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 5,190 篇，第 83 / 104 页
- NeurIPS 2026Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
- NeurIPS 2026Controlling for Omitted Variable Bias in Deep Neural Networks
- NeurIPS 2026CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelling
- NeurIPS 2026CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy
- NeurIPS 2026CoRDS: Coreset-Based Representative and Diverse Selection for Streaming Video Understanding
- NeurIPS 2026CoRE-RL: Co-evolving Reasoning Trajectories and Evidence Subgraphs with Learned Evidence Projection
- NeurIPS 2026Coresets for Clustering Using Noisy Comparisons and Few Distance Queries
- NeurIPS 2026Correpondence Alignment For Improved Virtual Try-On
- NeurIPS 2026Correspondence Pruning by Iterative Structural Rectification
- NeurIPS 2026CoScan: Multi-Scale Content-Adaptive Space-Filling Scans for Causal State-Space Image Restoration
- NeurIPS 2026Counterfactual Instruction Grounding for Vision-Language-Action Models
- NeurIPS 2026Counting without Scale: Scale-Consistent Error Correction for Crowd Counting
- NeurIPS 2026Coverage-Based Calibration for Post-Training Quantization via Weighted Maximum Coverage over Outlier Channels
- NeurIPS 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
- NeurIPS 2026Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
- NeurIPS 2026CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
- NeurIPS 2026CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
- NeurIPS 2026CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
- NeurIPS 2026CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
- NeurIPS 2026Cross-Channel Agreement Beats Consensus: Compositional Verification for Geometry Reasoning
- NeurIPS 2026Cross-Distribution Generalization in Longitudinal Behavioral Data Through Frozen Coherence Constraints
- NeurIPS 2026Cross-Layer Evolution Graph Learning for Fine-grained VLM Hallucination Detection
- NeurIPS 2026Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud Registration
- NeurIPS 2026Cross-Model Transfer Attacks against Large Vision-Language Models via Model Diversity Enrichment and Stochastic Parameter Sampling
- NeurIPS 2026CrossID: Cross-Supervised Spatio-Temporal Gated Fusion for Personalized Portrait Generation
- NeurIPS 2026CryptanalysisBench: Can LLMs do cryptanalysis?
- NeurIPS 2026CSBench: A Comprehensive Benchmark for Evaluating Project-Level System Construction in Computer Science
- NeurIPS 2026CSI-TextBench: A Dataset and Benchmark for Language-Grounded Ambient Sensing Perception
- NeurIPS 2026CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness
- NeurIPS 2026CURE: Visual Reprogramming of Vision-Language Models under Limited Supervision
- NeurIPS 2026Curvature Beyond Positivity: Greedy Guarantees for Arbitrary Submodular Functions
- NeurIPS 2026CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
- NeurIPS 2026D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
- NeurIPS 2026D-VLA: A High-Concurrency Distributed Asynchronous RL Framework for Vision-Language-Action Models
- NeurIPS 2026D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
- NeurIPS 2026DAG-Biased Graph Learning for Multimodal Survival on EHR
- NeurIPS 2026DAGA: Dynamic Attention-Guided Adaptation for Self-Supervised Vision Transformers
- NeurIPS 2026DARE: Dual-Level Adversarial Learning with Domain-Aware Regularization for Whole Slide Image Classification
- NeurIPS 2026DataComp-VLM: Improved open datasets for Vision-Language Models
- NeurIPS 2026DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
- NeurIPS 2026DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
- NeurIPS 2026Debiased DPO for Diffusion Models
- NeurIPS 2026Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models
- NeurIPS 2026Decoupled Prototype Contrastive Alignment Hashing for Cross-Modal Retrieval
- NeurIPS 2026Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality
- NeurIPS 2026DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models
- NeurIPS 2026DegBins: Degradation-Driven Binning for Depth Super-Resolution
- NeurIPS 2026Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
- NeurIPS 2026DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
- NeurIPS 2026DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
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。