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 53 / 225 页
- ICLR 2026Tracing and Reversing Edits in LLMs
- ICLR 2026Train Once, Answer All: Many Pretraining Experiments for the Cost of One
- ICLR 2026Train-before-Test Harmonizes Language Model Rankings
- ICLR 2026Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
- ICLR 2026Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
- ICLR 2026Trajectory-aware Shifted State Space Models for Online Video Super-Resolution
- ICLR 2026Transducing Language Models
- ICLR 2026Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning
- ICLR 2026Transferable and Stealthy Adversarial Attacks on Large Vision-Language Models
- ICLR 2026Translation Heads: Unveiling Attention's Role in LLM Multilingual Translation
- ICLR 2026Trapped by simplicity: When Transformers fail to learn from noisy features
- ICLR 2026TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction
- ICLR 2026Tricks or Traps? A Deep Dive into RL for LLM Reasoning
- ICLR 2026TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization
- ICLR 2026TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
- ICLR 2026Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction
- ICLR 2026TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-Tuning
- ICLR 2026TSLM: Tree-Structured Language Modeling for Divergent Thinking
- ICLR 2026TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
- ICLR 2026TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
- ICLR 2026Tug-of-War No More: Harmonizing Accuracy and Robustness in Vision-Language Models via Stability-Aware Task Vector Merging
- ICLR 2026TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis
- ICLR 2026TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
- ICLR 2026Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
- ICLR 2026TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models
- ICLR 2026Type-Compliant Adaptation Cascades
- ICLR 2026U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs
- ICLR 2026U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding
- ICLR 2026UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction as Reasoning
- ICLR 2026UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models
- ICLR 2026UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
- ICLR 2026Uncertainty-Aware Gaussian Map for Vision-Language Navigation
- ICLR 2026Uncertainty-driven Embedding Convolution
- ICLR 2026Uncovering Robot Vulnerabilities through Semantic Potential Fields
- ICLR 2026Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
- ICLR 2026Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
- ICLR 2026Understanding the Implicit Biases of Design Choices for Time Series Foundation Models
- ICLR 2026Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
- ICLR 2026Understanding VLMs Spatial Mental Modeling Capability from Limited Views
- ICLR 2026Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models
- ICLR 2026Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations
- ICLR 2026Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision
- ICLR 2026Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models
- ICLR 2026UniCA: Unified Covariate Adaptation for Time Series Foundation Model
- ICLR 2026UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels
- ICLR 2026Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Diffusion Diffusion Process
- ICLR 2026Unified Vision-Language-Action Model
- ICLR 2026Unified Vision–Language Modeling via Concept Space Alignment
- ICLR 2026Unifying Diffusion and Autoregression for Generalizable Vision-Language-Action Model
- ICLR 2026UniHM: Unified Dexterous Hand Manipulation with Vision Language Model
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。