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 1,401 篇，第 5 / 29 页
- ICLR 2026Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
- ICLR 2026Contamination Detection for VLMs Using Multi‑Modal Semantic Perturbations
- ICLR 2026Content-Aware Mamba for Learned Image Compression
- ICLR 2026Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning
- ICLR 2026Context Tokens are Anchors: Understanding the Repetition Curse in Diffusion MLLMs from an Information Flow Perspective
- ICLR 2026ContextNav: Towards Agentic Multimodal In-Context Learning
- ICLR 2026Continuous Space-Time Video Super-Resolution with 3D Fourier Fields
- ICLR 2026Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate
- ICLR 2026ConvT3: Structured State Kernels for Convolutional State Space Models
- ICLR 2026CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter
- ICLR 2026CORE: Concept-Oriented Reinforcement for Bridging the Definition–Application Gap in Mathematical Reasoning
- ICLR 2026Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
- ICLR 2026CortiLife: A Unified Framework for Cortical Representation Learning across the Lifespan
- ICLR 2026COSMO-INR: Complex Sinusoidal Modulation for Implicit Neural Representations
- ICLR 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- ICLR 2026Cost-Aware Dynamic Tree Construction for Efficient Large Language Model Inference
- ICLR 2026CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
- ICLR 2026CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos
- ICLR 2026Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
- ICLR 2026CP-Agent: Context‑Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations
- ICLR 2026CPQS-Tuning: A Model Self-Perception-Based Data Filtering Algorithm for Efficient Instruction Fine-Tuning
- ICLR 2026Critic–Adviser–Reviser Cyclic Refinement: Towards High-Quality EMR Corpus Generation with LLMs
- ICLR 2026Critical attention scaling in long-context transformers
- ICLR 2026Critical Confabulation: Can LLMs Hallucinate for Social Good?
- ICLR 2026Critique-RL: Training Critiquing Language Models Through Two-Stage RL for Improved Discrimination and Constructive Feedback
- ICLR 2026Cross-Modal Redundancy and the Geometry of Vision–Language Embeddings
- ICLR 2026Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation
- ICLR 2026Ctrl-World: A Controllable Generative World Model for Robot Manipulation
- ICLR 2026Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness
- ICLR 2026CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
- ICLR 2026Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach
- ICLR 2026d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
- ICLR 2026D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
- ICLR 2026DAG-Math: Graph-Guided Mathematical Reasoning in LLMs
- ICLR 2026Data Provenance for Image Auto-Regressive Generation
- ICLR 2026Data-Centric Lessons To Improve Speech-Language Pretraining
- ICLR 2026DAVE: A VLM Vision Encoder for Document Understanding and Web Agents
- ICLR 2026DaVinci: Reinforcing Visual-Structural Syntax in MLLMs for Generalized Scientific Diagram Parsing
- ICLR 2026DeAltHDR: Learning HDR Video Reconstruction from Degraded Alternating Exposure Sequences
- ICLR 2026DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
- ICLR 2026Death of the Novel(ty): Beyond N-Gram Novelty as a Metric for Textual Creativity
- ICLR 2026DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning
- ICLR 2026Decoding Inner Speech with an End-to-End Brain-to-Text Neural Interface
- ICLR 2026Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading
- ICLR 2026Decomposed Attention Fusion in MLLMs for Training-free Video Reasoning Segmentation
- ICLR 2026Decomposition of Concept-Level Rules in Visual Scenes
- ICLR 2026Decoupling Positional and Symbolic Attention in Transformers
- ICLR 2026Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
- ICLR 2026Deep Think with Confidence
- ICLR 2026DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
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。