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 1,372 篇，第 24 / 28 页
- CVPR 2026The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations
- CVPR 2026TherA Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation
- CVPR 2026Think 360deg Beyond Depth Evaluating the Width-centric Reasoning Capability of
- CVPR 2026Think Visually Reason Textually Vision-Language Synergy in Abstract Reasoning
- CVPR 2026Think with 3D Geometric Imagination Grounded Spatial Reasoning from Limited
- CVPR 2026Think-as-You-See Streaming Chain-of-Thought Reasoning for Large Vision-Language Models
- CVPR 2026Thinking Diffusion Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal
- CVPR 2026Thinking with Drafts Speculative Temporal Reasoning for Efficient Long Video
- CVPR 2026Thinking with Programming Vision Towards a Unified View for Thinking
- CVPR 2026Thinking with Video Video Generation as a Promising Multimodal Reasoning
- CVPR 2026ThinkingViT Matryoshka Thinking Vision Transformer for Elastic Inference
- CVPR 2026TIM Temporal Decoupling with Iterative Mutual-Refinement Model for Longitudinal Radiology
- CVPR 2026Time Blindness Why Video-Language Models Cant See What Humans Can
- CVPR 2026Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution
- CVPR 2026Time-Specialized Event-Image Alignment for Blur-to-Video Decomposition
- CVPR 2026TimeLens Rethinking Video Temporal Grounding with Multimodal LLMs
- CVPR 2026TimeViper A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video
- CVPR 2026TIPSv2 Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
- CVPR 2026TiViBench Benchmarking Think-in-Video Reasoning for Video Generation
- CVPR 2026TLMA Mitigating the Impact of Weakly Labeled Information for Video
- CVPR 2026Token Warping Helps MLLMs Look from Nearby Viewpoints
- CVPR 2026Tokenization Allows Multimodal Large Language Models to Understand Generate and
- CVPR 2026TopoHR Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving
- CVPR 2026TopoSlide Topologically-Informed Histopathology Whole Slide Image Representation Learning
- CVPR 2026Toward Low-Cost yet Effective Temporal Learning for UAV Tracking
- CVPR 2026Towards an Incremental Unified Multimodal Anomaly Detection Augmenting Multimodal Denoising
- CVPR 2026Towards Calibrating Prompt Tuning of Vision- Language Models
- CVPR 2026Towards Dynamic Modality Alignment in Multimodal Continual Learning
- CVPR 2026Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data
- CVPR 2026Towards Fine-Grained Attribution Instance-Aware Preference Optimization for Aligning Diffusion Models
- CVPR 2026Towards Generalized Multimodal Homography Estimation
- CVPR 2026Towards GUI Agents Vision-Language Diffusion Models for GUI Grounding
- CVPR 2026Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
- CVPR 2026Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion
- CVPR 2026Towards Intrinsic-Aware Monocular 3D Object Detection
- CVPR 2026Towards Knowledge-augmented Bayesian Deep Learning For Computer Vision
- CVPR 2026Towards Multimodal Domain Generalization with Few Labels
- CVPR 2026Towards Open Environments and Instructions General Vision-Language Navigation via Fast-Slow
- CVPR 2026Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset
- CVPR 2026Towards Policy-Adaptive Image Guardrail Benchmark and Method
- CVPR 2026Towards Realistic and Consistent Orbital Video Generation via 3D Foundation
- CVPR 2026Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
- CVPR 2026Towards Robust Sequential Decomposition for Complex Image Editing
- CVPR 2026Towards Robust Vision Transformers Path Dependency Analysis and a Simple
- CVPR 2026Towards Sparse Video Understanding and Reasoning
- CVPR 2026Towards Unified Human Perception and Machine Understanding Token Flow Guided
- CVPR 2026TrackMAE Video Representation Learning via Track Mask and Predict
- CVPR 2026Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI
- CVPR 2026Training-Free Open-Vocabulary Camouflaged Object Segmentation via Fine-Grained Object Binding and
- CVPR 2026Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
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。