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 3,319 篇，第 47 / 67 页
- NeurIPS 2025Towards Fully FP8 GEMM LLM Training at Scale
- NeurIPS 2025Towards General Continuous Memory for Vision-Language Models
- NeurIPS 2025Towards Generalizable Detector for Generated Image
- NeurIPS 2025Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era
- NeurIPS 2025Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
- NeurIPS 2025Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study
- NeurIPS 2025Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation
- NeurIPS 2025Towards Robust Uncertainty Calibration for Composed Image Retrieval
- NeurIPS 2025Towards Self-Refinement of Vision-Language Models with Triangular Consistency
- NeurIPS 2025Towards Understanding Camera Motions in Any Video
- NeurIPS 2025Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization
- NeurIPS 2025ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
- NeurIPS 2025TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making
- NeurIPS 2025TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval
- NeurIPS 2025Track3R: Joint Point Map and Trajectory Prior for Spatiotemporal 3D Understanding
- NeurIPS 2025Training-free Online Video Step Grounding
- NeurIPS 2025Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models
- NeurIPS 2025Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties
- NeurIPS 2025Transferring Linear Features Across Language Models With Model Stitching
- NeurIPS 2025Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection
- NeurIPS 2025Transition Matching: Scalable and Flexible Generative Modeling
- NeurIPS 2025TRAP: Targeted Redirecting of Agentic Preferences
- NeurIPS 2025Tri-MARF: A Tri-Modal Multi-Agent Responsive Framework for Comprehensive 3D Object Annotation
- NeurIPS 2025TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence
- NeurIPS 2025Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
- NeurIPS 2025TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
- NeurIPS 2025Truthful Aggregation of LLMs with an Application to Online Advertising
- NeurIPS 2025Two Causally Related Needles in a Video Haystack
- NeurIPS 2025Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
- NeurIPS 2025UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning
- NeurIPS 2025UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
- NeurIPS 2025UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation
- NeurIPS 2025un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
- NeurIPS 2025Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
- NeurIPS 2025Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Video Temporal Grounding
- NeurIPS 2025Understanding and Rectifying Safety Perception Distortion in VLMs
- NeurIPS 2025Understanding the Gain from Data Filtering in Multimodal Contrastive Learning
- NeurIPS 2025Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition
- NeurIPS 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
- NeurIPS 2025Unified Reinforcement and Imitation Learning for Vision-Language Models
- NeurIPS 2025Unified Transferability Metrics for Time Series Foundation Models
- NeurIPS 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
- NeurIPS 2025UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback
- NeurIPS 2025UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning
- NeurIPS 2025UniTok: a Unified Tokenizer for Visual Generation and Understanding
- NeurIPS 2025UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
- NeurIPS 2025Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
- NeurIPS 2025Universal Visuo-Tactile Video Understanding for Embodied Interaction
- NeurIPS 2025UniViT: Unifying Image and Video Understanding in One Vision Encoder
- NeurIPS 2025Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs
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。