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 816 篇，第 10 / 17 页
- ICLR 2025MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
- ICLR 2025MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
- ICLR 2025MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
- ICLR 2025MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
- ICLR 2025MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions
- ICLR 2025MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation
- ICLR 2025MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents
- ICLR 2025MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines
- ICLR 2025Modality-Specialized Synergizers for Interleaved Vision-Language Generalists
- ICLR 2025MoDeGPT: Modular Decomposition for Large Language Model Compression
- ICLR 2025Model Equality Testing: Which Model is this API Serving?
- ICLR 2025Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning
- ICLR 2025Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions
- ICLR 2025Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
- ICLR 2025Morphing Tokens Draw Strong Masked Image Models
- ICLR 2025Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs
- ICLR 2025MotionClone: Training-Free Motion Cloning for Controllable Video Generation
- ICLR 2025mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
- ICLR 2025MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation
- ICLR 2025MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models
- ICLR 2025Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM
- ICLR 2025MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
- ICLR 2025Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits
- ICLR 2025Multi-Label Test-Time Adaptation with Bound Entropy Minimization
- ICLR 2025Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
- ICLR 2025Multi-modal brain encoding models for multi-modal stimuli
- ICLR 2025Multi-Reward as Condition for Instruction-based Image Editing
- ICLR 2025Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
- ICLR 2025Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning
- ICLR 2025Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine
- ICLR 2025Multimodal Quantitative Language for Generative Recommendation
- ICLR 2025Multimodal Situational Safety
- ICLR 2025Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap
- ICLR 2025Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning
- ICLR 2025MuPT: A Generative Symbolic Music Pretrained Transformer
- ICLR 2025Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning
- ICLR 2025Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solver
- ICLR 2025Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
- ICLR 2025Natural Language Inference Improves Compositionality in Vision-Language Models
- ICLR 2025NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics
- ICLR 2025Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
- ICLR 2025Near, far: Patch-ordering enhances vision foundation models' scene understanding
- ICLR 2025Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
- ICLR 2025Needle Threading: Can LLMs Follow Threads Through Near-Million-Scale Haystacks?
- ICLR 2025NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields
- ICLR 2025NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains
- ICLR 2025Neural Multi-Objective Combinatorial Optimization via Graph-Image Multimodal Fusion
- ICLR 2025Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning
- ICLR 2025Neural Wave Equation for Irregularly Sampled Sequence Data
- ICLR 2025Neuron based Personality Trait Induction in Large Language Models
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。