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 48 / 225 页
- ICLR 2026Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
- ICLR 2026Rethinking Causal Mask Attention for Vision-Language Inference
- ICLR 2026Rethinking Code Similarity for Automated Algorithm Design with LLMs
- ICLR 2026Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
- ICLR 2026Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration
- ICLR 2026Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
- ICLR 2026Rethinking LLM Evaluation: Can We Evaluate LLMs with 200× Less Data?
- ICLR 2026Rethinking LLM Reasoning: From Explicit Trajectories to Latent Representations
- ICLR 2026Rethinking Radiology Report Generation: From Narrative Flow to Topic-Guided Findings
- ICLR 2026Rethinking Residual Errors in Compensation-based LLM Quantization
- ICLR 2026Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
- ICLR 2026Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
- ICLR 2026Reverse-Engineered Reasoning for Open-Ended Generation
- ICLR 2026Reversible Primitive–Composition Alignment for Continual Vision–Language Learning
- ICLR 2026Revisiting Confidence Calibration for Misclassification Detection in VLMs
- ICLR 2026Revisiting Multimodal Positional Encoding in Vision–Language Models
- ICLR 2026Revisiting the Past: Data Unlearning with Model State History
- ICLR 2026Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning
- ICLR 2026ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis
- ICLR 2026RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
- ICLR 2026Riemannian High-Order Pooling for Brain Foundation Models
- ICLR 2026RIVER: Real-time Video Interaction Benchmark
- ICLR 2026RL for Reasoning by Adaptively Revealing Rationales
- ICLR 2026RL makes MLLMs see better than SFT
- ICLR 2026RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
- ICLR 2026RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
- ICLR 2026RLAP-CLIP: Continual Multimodal Learning with Prototype Adaptation and Difficulty-Aware Routing
- ICLR 2026RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
- ICLR 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
- ICLR 2026RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
- ICLR 2026RobotArena $\infty$: Unlimited Robot Benchmarking via Real-to-Sim Translation
- ICLR 2026Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
- ICLR 2026Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging
- ICLR 2026Robust Reward Modeling via Causal Rubrics
- ICLR 2026Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts
- ICLR 2026RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
- ICLR 2026RoRE: Rotary Ray Embedding for Generalised Multi-Modal Scene Understanding
- ICLR 2026Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
- ICLR 2026Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
- ICLR 2026Routing, Cascades, and User Choice for LLMs
- ICLR 2026ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
- ICLR 2026RPM: Reasoning-Level Personalization for Black-Box Large Language Models
- ICLR 2026SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
- ICLR 2026SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression
- ICLR 2026Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
- ICLR 2026SafeMoE: Safe Fine-Tuning for MoE LLMs by Aligning Harmful Input Routing
- ICLR 2026Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
- ICLR 2026SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
- ICLR 2026SAM 3: Segment Anything with Concepts
- ICLR 2026Same Content, Different Representations: A Controlled Study for Table QA
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。