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 44 / 54 页
- ICLR 2025Uncovering Overfitting in Large Language Model Editing
- ICLR 2025Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
- ICLR 2025Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
- ICLR 2025Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention
- ICLR 2025Understanding Long Videos with Multimodal Language Models
- ICLR 2025Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models
- ICLR 2025Unhackable Temporal Reward for Scalable Video MLLMs
- ICLR 2025Unified Parameter-Efficient Unlearning for LLMs
- ICLR 2025UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting
- ICLR 2025UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation
- ICLR 2025UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation
- ICLR 2025Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
- ICLR 2025Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
- ICLR 2025Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
- ICLR 2025Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
- ICLR 2025Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
- ICLR 2025VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
- ICLR 2025VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning
- ICLR 2025VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models
- ICLR 2025VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation
- ICLR 2025Video Action Differencing
- ICLR 2025VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
- ICLR 2025ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
- ICLR 2025VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
- ICLR 2025Vision and Language Synergy for Rehearsal Free Continual Learning
- ICLR 2025Vision Language Models are In-Context Value Learners
- ICLR 2025Vision-LSTM: xLSTM as Generic Vision Backbone
- ICLR 2025VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
- ICLR 2025Visual Agents as Fast and Slow Thinkers
- ICLR 2025Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
- ICLR 2025Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark
- ICLR 2025Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning
- ICLR 2025VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
- ICLR 2025VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
- ICLR 2025VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
- ICLR 2025VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
- ICLR 2025VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation
- ICLR 2025VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
- ICLR 2025VLMaterial: Procedural Material Generation with Large Vision-Language Models
- ICLR 2025VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
- ICLR 2025Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned Policy
- ICLR 2025Watermark Anything With Localized Messages
- ICLR 2025Wavelet-based Positional Representation for Long Context
- ICLR 2025Wayward Concepts In Multimodal Models
- ICLR 2025Weak to Strong Generalization for Large Language Models with Multi-capabilities
- ICLR 2025Weak-to-Strong Generalization Through the Data-Centric Lens
- ICLR 2025Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors
- ICLR 2025Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation
- ICLR 2025Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
- ICLR 2025What is Wrong with Perplexity for Long-context Language Modeling?
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。