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 12 / 67 页
- NeurIPS 2026H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
- NeurIPS 2026Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
- NeurIPS 2026HalluciText: Mitigating Text Hallucinations in Diffusion-Based Image Restoration
- NeurIPS 2026HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing
- NeurIPS 2026HandXFM: Semantic-Structural Distillation for Hand Radiograph Foundation Models
- NeurIPS 2026HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies
- NeurIPS 2026Harder the Task, Sparser the Representation: Sparsity as a Learning Signature of Capability in LLMs
- NeurIPS 2026Harmonic Torsional Diffusion for Flexible Protein-Ligand Docking
- NeurIPS 2026Harnessing Image Diffusion Prior for Photo-Realistic Video Restoration
- NeurIPS 2026Harnessing Textual Refusal Directions for Multimodal Safety
- NeurIPS 2026Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-visual LLMs
- NeurIPS 2026HearSayBench: Can LLMs Navigate from Abstract Human Rights to Lived Lives?
- NeurIPS 2026HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
- NeurIPS 2026HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
- NeurIPS 2026HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
- NeurIPS 2026Heterogeneous Parallelism for Multimodal Large Language Model Training
- NeurIPS 2026Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
- NeurIPS 2026Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
- NeurIPS 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
- NeurIPS 2026Hider–Seeker Self-Play: Geometry-Verifiable Process Rewards for Long-Horizon Visual Search
- NeurIPS 2026Hierarchical Adaptive Frame Sampling For Video Understanding
- NeurIPS 2026Hierarchical Cross-Class Part Alignment for Prototypical Part Networks via Hyperbolic Entailment
- NeurIPS 2026Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
- NeurIPS 2026HIFC-IQA: Train-Free Cross-Domain Image Quality Assessment via Dual-Process Cognition
- NeurIPS 2026HiFloat4 Format for Language Model Pre-training on Ascend NPUs
- NeurIPS 2026HiLoc: A Hierarchical Representation Method for Spatial Localization in Multimodal Large Language Models
- NeurIPS 2026HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding
- NeurIPS 2026HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement
- NeurIPS 2026HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
- NeurIPS 2026HOPE: Hand-Object Pressure Estimation from Monocular Videos
- NeurIPS 2026How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
- NeurIPS 2026How Does Pruning Change Decisions in Large Language Models?
- NeurIPS 2026How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
- NeurIPS 2026How Much is Left? LLMs Linearly Encode Their Remaining Output Length
- NeurIPS 2026How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
- NeurIPS 2026How Private is Private? A Comparative Study for Face De-Identification
- NeurIPS 2026How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
- NeurIPS 2026How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction
- NeurIPS 2026HPC-Bench: A Comprehensive Benchmark for High Performance Computing Codes
- NeurIPS 2026HRIL: Isolating Multimodal Synergy via Higher-Order Dependence
- NeurIPS 2026Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating
- NeurIPS 2026HybridCache: Enhancing Prefix Caching for Linear–Softmax Language Models
- NeurIPS 2026Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
- NeurIPS 2026Hyperbolic Displacement-Constrained Adaptation for CLIP-Based Class-Incremental Learning
- NeurIPS 2026Hypernetworks for Dynamic Feature Selection
- NeurIPS 2026HyperTransport: Amortized Conditioning of T2I Generative Models
- NeurIPS 2026HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion
- NeurIPS 2026HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression
- NeurIPS 2026HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
- NeurIPS 2026i-DEQ: A stable inertial Deep Equilibrium model for image restoration
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。