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 3,319 篇，第 46 / 67 页
- NeurIPS 2025Surface-Aware Feed-Forward Quadratic Gaussian for Frame Interpolation with Large Motion
- NeurIPS 2025Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
- NeurIPS 2025SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
- NeurIPS 2025Switchable Token-Specific Codebook Quantization For Face Image Compression
- NeurIPS 2025SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
- NeurIPS 2025Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
- NeurIPS 2025Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
- NeurIPS 2025T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning
- NeurIPS 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
- NeurIPS 2025TabArena: A Living Benchmark for Machine Learning on Tabular Data
- NeurIPS 2025Table as a Modality for Large Language Models
- NeurIPS 2025TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields
- NeurIPS 2025Tabula: A Tabular Self-Supervised Foundation Model for Single-Cell Transcriptomics
- NeurIPS 2025TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models
- NeurIPS 2025Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
- NeurIPS 2025TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation
- NeurIPS 2025TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video
- NeurIPS 2025TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
- NeurIPS 2025Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error
- NeurIPS 2025Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
- NeurIPS 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
- NeurIPS 2025Tensor-Parallelism with Partially Synchronized Activations
- NeurIPS 2025Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation
- NeurIPS 2025Test-Time Adaptive Object Detection with Foundation Model
- NeurIPS 2025Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
- NeurIPS 2025Text to Sketch Generation with Multi-Styles
- NeurIPS 2025The Curse of Depth in Large Language Models
- NeurIPS 2025The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
- NeurIPS 2025The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
- NeurIPS 2025The Indra Representation Hypothesis
- NeurIPS 2025The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
- NeurIPS 2025The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models
- NeurIPS 2025The Promise of RL for Autoregressive Image Editing
- NeurIPS 2025The Quest for Universal Master Key Filters in DS-CNNs
- NeurIPS 2025Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
- NeurIPS 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
- NeurIPS 2025ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing
- NeurIPS 2025Thresholds for sensitive optimality and Blackwell optimality in stochastic games
- NeurIPS 2025THUNDER: Tile-level Histopathology image UNDERstanding benchmark
- NeurIPS 2025Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series
- NeurIPS 2025Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
- NeurIPS 2025Timely Clinical Diagnosis through Active Test Selection
- NeurIPS 2025Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
- NeurIPS 2025Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task
- NeurIPS 2025Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation
- NeurIPS 2025Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
- NeurIPS 2025Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis
- NeurIPS 2025Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models
- NeurIPS 2025Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs
- NeurIPS 2025Towards Evaluating Proactive Risk Awareness of Multimodal 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。