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 95 / 104 页
- NeurIPS 2026Patch4Patch: Restoring Structural Connectivity in Patch-based Vision Encoders
- NeurIPS 2026PatchKV: Weight Space Compensation of KV Cache
- NeurIPS 2026PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
- NeurIPS 2026Pathways of Visual Information Flow in Vision-Language Models
- NeurIPS 2026PAVE: Prefill-Conditioned Activation Editing for Hallucination Mitigation in LVLMs
- NeurIPS 2026PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image Fusion
- NeurIPS 2026PCFBench: How Far Can Large Vision-Language Models Go in Physics-aware Photonic Inverse Design?
- NeurIPS 2026Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation
- NeurIPS 2026Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning
- NeurIPS 2026Personal Visual Memory from Explicit and Implicit Evidence
- NeurIPS 2026Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding
- NeurIPS 2026PerturbReason: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects
- NeurIPS 2026PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization
- NeurIPS 2026Phase-Adaptive Fusion: Spatio-Temporal Modulation for VLA Models
- NeurIPS 2026PHOEBI: An Open-World Benchmark for Multi-Label Bacterial Identification in Phase-Contrast Microscopy
- NeurIPS 2026PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos
- NeurIPS 2026PhysDNet: Physics-Driven Gradient Amplification for Real-Time Image Dehazing
- NeurIPS 2026PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?
- NeurIPS 2026PhysGraphNet: Physical-State Scene Graphs via Latent Graph Reasoning and Counterfactual Supervision
- NeurIPS 2026PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
- NeurIPS 2026PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video
- NeurIPS 2026PipeFSDP: Efficient Pipeline Parallel under Fully Sharded Data Parallel for Large Language Model Training
- NeurIPS 2026PIS: Pose-Interpolation Smoothness for Skinning Weight Refinement
- NeurIPS 2026PIU-CR: Physics-Informed Deep Unfolding Network with SAR-Optical Image Fusion for Cloud Removal
- NeurIPS 2026PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
- NeurIPS 2026PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation
- NeurIPS 2026PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
- NeurIPS 2026PLACE: Patch-Level Agnostic Concept Extraction
- NeurIPS 2026Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
- NeurIPS 2026PM1: A Multimodal Foundation Model for Genomes, Phenotypes, and Images at Biobank Scale
- NeurIPS 2026Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
- NeurIPS 2026Polar Transformers: $SO(2)^K$-Equivariant Angular Attention for Cryo-EM Image-Set Processing
- NeurIPS 2026PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation
- NeurIPS 2026Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
- NeurIPS 2026PolyVision: Conditional Visual Scaling Via Dynamic Expert Routing For Vision-Centric MLLMs
- NeurIPS 2026Pose6DAug: Physically Plausible Multi-View Object Swapping for Robot Data Augmentation
- NeurIPS 2026Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases
- NeurIPS 2026Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
- NeurIPS 2026Post-hoc Selective Classification for Reliable Synthetic Image Detection
- NeurIPS 2026Post-Training Quantization with Gradient-Projected Fisher Approximation for Vision Transformers
- NeurIPS 2026POST: Progressive Object-Slot Tokenization for Multimodal Large Language Models
- NeurIPS 2026Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
- NeurIPS 2026Predicting Quantization Price for Selecting PTQ Configurations Before Deployment
- NeurIPS 2026Prefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers
- NeurIPS 2026Principia: Relational Physics Tests for Video Models
- NeurIPS 2026Prior Text-Informed Gate Attention Framework for Multimodal Psychiatric Disorder Diagnosis
- NeurIPS 2026PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
- NeurIPS 2026Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
- NeurIPS 2026PRISM: Primitive Routing via In-context Skill Mixing for Lifelong VLA
- NeurIPS 2026PriSM: Prior-guided Shared-basis Mixture Personalization for LLMs under Sparse User Histories
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。