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 27 / 28 页
- NeurIPS 2026VistaQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence
- NeurIPS 2026Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
- NeurIPS 2026Visual Reinforcement Fine-Tuning via Bootstrapped Medical Reasoning
- NeurIPS 2026Visual Text Compression as Measure Transport
- NeurIPS 2026Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
- NeurIPS 2026ViT-AdaLA: Adapting Vision Transformers with Linear Attention
- NeurIPS 2026VL-DocIR: A Benchmark for Vision-Based Long Document Retrieval
- NeurIPS 2026VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
- NeurIPS 2026VLM$^3$: Vision Language Models Are Native 3D Learners
- NeurIPS 2026VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
- NeurIPS 2026VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
- NeurIPS 2026VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph
- NeurIPS 2026Voronoi-Markov chain and spatial entropy for point pattern analysis
- NeurIPS 2026Voxel as Token: A New Perspective for Zero-shot Cross-subject Vision Decoding
- NeurIPS 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
- NeurIPS 2026VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness
- NeurIPS 2026VTBench: Disentangled and Human-Aligned Evaluation for Image-Based Virtual Try-on
- NeurIPS 2026VVTRec: Radio Interferometric Reconstruction through Visual and Textual Modality Enrichment
- NeurIPS 2026Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
- NeurIPS 2026Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning
- NeurIPS 2026Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions
- NeurIPS 2026WebSpatial: A Benchmarking Framework of Spatial Intelligence via Web-based Runtime Environments
- NeurIPS 2026What DNA Foundation Models Learn Beyond Sequence Composition
- NeurIPS 2026What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective
- NeurIPS 2026What MLLMs Learn about When they Learn about Multimodal Reasoning
- NeurIPS 2026What Should a Streaming Video Model Remember?
- NeurIPS 2026What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation
- NeurIPS 2026What Stops SGD on LLM Pre-Training: The Need for Large Learning Rate and How to Achieve it
- NeurIPS 2026What to Perturb, How to Propagate: A Graph-Guided Transferable Attack on VLP Models
- NeurIPS 2026What’s Holding Back Latent Visual Reasoning?
- NeurIPS 2026When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering
- NeurIPS 2026When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA
- NeurIPS 2026When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
- NeurIPS 2026When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction
- NeurIPS 2026When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity
- NeurIPS 2026When Do Cosine Prototypes Mislead? A Whitening-Aware Benchmark for Frozen-Feature Image Classification
- NeurIPS 2026When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
- NeurIPS 2026When LLMs Know but Fail to Reason: Injecting Memory for Reasoning Enhancement
- NeurIPS 2026When Medical VLMs Stop Understanding: MedTEC-Bench for Probing Semantic Specificity
- NeurIPS 2026When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting
- NeurIPS 2026When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling
- NeurIPS 2026When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
- NeurIPS 2026When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
- NeurIPS 2026When to Inject the Target: Stage-Decoupled Guidance for Diffusion-Based Targeted Adversarial Attacks
- NeurIPS 2026When Transcriptomic Foundation Models Scale: Domain-Focused Pretraining for Drug Development in Immunology and Inflammation
- NeurIPS 2026Where Are MLLMs Looking When They Hallucinate? Mitigating Visual Hallucination via Gaze Steering
- NeurIPS 2026Where Reusable Computation Becomes Detectable: Solution-Frame Path Triage for Modular-Arithmetic Grokking
- NeurIPS 2026Where to Approximate in Neurosymbolic Inference?
- NeurIPS 2026Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video LLMs
- NeurIPS 2026Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups
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。