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 1,366 篇，第 8 / 28 页
- NeurIPS 2026Diving-R1: Empowering Multimodal LLMs with Traceable Progressive Reasoning for Interpretable Diving Action Quality Assessment
- NeurIPS 2026DMax: Aggressive Parallel Decoding for dLLMs
- NeurIPS 2026Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
- NeurIPS 2026Do LLMs Bind Episodes? Probing Cross-Episode Parametric Retrieval Through Shared Cues
- NeurIPS 2026Do LLMs Feel Social Pressure? Locating and Steering Social Desirability Bias in LLMs
- NeurIPS 2026Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness
- NeurIPS 2026Do multimodal models imagine electric sheep?
- NeurIPS 2026Do Reasoning LLMs Refuse What They Infer in Long Contexts?
- NeurIPS 2026Do Robust LVLMs Hallucinate More? Uncovering Robustness-Induced Hallucination in Large Vision-Language Models
- NeurIPS 2026Do You CARE to Generalize? Extracting Robust Concept Directions from LLMs
- NeurIPS 2026DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding
- NeurIPS 2026Dodge-It: Learning Collision-Aware VLA Models for Robotic Manipulation
- NeurIPS 2026Does Mixed Label Imbalance Matter to Minority Collapse in Imbalanced Learning?
- NeurIPS 2026Does Your Large Language Model Have An Intuitive Sense of The Difficulty of A Question?
- NeurIPS 2026Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
- NeurIPS 2026Doomed to Re-Annotate, Forever: The ImageNet Story
- NeurIPS 2026DPA: Decentralized Primal Averaging with Quasi-Global Momentum for Highly Heterogeneous Data
- NeurIPS 2026DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
- NeurIPS 2026Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing
- NeurIPS 2026DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
- NeurIPS 2026Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts
- NeurIPS 2026DRILL: Training World Models to Improve Policies, Not Predict Pixels
- NeurIPS 2026DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
- NeurIPS 2026DriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving
- NeurIPS 2026DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
- NeurIPS 2026DriveStreamBench: Evaluating User-Conditioned Watch-and-Notify in Streaming Driving Video
- NeurIPS 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
- NeurIPS 2026Driving Video Retrieval for Complex Queries with Structured Grounding
- NeurIPS 2026DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction
- NeurIPS 2026DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
- NeurIPS 2026Dual Dimensionality for Local and Global Attention
- NeurIPS 2026Dual-Space Preconditioning for Variational Inequalities and Root-Finding Problems
- NeurIPS 2026DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?
- NeurIPS 2026Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
- NeurIPS 2026Dynamic Model Merging Made Slim
- NeurIPS 2026Dynamic Regulatory Graph Learning for Histology-to-Spatial Transcriptomics
- NeurIPS 2026Dynamic Resolution Routing for Efficient Egocentric Grounding
- NeurIPS 2026Dynamics-Aware Sparse Attention for Efficient Autoregressive Video Diffusion
- NeurIPS 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
- NeurIPS 2026DynaProto: Dynamic Prototypical Contrast for Temporally Consistent Object-Centric Learning
- NeurIPS 2026E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion
- NeurIPS 2026EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
- NeurIPS 2026ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
- NeurIPS 2026EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function
- NeurIPS 2026Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
- NeurIPS 2026EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth
- NeurIPS 2026EDMA: Entropy-Driven Multimodal Answering
- NeurIPS 2026EEG-X: Toward Device-Agnostic and Noise-Robust Foundation Models for EEG
- NeurIPS 2026Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization
- NeurIPS 2026Efficient Image Synthesis with Sphere Latent Encoder
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。