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 26 / 28 页
- CVPR 2026UniGame Turning a Unified Multimodal Model Into Its Own Adversary
- CVPR 2026UniGenDet A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and
- CVPR 2026UniGeoRS A Unified Benchmark for Tri-view Geo-Localization
- CVPR 2026UniGeoSeg Towards Unified Open-World Segmentation for Geospatial Scenes
- CVPR 2026UniLDiff Unlocking the Power of Diffusion Priors for All-in-One Image
- CVPR 2026UniRefiner Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
- CVPR 2026UniSER A Foundation Model for Unified Soft Effects Removal
- CVPR 2026Universal 3D Shape Matching via Coarse-to-Fine Language Guidance
- CVPR 2026Universal-to-Specific Dynamic Knowledge-Guided Multiple Instance Learning for Few-Shot Whole Slide
- CVPR 2026UniVerse Empower Unified Generation with Reasoning and Knowledge
- CVPR 2026Unlearning without Forgetting Securely Removing Targeted Concepts from Large-Scale Vision-Language
- CVPR 2026Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language
- CVPR 2026Unleashing Vision-Language Semantics for Deepfake Video Detection
- CVPR 2026Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from
- CVPR 2026Unlocking Motion from Large Vision Models with a Semantic and
- CVPR 2026Unsafe2Safe Controllable Image Anonymization for Downstream Utility
- CVPR 2026Unstitching the Chimera Frame-Level Risk and Train-Free Mitigation for Video
- CVPR 2026URICA A Uniformity Region Affine Identifier Capture Algorithm for Arbitrary
- CVPR 2026UTPTrack Towards Simple and Unified Token Pruning for Visual Tracking
- CVPR 2026UVU Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
- CVPR 2026UZ3DVG Unaided Zero-Shot 3D Visual Grounding with Generated Language Conditions
- CVPR 2026V-Attack Targeting Disentangled Value Features for Controllable Adversarial Attacks on
- CVPR 2026Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
- CVPR 2026VAST Video Ability-Stratified Taxonomy for Data-Efficient Video Reasoning
- CVPR 2026VCP-Attack Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large
- CVPR 2026Vector Prism Animating Vector Graphics by Stratifying Semantic Structure
- CVPR 2026VectorArk Learning Practical Image Vectorization with Rounded Polygon Representation
- CVPR 2026Venus Benchmarking and Empowering Multimodal Large Language Models for Aesthetic
- CVPR 2026VES-RFT Rewarding Visual Evidence Sensitivity to Mitigate Hallucinations in Large
- CVPR 2026VGA-Bench A Unified Benchmark and Multi-Model Framework for Video Aesthetics
- CVPR 2026VGent Visual Grounding via Modular Design for Disentangling Reasoning and
- CVPR 2026VGGDrive Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous
- CVPR 2026VIAFormer Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinement
- CVPR 2026Vibe Spaces for Creatively Connecting and Expressing Visual Concepts
- CVPR 2026Video-as-Answer Predict and Generate Next Video Event with Joint-GRPO
- CVPR 2026Video-Only ToM Enhancing Theory of Mind in Multimodal Large Language
- CVPR 2026VideoFusion A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion
- CVPR 2026VideoITG Multimodal Video Understanding with Instructed Temporal Grounding
- CVPR 2026VidEoMT Your ViT is Secretly Also a Video Segmentation Model
- CVPR 2026VideoNet A Large-Scale Dataset for Domain-Specific Action Recognition
- CVPR 2026VideoWeaver Multimodal Multi-View Video-to-Video Transfer for Embodied Agents
- CVPR 2026VidPrism Heterogeneous Mixture of Experts for Image-to-Video Transfer
- CVPR 2026VidTAG Temporally Aligned Video to GPS Geolocalization with Denoising Sequence
- CVPR 2026ViHOI Human-Object Interaction Synthesis with Visual Priors
- CVPR 2026ViRC Enhancing Visual Interleaved Mathematical CoT with Reason Chunking
- CVPR 2026VIRO Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring
- CVPR 2026VIRST Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation
- CVPR 2026VirtueBench Evaluating Trustworthiness under Uncertainty in Long Video Understanding
- CVPR 2026VISion On Request Enhanced VLLM efficiency with sparse dynamically selected
- CVPR 2026Vision Transformers Need More Than Registers
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。