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 1,051 篇，第 19 / 22 页
- ICML 2026Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
- ICML 2026Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
- ICML 2026Thinking in Latent Space: Progressive Multimodal Simplification for Visual Reasoning
- ICML 2026Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning
- ICML 2026Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces
- ICML 2026Thinking with Geometry: Active Geometry Integration for Spatial Reasoning
- ICML 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
- ICML 2026Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
- ICML 2026Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces
- ICML 2026TIME: Tensor-Factorized Mixture-of-Experts with Intrinsic Routing for Lifelong Multimodal Knowledge Editing
- ICML 2026TimeOmni-VL: Unified Models for Time Series Understanding and Generation
- ICML 2026TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts
- ICML 2026ToaSt: Token Channel Selection and Structured Pruning for Efficient ViT
- ICML 2026Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning
- ICML 2026TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
- ICML 2026TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering
- ICML 2026Topological Active Inference for Task Disambiguation
- ICML 2026Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach
- ICML 2026Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages
- ICML 2026Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts
- ICML 2026Towards Diffeomorphism-Equivariant Neural Networks via Canonicalization
- ICML 2026Towards Efficient LLMs Annealing with Principled Sample Selection
- ICML 2026Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
- ICML 2026Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs
- ICML 2026Towards Multimodal Large Language Models with Both Training and Inference Efficiency
- ICML 2026Towards One-to-Many Temporal Grounding
- ICML 2026Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
- ICML 2026Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines
- ICML 2026Towards Solving the Gilbert-Pollak Conjecture via Large Language Models
- ICML 2026Towards Trustworthy Video Anomaly Understanding: A Class-Guided Chain-of-Evaluation Metric and An Anomaly-focused Meta-Benchmark
- ICML 2026Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
- ICML 2026Towards Uniformity and Alignment for Multimodal Representation Learning
- ICML 2026TRACER: Persistent Regularization for Robust Multimodal Finetuning
- ICML 2026Training Data Efficiency in Multimodal Process Reward Models
- ICML 2026Training-Free Multimodal Large Language Model Orchestration
- ICML 2026Training–Inference Consistent Segmented Execution for Long-Context LLMs
- ICML 2026Transform Trained Transformer for Accelerating Native 4K Video Generation
- ICML 2026Transitive Representation Learning Enhances Histopathology Annotation
- ICML 2026Transport and Merge: Cross-Architecture Merging for Large Language Models
- ICML 2026TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection
- ICML 2026TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
- ICML 2026TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution
- ICML 2026TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
- ICML 2026Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal Fusion
- ICML 2026TrustworthyQENN: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern Classification
- ICML 2026TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
- ICML 2026Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
- ICML 2026TVDRNet: Text-driven Viewpoint Optimization via Differentiable Rendering for 3D Reasoning Segmentation
- ICML 2026TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
- ICML 2026TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins
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。