Keep Thinking When Told Not To
- NeurIPS 2026LLMs Optimizing LLMs: Automated MegaKernel Generation for Inference Acceleration
- NeurIPS 2026Locating and Repairing Domain Shift in VLM Trajectory Planning
- NeurIPS 2026Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space
- NeurIPS 2026LogT: Logically Think with Images for Visual Search
- NeurIPS 2026LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
- NeurIPS 2026Long-term Embodied Visual Tracking with Lightweight Vision-Language-Action Models
- NeurIPS 2026LongSCOP: Semantically Consistent Long Video Outpainting
- NeurIPS 2026Look Before You Leap: Self-Evolving Clinical Reasoning with Psychometric Preference Optimization for Radiology Report Generation
- NeurIPS 2026Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
- NeurIPS 2026Lookalike3D: Seeing Double in 3D
- NeurIPS 2026LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
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。