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 2,676 篇，第 4 / 54 页
- ICLR 2026Cascadia: An Efficient Cascade Serving System for Large Language Models
- ICLR 2026Cat-PO: Cross-modal Adaptive Token-rewards for Preference Optimization in Truthful Multimodal LLMs
- ICLR 2026Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
- ICLR 2026CaTs and DAGs: Integrating Directed Acyclic Graphs with Transformers for Causally Constrained Predictions
- ICLR 2026CaTS: Calibrated Test-Time Scaling for Efficient LLM Reasoning
- ICLR 2026Causality ≠ Invariance: Function and Concept Vectors in LLMs
- ICLR 2026Cautious Optimizers: Improving Training with One Line of Code
- ICLR 2026CellDuality: Unlocking Biological Reasoning in LLMs with Self-Supervised RLVR
- ICLR 2026CerebraGloss: Instruction-Tuning a Large Vision-Language Model for Fine-Grained Clinical EEG Interpretation
- ICLR 2026ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations
- ICLR 2026Channel-Aware Mixed-Precision Quantization for Efficient Long-Context Inference
- ICLR 2026Chart Deep Research in LVLMs via Parallel Relative Policy Optimization
- ICLR 2026ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
- ICLR 2026ChemEval: A Multi-level and Fine-grained Chemical Capability Evaluation for Large Language Models
- ICLR 2026Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
- ICLR 2026ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World Simulation
- ICLR 2026CIMemories: A Compositional Benchmark For Contextual Integrity In LLMs
- ICLR 2026CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing
- ICLR 2026CitySeeker: How Do VLMs Explore Embodied Urban Navigation with Implicit Human Needs?
- ICLR 2026CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk
- ICLR 2026CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally
- ICLR 2026CLIP-FMoE: Scalable CLIP via Fused Mixture-of-Experts with Enforced Specialization
- ICLR 2026Closing the Gap Between Text and Speech Understanding in LLMs
- ICLR 2026Closing the Modality Gap Aligns Group-Wise Semantics
- ICLR 2026CLUE: Conflict-guided Localization for LLM Unlearning Framework
- ICLR 2026Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models
- ICLR 2026CodeBrain: Towards Decoupled Interpretability and Multi-Scale Architecture for EEG Foundation Model
- ICLR 2026CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts
- ICLR 2026Codified Finite-state Machines for Role-playing
- ICLR 2026CoFact: Conformal Factuality Guarantees for Language Models under Distribution Shift
- ICLR 2026CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
- ICLR 2026CogMoE: Signal-Quality–Guided Multimodal MoE for Cognitive Load Prediction
- ICLR 2026COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
- ICLR 2026CoMem: Compositional Concept-Graph Memory for Vision–Language Adaptation
- ICLR 2026COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning
- ICLR 2026Comparing the learning dynamics of in-context learning and fine-tuning in language models
- ICLR 2026CompassNav: Steering From Path Imitation to Decision Understanding In Navigation
- ICLR 2026CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
- ICLR 2026Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
- ICLR 2026Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
- ICLR 2026Composer: A Search Framework for Hybrid Neural Architecture Design
- ICLR 2026Compositional-ARC: Assessing Systematic Generalization in Abstract Spatial Reasoning
- ICLR 2026Compute-Optimal Quantization-Aware Training
- ICLR 2026CoNavBench: Collaborative Long-Horizon Vision-Language Navigation Benchmark
- ICLR 2026CONCUR: A Framework for Continual Constrained and Unconstrained Routing
- ICLR 2026Conditioned Initialization for Attention
- ICLR 2026Conformal Prediction for Long-Tailed Classification
- ICLR 2026Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
- ICLR 2026Constantly Improving Image Models Need Constantly Improving Benchmarks
- ICLR 2026Constitutional Classifiers++: Production-Grade Defenses against Universal Jailbreaks
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。